SIGGEN: Newsletter Archive

The following issues of the SIGGEN newsletter are available:

2005

Issue 1

SIGGEN Newsletter

www.siggen.org

Date: 05 June 2005

---

TOPICS:

1. INF: Recent SIGGEN updates; board election, state of SIGGEN

2. CfB: Call for Bids for INLG'06

3. CfP: EWNLG'05 in Aberdeen [Early Registration by June 17]

4. CfP: Symposium on Dialog Modeling and Generation [July 7]

5. CfP: Using Corpora for Natural Language Generation [July 14]

6. TUT: Statistical Machine Translation and Generation [Aug. 11]

7. JOB: Postdoctoral Position in Adaptive Spoken Language, NY

8. JOB: Research Fellow/PostDoc, Aberdeen

9. Stu: Funded Studentship, Aberdeen

10. ANN: Surge 2.3 now available

---

SIGGEN Board Members:
Tilman Becker	Tilman.Becker(at)dfki(dot)de
Charles Callaway	ccallawa(at)inf(dot)ed(dot)ac(dot)uk
Irene Langkilde-Geary	irenelg(at)cs(dot)byu(dot)edu
David McDonald	dmcdonald(at)bbn(dot)com
David Reitter	dreitter(at)inf(dot)ed(dot)ac(dot)uk

---

TOPIC 1: Recent SIGGEN updates; board election, state of SIGGEN

Dear SIGGEN members,

Tilman Becker, the last remaining member from the previous SIGGEN board, has been joined by the 4 new board members from this winter's election: Charles Callaway, Irene Langkilde-Geary, David McDonald, and student representative Dave Reitter.

As mentioned before, the website has been moved to www.siggen.org, (change your bookmarks!) hosted at DFKI, and has been updated, most significantly in regards to the membership on the Who's who page. This page, which now lists 145 members, has been revamped to ensure that all links are valid. If you, or someone you know, would like to be added to this list, please don't hesitate to email us. The mailing list has been similarly checked to ensure valid email addresses, and now contains 209 members. This means that those who do not receive copies of this newsletter are not currently on the email list, not considered to be members, and thus cannot vote in future elections. (A copy of the current SIGGEN constitution is located at: http://www.siggen.org/discussion/constitution/constitution_v2.html)

Your board members will be attending a wide array of conferences this summer, so if you see us, please don't hesitate to talk to us, or of course send us email. We will quickly respond to any suggestions or comments you may have.

-- The SIGGEN Board

---

TOPIC 2: SIGGEN: Call for Bids to Host INLG-2006

http://www.siggen.org/event/bidinlg06.html

SIGGEN (Special Interest Group in Generation of the Association for Computational Linguistics) invites proposals to host the International Natural Language Generation (INLG) Conference in 2006. INLG conferences are usually held in the summer, and sometimes co-located with other NLP events, such as ACL. INLG attendance is usually on the order of 80 people (that is, more than 50 and less than 120).

As INLG-2004 was in the ACL European region, we especially welcome and will prefer proposals for holding INLG-2006 in the ACL Americas or Asia/Pacific regions.

Draft proposals should be emailed to ccallawa(at)inf(dot)ed(dot)ac(dot)uk by 30 Sept 2005.

These proposals should outline:

* conference location and practicalities (venue, accomodation, meals). Note that INLG's have traditionally been held in places which are secluded but easily accessible (within a few hours drive of a major international airport), such as Brighton, UK (2004); mid-State New York (2002); Mitzpe Ramon, Israel (2000); Niagara-on-the-Lake, Canada (1998); Hertsmonceux Castle, UK (1996); and Kennebunkport, USA (1994).

* approximate conference date. Will it be possible for INLG attendees to combine attendance at INLG with attendance at other conferences of interest to the NLG community (for example, INLG-02 immediately preceded ACL-02, INLG-98 immediately preceded ACL-98, and INLG-92 immediately followed ANLP-92).

* rough budget and expected sponsorship. Approximately how much will participants need to pay to attend, including accomodation and meals as well as conference registration? Note that attendance cost for previous INLG's has generally been US$500 or less.

* local arrangements. Who will be in charge of organising the conference, and how will finances be handled (eg, can participants pay by credit card)?

Draft proposals will be considered by a committee that includes some SIGGEN board members and previous INLG chairs. This committee may contact proposers and request additional information.

For more information, see:

* http://www.itri.brighton.ac.uk/inlg04/ for information about INLG-2004.

* http://inlg02.cs.columbia.edu/ for information about INLG-2002.

* http://www.dfki.de/~wahlster/bids/ for draft bids for ACL-01 (a bit different from INLG draft bids, but useful as examples).

---

TOPIC 3: EWNLG'05 in Aberdeen [Early Registration by June 17]

Call for Participation

8-10 August 2005 Aberdeen, Scotland (following IJCAI-2005 in Edinburgh) http://www.ling.helsinki.fi/~gwilcock/ENLG-05/

Natural language generation (NLG) is a subfield of natural language processing that focuses on the generation of written texts in natural languages from some underlying non-linguistic representation of information, generally from databases or knowledge sources. Accomplishing this goal may be envisioned for a number of different purposes, including standardized and/or multi-lingual reports, summaries, machine translation, dialogue applications, and embedding in multi-media and hypertext environments. Consequently, the automated production of language is associated with a large number of highly diverse tasks whose appropriate orchestration in high quality poses a variety of theoretical and practical problems. Relevant issues include content selection, text organization, production of referring expressions, aggregation, lexicalization, and surface realization, as well as coordination with other media.

The workshop continues a biennial series of workshops on natural language generation that has been running since 1987. Previous European workshops have been held at Royaumont, Edinburgh, Judenstein, Pisa, Leiden, Duisburg, Toulouse (2001) and Budapest (2003). The series provides a regular forum for presentation of research in this area, both for NLG specialists and for researchers who may not think of themselves as part of the NLG community.

The 2005 workshop will span the interest areas of natural language generation and Artificial Intelligence, with a special focus on research that integrates NLG with AI, including vision, robotics, intelligent agents, and knowledge discovery. We also encourage papers that investigate the use of state-of-the-art generation technology in real world applications to handle both spoken and text output, and apply language generation techniques to interactive AI systems like communicating robots, to allow the user to enter into short conversations with the system in search for information. There will be demonstrations of working NLG systems, and special sessions for posters describing real-world applications and advanced language technology systems.

Papers will be presented on formal, corpus-based, implementational and analytical work on conventional NLG topics (realisation, microplanning, etc), and especially papers with a focus on the following themes:

* Embodied agents and robot communication (special track)

* NLG for real-world applications

* Use of ontologies in NLG

* Statistical methods for NLG

* Information organization for planning and NLG

* Robust methods and techniques for NLG

* Evaluation of NLG systems

Invited Speaker:

Kevin Knight (Information Sciences Institute, University of Southern California) will give an invited talk on Tree Transducers for Machine Translation and Generation

---

TOPIC 4: Symposium on Dialogue Modelling and Generation

Call for Participation

July 7, Amsterdam, The Netherlands

http://lubitsch.lili.uni-bielefeld.de/DMG/

This symposium is intended to tackle issues in the semantics and pragmatics of dialogue and dialogue generation. It aims at bringing together the dialogue modelling and language generation/production communities and will provide an opportunity for researchers from a variety of disciplines, including linguistics, computer science and psycholinguistics, to exchange ideas.

We invited talks elaborating on important theoretical notions in dialogue modelling -such as constraints (Asher & Lascarides, 2003, and many other recent papers), the role of domain knowledge (e.g., Ludwig, 2003, and, again, many more) and the influence of social relations between interlocutors on dialogue behaviour (going back to the seminal work by Brown and Levinson, 1978)- and asked presenters to shed light on these or other theoretically fruitful notions in dialogue modelling by:

* relating them to issues in language generation/production or

* drawing out similarities and differences between applications of such notions in discourse generation versus interpretation or

* describing computational/implemented models, in particular, for generation/production or

* comparing psycholinguistic with linguistic or engineering approaches to dialogue modelling.

The symposium will thus be a natural complement to ones that deal with natural language interpretation or structural properties of discourse.

---

TOPIC 5: Using Corpora for Natural Language Generation

Call for Participation

July 14, Birmingham, England (preceding Corpus Linguistics 2005) http://www.itri.brighton.ac.uk/ucnlg/

We aim to bring together researchers who use corpora for NLG research either in the traditional, manual way, or automatically, involving machine learning and statistical methods. The goal of the workshop is to present and discuss current research, to compare manual and automatic corpus exploitation, to evaluate achievements, and to identify challenges for the future.

Registration is open at the Corpus Linguistics 2005 website. Please note that Using Corpora for NLG is a full-day workshop, and that you do not need to register for the main conference. Simply select the appropriate options in the registration form. The workshop registration fee is 70 Pounds.

Papers will be presented on all aspects of using corpora for natural language generation, including, but not limited to:

* (Partial) automation of traditional corpus analysis for NLG

* Issues in annotating corpora for NLG

* Statistical approaches to deep and/or surface generation

* Machine learning methods for deep and/or surface generation

* Role of corpora in the evaluation of NLG systems

* Reuse of resources developed for NLU (e.g. treebanks) in NLG

* Domain-specific vs. general purpose corpora for NLG

We would like to emphasise that where we say `NLG' we mean to include the language generation components of machine translation and dialogue systems.

Invited Speaker:

Irene Langkilde-Geary (Brigham Young University, Provo, USA) will give an invited talk with the provisional title: Constraint programming as a Whiteboard Architecture for Probabilistic NLG.

Panel on Exploiting Corpora for NLG:

We will hold a panel discussion on the topics of the workshop. The panel members are:

Chris Brew, Linguistics, Ohio State University, USA

Irene Langkilde-Geary, Brigham Young University, USA

Ehud Reiter, Computing Science, University of Aberdeen, UK

Donia Scott, CRC, Open University, UK

Bonnie Webber, Informatics, University of Edinburgh, UK

---

TOPIC 6: Tutorial: Statistical Machine Translation and Generation

August 11, Aberdeen, Scotland (Immediately following EWNLG'05)

http://www.csd.abdn.ac.uk/~cmellish/knight.html

Kevin Knight, USC/Information Sciences Institute, USA

The statistical approach to machine translation provides a set of techniques for (1) automatically learning translation knowledge from bilingual data, and (2) applying that knowledge to translate previously-unseen sentences. When it was first introduced, statistical MT was far too slow and inaccurate to be useful -- it was an interesting lab experiment. In 2005, we see statistical MT significantly outperforming other methods in many language pairs and domains, at speeds permitting commercial applications like foreign news broadcast translation. What made this possible? This tutorial will cover the basic theory and the major technical advances of the past few years. Of course, there is a long way to go! The tutorial will also cover known limitations of current MT models and describe current research trends. We will also discuss problems in natural language generation, where the input is typically more abstract than foreign text, and describe how statistical MT research is currently exploiting linguistic categories.

This tutorial is free of charge. It is hosted by the Natural Language Generation group at the University of Aberdeen. We are grateful for the support of EPSRC grant EP/C523156/1 which has made this tutorial possible.

If you are interested in attending this tutorial, please send an email to ccameron(at)csd(dot)abdn(dot)ac(dot)uk so that you can be allocated a place and informed of any further developments. For more information, contact Chris Mellish (cmellish(at)csd(dot)abdn(dot)ac(dot)uk).

---

TOPIC 7: Postdoctoral Position in Adaptive Spoken Language

StonyBrook, NY

The Psychology, Linguistics, and Computer Science Departments at Stony Brook University are collaborating on an innovative project, funded by the National Science Foundation: "Adaptive Spoken Dialog with Human and Computer Partners." We seek a postdoctoral associate to collaborate with us. The successful applicant will have a Ph.D. in Psychology, Linguistics, or Computer Science, or a relevant interdisciplinary field.

Preferred Qualifications: Experience in one or more of the following: experiment design, statistics, linguistic phonetics, computational linguistics, speech processing, psycholinguistics techniques such as eyetracking.

Depending on the candidate's background and qualifications, duties will include:

1) Contributing to empirical (laboratory and corpus-based) studies of language use (both comprehension and production). This involves working with human subjects, designing experiments, collecting data, and conducting detailed analyses of text and spoken corpora

2) Contributing to our efforts to model human language behavior and test computational models using data.

3) Generating independent sub-projects relevant to project's research questions.

4) Supervising graduate and undergraduate student researchers in day-to-day activities across one or more projects conducted within the PI's laboratories

5) Assisting with management of laboratory resources, such as ordering equipment, software installation, etc.

6) Writing up results for publication

7) Traveling to conferences and workshops as appropriate

8) Developing expertise in relevant techniques and procedures that span Psychology, Linguistics, and Computer Science

This is a full time position. The Research Foundation of SUNY is a private educational corporation. Employment is subject to the Research Foundation policies and procedures, sponsor guidelines, and availability of funding. Projected start date: January 1, 2006 (flexible)

Application Procedure: Applications will be accepted until the position is filled. More details about the project can be found at http://www.cs.sunysb.edu/~adaptation/. Applications for the may be submitted on-line at http://naples.cc.sunysb.edu/Admin/CampusJob.nsf via the "Postdoctoral positions" link, or else submit a cover letter and resume to:

Prof. Susan E. Brennan

Department of Psychology

Stony Brook University

Stony Brook, New York 11794-2500

Fax: 631-632-7876

Stony Brook University, flagship campus of the S.U.N.Y. system, is a world-class, student-centered research university located 60 miles from New York City.

---

TOPIC 8: Research Fellow/PostDoc: Towards a Unified Algorithm for the generation of referring expressions

University of Aberdeen, Scotland

Applications due: July 15, 2005

Contact: Dr Kees van Deemter

kvdeemte(at)csd(dot)abdn(dot)ac(dot)uk

Background:

Natural Language Generation programs generate text from an underlying Knowledge Base. It can be difficult to find a mapping from the information in the Knowledge Base to the words in a sentence. Difficulties arise, for example, when the Knowledge Base uses `names' (i.e., databases keys) that a hearer/reader does not understand. This can happen, for instance, if the Knowledge Base contains an artificial name like `#Jones083', because `Jones' alone is not uniquely distinguishing; it is also true if the Knowledge Base deals with entities for which no names at all are in common usage (e.g., a specific tree or a chair). In all such cases, the program has to "invent" a description that enables the reader to identify the referent. In the case of Mr. Jones, for example, the program could give his name and address; in the case of a tree, some longer description may be necessary (e.g., `the green oak on the corner of ... and ...'. The technical term for this set of problems is Generation of Referring Expressions (GRE). GRE is a key aspect of almost any Natural Language Generation system.

Aims:

Existing GRE algorithms tend to focus on one particular class of referring expressions, for example conjunctions of atomic or relational properties (e.g., `the black dog', `the book on the table'). Our research is aimed at designing and implementing a new algorithm for the generation of referring expressions that generates appropriate descriptions in a far greater variety of situations than any of its predecessors. The algorithm will be more complete than its predecessors because it is able to construct a greater variety of descriptions (involving negations, disjunctions, relations, vagueness, etc.). The descriptions generated should also be more appropriate (i.e., more natural in the eyes of a human hearer/reader), because the algorithm will be based on empirical studies involving corpora and controlled experiments. Among other things, these empirical studies will address the question under what circumstances the descriptions should be logically under- or overspecific; they will also allow us to prune the search space (i.e., the space of all descriptions) which would otherwise threaten to make the problem intractible. The project combines (psycho)linguistic, computational and logical challenges and should be of interest to people whose intellectual home is in either of these areas.

General Info:

http://www.itri.brighton.ac.uk/projects/tuna/TUNA-index.html

---

TOPIC 9: Funded Studentship: Managing Ambiguity in Generated Text

University of Aberdeen, Scotland

Applications due: July 15, 2005

Contact:	Dr Kees van Deemter
	kvdeemte(at)csd(dot)abdn(dot)ac(dot)uk

General Info for prospective students at Aberdeen:

http://www.abdn.ac.uk/sras/postgraduate/apply5

---

TOPIC 10: Surge 2.3 now available for download

Contact:	Charles Callaway
	ccallawa(at)inf(dot)ed(dot)ac(dot)uk

Surge 2.3, the latest version of the SURGE English grammar, has been packaged for download at the following location. Improvements have been made for written and spoken dialogue, XML and LATEX formatting, punctuation, and additional coverage rules derived from the Penn TreeBank. For use with FUF5.3.

http://homepages.inf.ed.ac.uk/ccallawa/index-c.html

--- eof ---

1998

Issue 1

Date: 25 Mar 1998

---

TOPICS:

1. A: INLG Registration & Program [Act by May 1st 1998]

2. CFP: TAG+ Workshop [Philadelphia - Deadline Apr 15th 1998]

3. A: CSLU Spring Short Courses [Portland, OR - May 5 - May 18]

4. JOB: ITRI Brighton PhD Studentship [Apply by Apr 30, 1998]

5. CFP: COLING/ACL98 Discourse Relations Workshop [Deadline Apr 6]

6. CFP: Special issue NRHM Adaptivity and User Modeling [Deadline Jun 1]

7. CFP: Computational Treatment of Portuguese - Brazil [Deadline May 4]

8. A: KPML Mailing List

9. P: Diana McKinnie [Generating reports from dictated X-ray reports]

---

---

TOPIC 1:

A: INLG Registration & Program [Act by May 1st 1998]

From: Graeme Hirst <gh(at)cs(dot)toronto(dot)edu>

9th International Workshop on

NATURAL LANGUAGE GENERATION

5-7 August 1998

Prince of Wales Hotel

Niagara-on-the-Lake, Ontario, Canada

REGISTRATION INFORMATION

Preliminary details of the program and registration information and forms are now available for the 9th biennial Workshop on Natural Language Generation.

This message gives basic information on participation. For full information, please visit the INLG-98 Website:

http://logos.uwaterloo.ca/~inlg98

PROGRAM AND SCHEDULE:

The workshop will begin with an opening reception on the evening of Tuesday 4 August, and end with lunch on Friday 7 August.

The program includes approximately 30 papers, demonstrations, and a panel session to be presented over 2 1/2 days. (The complete list of accepted papers is on the conference Web site.)

In addition, the social program includes an outing to Niagara Falls with dinner at the top of the Skylon Tower.

LOCATION AND TRANSPORTATION:

The workshop will be held at the Prince of Wales Hotel, in the scenic town of Niagara-on-the-Lake, which is easily accessible from Toronto International Airport. See our Web page on transportation for details of transfers to Niagara-on-the-Lake from Toronto International Airport, on Buffalo Airport as an alternative, and for directions to Niagara-on-the-Lake by car, bus, and train.

REGISTRATION AND ACCOMMODATION:

A discount accommodation-and-meal package has been negotiated with the Prince of Wales Hotel for the workshop. To get the discount, you must book your accommodation on the conference registration form, which is available from our Web site.

Registration paid by credit card will be accepted by e-mail and fax.

NOTE!!! Space at the workshop is limited. We will allocate space in the order that registrations are received, except that a space will be held for one author of each submitted paper (whether accepted or not) until **1 May 1998**. If the workshop is oversubscribed before the final June deadline, we will endeavour to find additional space, but cannot promise to succeed nor that any space found will be as cheap as the reserved space. Workshop registration and hotel reservations must be received by **1 June 1998**. Any unassigned hotel rooms will be released after this date. Late registrants will be accommodated only if space is available, and will have to pay the hotel's full rack rates.

FINANCIAL ASSISTANCE:

We anticipate having funds to subsidize attendance at the workshop by graduate students and unfunded researchers. Details should be known by mid-April.

TOURISM:

See the INLG Web pages for links to information on tourism in the Niagara region, Toronto, and Montreal.

TRANSPORTATION TO MONTREAL FOR COLING:

The workshop is to be held in the week immediately prior to the joint conference of COLING and ACL, in Montreal, Canada (10-14 August 1998). After the workshop, a bus will take participants who wish to attend COLING / ACL directly to the Toronto train station for an express train to Montreal.

WORKSHOP SPONSOR AND ORGANIZERS:

The workshop is sponsored by the Association for Computational Linguistics and ACL SIGGEN (Special Interest Group on Natural Language Generation).

The workshop is organized by Chrysanne DiMarco of the University of Waterloo, with the assistance of Graeme Hirst of the University of Toronto. The Program Chair is Eduard Hovy of USC/ISI.

General enquiries concerning registration and accommodation:

Jean Webster, University of Waterloo

jrwebster(at)icr(dot)uwaterloo(dot)ca

phone +1 519-888-4567 extension 5076.

General workshop questions:

Chrysanne DiMarco, University of Waterloo

cdimarco(at)logos(dot)uwaterloo(dot)ca

phone +1 519 888 4443

For more information, program, and registration forms, visit the INLG-98 Website:

http://logos.uwaterloo.ca/~inlg98

---

TOPIC 2:

CFP: TAG+ Workshop [Philadelphia - Deadline Apr 15th 1998]

From: Jennifer MacDougall <jmacdoug(at)central(dot)cis(dot)upenn(dot)edu>

TAG+ WORKSHOP -- FIRST CALL FOR PAPERS

August 1 to August 3, 1998

TAG TUTORIALS -- PRELIMINARY ANNOUNCEMENT

July 28 to July 31, 1998

Philadelphia, PA, USA

URL: http://www.cis.upenn.edu/~ircs/mol/tag98.html

The fourth workshop on tree-adjoining grammars and related frameworks (hence the + after TAG) will be held at the Institute for Research in Cognitive Science at the University of Pennsylvania in August 1998, from August 1 to August 3. Previous workshops were held at Dagstuhl (1990), UPenn (1992), and Univ. Paris 7 (1994).

Papers on all aspects of TAG (linguistic, mathematical, computational, and applicational), as well as papers relating TAGs to other frameworks, are invited. As in the past there will be some invited talks on other grammar formalisms which have interesting relationships to TAGs (for example, Categorial Grammars and HPSG).

GUIDELINES FOR ABSTRACTS:

Abstracts should be at most two pages (exclusive of references), and should be submitted in ASCII format, as a .ps file, or as SELF-CONTAINED latex file to jmacdoug (at) central (dot) cis (dot) upenn (dot) edu. (If email is not available, please send the abstract to the address given below.) Please indicate on the abstract if you would prefer to give a short presentation (10 minutes) or a long one (30 minutes). The abstract should contain your name, address, and email address. Proceedings including extended versions (4 pages) of accepted abstracts will be available at the workshop.

Deadline for submission for abstracts:	April 15
Notification of acceptance:	May 15
Deadline for submission of camera-ready
extended abstract:	July 6
Workshop Dates:	August 1 to August 3

If you do not want to submit an abstract, but would like to attend, we would appreciate it if you could inform us by email by July 6 (unless you have already done so). If you would like to present a demo, please let us know as soon as possible, including information about required hard and software.

PROGRAM COMMITTEE:

Anne Abeille (Universit'e Paris 7)

Tilman Becker (DFKI)

Christy Doran (University of Pennsylvania)

Robert Frank (Johns Hopkins University)

Klaus Netter (DFKI)

Richard Oehrle (University of Arizona)

Owen Rambow (CoGenTex, Inc.)

Giorgio Satta (Universita di Padova)

Yuka Tateisi (University of Tokyo)

K. Vijayshanker (University of Delaware)

David Weir (University of Sussex)

CONTACT ADDRESS:

Jennifer MacDougall

553 Moore Building

University of Pennsylvania

Philadelphia, PA 19104-6389

USA

Telephone: (215) 898-3191

FAX: (215) 898-0587

Email: jmacdoug (at) central (dot) cis (dot) upenn (dot) edu

TUTORIAL:

Prior to the workshop there will be a tutorial (including labs and demos) from July 28 to July 31 1998. Details about the tutorial will be sent out soon. We are trying to get some partial support for some of the students attending the tutorials. If you may be interested in attending this tutorial, please contact Jennifer MacDougall at the address above (preferably by email) and we will send you more information.

ORGANIZING COMMITTEE:

Anne Abeille (Paris 7)

Tilman Becker (DFKI)

Owen Rambow (CoGenTex, Inc.)

Giorgio Satta (Universita di Padova)

K. Vijayshanker (University of Delaware)

---

TOPIC 3:

A: CSLU Spring Short Courses [Portland, OR - May 5 - May 18]

From: "Terri Durham" <durham(at)cse(dot)ogi(dot)edu>

Institute in Portland, Oregon will be giving two spring short courses in May to coincide with the ICASSP '98 Conference in Seattle Washington.

Please visit our web page for a full description of each course and to fill out your registration form. http://www.cse.ogi.edu/CSLU/shortcourse2/

If you have any questions please don't hesitate to give me a call.

Thank You,

Terri Durham

CSLU Center Administrator

PO Box 91000 Portland, OR. 97291

20000 NW Walker Rd., Beaverton, OR. 97006

Phone: 503-690-1630 // Fax: 503-690-1306

May 5-8th Text-to-Speech Synthesis

Instructors:

Paul Taylor

Center for Speech Technology Research, University of Edinburgh

Alan Black

Center for Speech Technology Research, University of Edinburgh

Michael Macon

Center for Spoken Language Understanding, Oregon Graduate Institute

May 18-22 Building Spoken Dialogue Systems

Instructors:

Stephen Sutton

Center for Spoken Language Understanding, Oregon Graduate Institute

Teaching Assistants:

Andrew Cronk

Center for Spoken Language Understanding, Oregon Graduate Institute

Ed Kaiser

Center for Spoken Language Understanding, Oregon Graduate Institute

---

TOPIC 4: JOB: ITRI Brighton PhD Studentship [Apply by Apr 30, 1998]

From: postgrad-admissions(at)itri(dot)brighton(dot)ac(dot)uk

Information Technology Research Institute

University of Brighton

PhD Studentship for October 1998

Application deadline: 30 April 1998

The Information Technology Research Institute (ITRI) invites applications for a three-year EPSRC studentship award to commence in October 1998. The studentship will be awarded in one (or more) of the following topics in Computational Linguistics:

DOCUMENT GENERATION (including TEXT GENERATION): architectures; corpus analysis; diagrammatic reasoning; discourse; evaluation; hybrid generation; implementation; layout; multilinguality; multimodality; representation languages; pragmatics; tools

LEXICONS: corpus analysis; evaluation; lexical statistics; lexicalized grammars; lexicography; lexicon induction from text; multilinguality; representation; tools; tuning; word sense disambiguation

NATURAL LANGUAGE INTERFACES: dialogue; interface design

Applicants should have a good honours degree or equivalent in Computer Science, Computational Linguistics or Linguistics.

EPSRC studentships are restricted to UK or EU residents. Residents of the UK are eligible for fees and a maintenance allowance; other EU residents are only eligible for fees (and so would need to be able to support themselves during their studies).

The EPSRC baseline rate of maintenance allowance is currently approx 5,295 pounds sterling per annum. For further general information on EPSRC studentships, please consult http://www.epsrc.ac.uk/in-depth/indpfram.htm.

Further information on the Institute's research programme can be found on the ITRI home page (http://www.itri.brighton.ac.uk) and information about students and how to apply on our research students page (http://www.itri.brighton.ac.uk/students).

If we already have your application on file for consideration this year, you do not need to apply again.

Deadline for applications: 30 April 1998

For additional advice and information, please contact:

Ms. Vivienne Wicks, Research Administrator

Information Technology Research Institute

University of Brighton

Lewes Rd.

Brighton

BN2 4GJ, UK

Email: postgrad-admissions (at) itri (dot) brighton (dot) ac (dot) uk

Tel: +44 1273 642900

Fax: +44 1273 642908

---

TOPIC 5:

CFP: COLING/ACL98 Discourse Relations Workshop [Deadline Apr 6]

From: <stede(at)cs(dot)tu-berlin(dot)de>

Coling-ACL '98 workshop "Discourse Relations and Discourse Markers” August 15, 1998 Universit� de Montr�al Montr�al/Canada

(See also: http://flp.cs.tu-berlin.de/~marker/aclcolingws.html)

The notion of discourse relation has received many different interpretations, some of which are hardly compatible with one another. Nonetheless, there is a consensus among researchers that intersegment relations hold between adjacent portions of a text and that these relations may be signalled by linguistic means, including so-called cue phrases, aspect and mood shifts, theme inversions, and other markers.

The workshop intends to bring together researchers working on discourse relations and discourse markers in different linguistic traditions and different NLP applications. The particular focus of the workshop is the issue of discourse relations from the viewpoint of linguistic realization. Specifically, contributions should address one or more of the following questions:

o What are sound methodologies for comparing similar discourse markers (contrastive studies, distribution analyses, etc.)?

o What are sound methodologies for relating discourse relations with potential realizations?

o Are there discourse relations that are always lexically signalled? Are there any that are never lexically signalled?

o What non-lexical (i.e., syntactic or prosodic) means are used to signal a relation?

o In production, how does one decide whether to signal a relation at all?

o In production, how does one motivate a choice among candidate signals for a given relation?

o In production, how does the choice of signal interact with other decisions (in particular, those of linearizing some tree or graph structure)?

o In analysis, is it possible to reliably infer discourse relations from surface cues?

o In analysis, how can one disambiguate polysemous signals such as "and", "since" (temporal or causal) etc.?

o What are useful lexical representations of discourse markers, for both analysis and production?

o What are useful representations of discourse relations (and the entities they relate), such that they facilitate the realization decision? What features would one like to have handy in a representation so that choices can be made easily?

o Are there significant differences between realizations in spoken and written language?

o How do individual languages differ in terms of any of the above issues?

Organizing committee

The workshop is organized by

Manfred Stede (TU Berlin)

Leo Wanner (University of Stuttgart)

Eduard Hovy (ISI/USC, Marina del Rey)

Requirements for submission

Papers are invited that address any of the topics listed above. Maximum length is 8 pages including figures and references. Please use A4 or US letter format and set margins so that the text lies within a rectangle of 6.5 x 9 inches (16.5 x 23 cm). Use classical fonts such as Times Roman or Computer Modern, 11 to 12 points for text, 14 to 16 points for headings and title. LaTeX users are encouraged to use the style file provided by ACL: http://coling-acl98.iro.umontreal.ca/colaclsub.sty Papers can be submitted either electronically in PostScript format, or as hardcopies.

Submissions from North America should be sent to:

Eduard Hovy

Information Sciences Institute

4676 Admiralty Way Marina del Rey, CA 90292-6695

U.S.A.

hovy (at) isi (dot) edu

Submissions from elsewhere should be sent to either of the following:

Manfred Stede	Leo Wanner
TU Berlin	Computer Science Department
KIT Project Group	Intelligent Systems Group
Sekr. FR 6-10	University of Stuttgart
Franklinstr. 28/29	Breitwiesenstr. 20-22
D-10587 Berlin	D-70565 Stuttgart
Germany	Germany
stede(at)cs(dot)tu-berlin(dot)de	wannerlo(at)informatik(dot)uni-stuttgart(dot)de

Timetable

Deadline for electronic submissions: April 6, 1998

Deadline for hardcopy submissions: April 9 (arrival date)

Notification of acceptance: May 25, 1998

Final manuscripts due: June 15, 1998

Program committee

	Sandra Carberry (U Delaware)
	Barbara DiEugenio (U Pittsburgh)
	Eduard Hovy (USC/ISI)
	Alistair Knott (U Edinburgh)
	Alex Lascarides (U Edinburgh)
	Owen Rambow (Cogentex Inc.)
	Ted Sanders (U Utrecht)
	Donia Scott (U Brighton)
	Wilbert Spooren (U Tilburg)
	Manfred Stede (TU Berlin)
	Keith Vander Linden (Calvin College)
	Marilyn Walker (ATT Labs)
	Leo Wanner (U Stuttgart)

---

TOPIC 6:

CFP: Special issue NRHM Adaptivity and User Modeling [Deadline Jun 1]

From: Maria Milosavljevic <mariam(at)alba.nsw.cmis.CSIRO.AU>

The New Review of Hypermedia and Multimedia

1998 call for submissions on the themes of 'adaptivity and user modeling in hypertext/hypermedia systems', and 'hypermedia for museums and cultural heritage’.

NRHM (previously Hypermedia, one of the original journals on the subject) is a refereed annual review journal covering research on practical and theoretical developments in hypermedia, interactive multimedia and related technologies. The new editorial team has introduced themed issues, each issue (normally 10-12 papers) will review and explore one or two topical themes from a variety of perspectives. The main theme of the 1997 issue was the evaluation of hypermedia and multimedia systems.

The themes for the 1998 issue of the New Review will be:

- hypermedia for museums and cultural heritage Theme editors Douglas Tudhope and Daniel Cunliffe

- adaptivity and user modeling in hypertext/hypermedia systems: Guest editors Peter Brusilovsky and Maria Milosavljevic (also see Adaptive Hypertext and Hypermedia Home Page http://www.education.uts.edu.au/projects/ah/index.html)

Papers should be submitted to the appropriate theme editors no later than June 1st 1998. For Instructions to Authors, see http://www.comp.glam.ac.uk/~NRHM/ or contact the Editor.

Submissions are welcomed on all aspects of the two themes, including but not restricted to:

Adaptive hypermedia

	user modeling in adaptive hypermedia
	adaptive educational hypermedia systems
	adaptive information systems
	adaptive museum hypermedia
	adaptive navigation support
	natural language techniques for dynamic hypertext generation
	adaptive WWW navigation aids
	adaptive visualization of hypertext structure
	empirical studies of adaptive hypermedia
	content adaptation in hypertext and hypermedia
	personalized information spaces
	adaptivity and adaptability in a hypermedia context
	adaptive information retrieval

Guest editors

Peter Brusilovsky - plb (at) cs (dot) cmu (dot) edu

School of Computer Science,

Carnegie Mellon University,

Pittsburgh, PA 15213,

USA.

Maria Milosavljevic - mariam (at) mpce (dot) mq (dot) edu (dot) au

MRI Language Technology Group,

Macquarie University,

Sydney, NSW 2109,

Australia.

Hypermedia for Museums and Cultural heritage

	hypermedia link services
	networked access
	time-varying interactive presentations
	image, audio and video databases
	navigation design
	intelligent hypermedia and agents
	web-based museum hypermedia
	spatial and temporal models
	evaluation and studies of use
	metadata and intellectual access
	thesauri and semantic representations
	copyright /IPR for digital multimedia standards

Editor

Douglas Tudhope - dstudhope (at) glamorgan (dot) ac (dot) uk

Department of Computer Studies

University of Glamorgan

Pontypridd, Mid-Glamorgan CF37 1DL

Wales, UK

fax +1443-482715

tel +1443-482271

Associate Editor (US) Andrew Dillon - adillon (at) ucs (dot) indiana (dot) edu

Associate Editor (UK) Daniel Cunliffe - djcunlif (at) glamorgan (dot) ac (dot) uk

For subscription information, contact

Taylor Graham Publishing, 500 Chesham House,

150 Regent Street, London W1R 5FA, UK.

---

TOPIC 7:

CFP: Computational Treatment of Portuguese - Brazil [Deadline May 4]

From: lucia (at) dc(dot) ufscar(dot) br (Lucia Rino)

III PROPOR

WORKSHOP ON THE COMPUTATIONAL TREATMENT OF THE

WRITTEN AND SPOKEN PORTUGUESE LANGUAGE

November 3-4, 1998

PUCRS Campus

Porto Alegre - RS

BRAZIL

Sponsored by the Brazilian Computer Society (SBC)

Organized by the Catholic University of Rio Grande do Sul (PUCRS)

CALL FOR PAPERS

Along with the XIV SBIA'98 (Artificial Inteligence Brazilian Symposium), to be held in Porto Alegre, RS, Brazil, in the PUCRS Campus between 04 and 06 of November, 1998, there will be carried out the III PROPOR - III WORKSHOP ON THE COMPUTATIONAL TREATMENT OF THE WRITTEN AND SPOKEN PORTUGUESE LANGUAGE - on the 3rd and 4th of November, 1998.

The former two PROPOR workshops occurred in Portugal and in Brazil, respectively in Feb/1993 and Oct/1996. The third one intends to bring together researchers working on Computational Linguistics, specially those whose work is in any sense related to the processing of the Portuguese language. The main goals of the workshop are to provide the means for the researchers to exchange information and to explore and discuss the availability of resources to solve problems related to Natural Language, having Portuguese as the central language. Contributions should address one or more of the following topics:

• The automatic interpretation of the Portuguese language

• The automatic generation of the Portuguese language

• Verbal discourse processing: problems and resources of the Portuguese language

• Differences and similarities between the treatment of spoken and written Portuguese

The above topics naturally include a broader discussion on Natural Language Processing as such, and other issues in the Computational Linguistics spectrum. Researchers are invited to submit articles or demoes, in order to integrate, and exchange, experiences with the participants during the event.

Workshop organization

The workshop will consist of technical pannels, conference and discussion sessions. Participants are also invited to present demoes and systems resulting from project and development of software.

Requirements for submission

Papers and software are invited that address any of the topics listed above, preference given to conclusive work. Work reporting ongoing MsC or PhD research can be submitted to the Workshop of Unconcluded Dissertations and Theses, which is held along with SBIA'98. In this case, submission requirements can be found in the following address:

http://www.inf.pucrs.br/~flavio/sbia98/sbia98.html.

IMPORTANT DEADLINES

Technical papers and software descriptions: May 04, 1998 (mailing date)

Notification of acceptance: July 01, 1998 (by email)

=46inal manuscripts due: August 15, 1998 (mailing date)

No electronic submission will be accepted.

INSTRUCTIONS FOR SUBMISSION

Manuscripts must be written either in Portuguese or in English. Please use A4 letter format, doubleline spacing, classical fonts such as Times Roman or Computer Modern, 12 points for text, 14 to 16 points for headings and title. Maximum length is 15 pages including figures and references. Small caps or figures must be avoided, since the manuscripts may be reduced for the proceedings. The content of the first page must include the title of the article, the author(s) fullname(s), institution of origin, address, and a summary of the work. Faxed or emailed work will not be accepted for revision. Software descriptions must contain title, goals and a short characterization, besides the names of the authors, their institution of origin and address, and the specification of software/hardware needs for demoes.

=46our hardcopy copies of both, technical papers or software descriptions, must be accompanied by a letter of submission containing the title of the work, authors, and the name of the contact person. Submissions should be sent to:

Vera L=FAcia Strube de Lima Instituto de Informatica -PUCRS Av. Ipiranga, 6681 - Pr=E9dio 16 - Sala 160 CEP 90619-900 Porto Alegre Brasil E-mail: vera (at) andros(dot)inf(dot)pucrs(dot)br

Organizing committee

	Vera L=FAcia Strube de Lima (PUCRS)
	Flavio Moreira de Oliveira (PUCRS)
	Rosa Maria Viccari (UFRGS)

Program committee

	Ariadne M. B. R. Carvalho (IC-UNICAMP)
	Clarisse Sieckenius de Souza (DI-PUCRJ)
	Elisabete Ranchhod (FL-UL)
	Isabel Trancoso (INESC)
	Jacques Robin (DI-UFPe)
	Jos=E9 Gabriel Pereira Lopes (FCT-UNL)
	Laura S. Garcia (CEFET-PR)
	L=FAcia Machado Rino (DC-UFSCar)
	Mike Dillinger (IL-UFMG)
	Raul S. Wazlawick (DI-UFSC)
	Rosa Maria Viccari (II-UFRGS)
	Vera L=FAcia Strube de Lima(II-PUCRS)

---

TOPIC 8:

A: KPML Mailing List

From: Elke Teich <elke(at)dude(dot)uni-sb(dot)de>

Announcing the KPML mailing list

KPML (Komet-Penman MultiLingual) is a grammar development environment for Systemic Functional Grammars and a sentence generator for English, German, Dutch and a few other languages. The system was developed at the Institute for Integrated Publication and Information Systems (IPSI) of the German National Research Center for Information Technology (GMD), Darmstadt, Germany (http://www.darmstadt.gmd.de/IPSI/index.html) and is now being further developed at the Center for Language and Communication research at the University of Stirling, UK (http://www.stir.ac.uk/english/communication).

KPML is based on the Penman system for generation of English sentences originally developed at the Information Sciences Institute, University of Southern California.

Added functionalities include

- multilinguality

- facilities for versioning and back-up for large-scale grammar resources

- graphic-based grammar writing tools

- graphic-based grammar exploration tools

- tools for preparing teaching materials

- specialized example and test suite management tools.

KPML has been used in a number of projects and is currently one of the most popular platforms for developing grammars for generation. Users of the system currently develop generation grammars for languages as diverse as English, German, Dutch, French, Spanish, Finnish, Greek, Czech, Russian and Bulgarian. More information about KPML can be found at http://www.stir.ac.uk/english/communication/Computational-tools/ including the requirements for installing the system, downloading the system, documentation etc.

You might also want to have a look at a sample generated document where the text parts are generated with KPML:

http://www.darmstadt.gmd.de/publish/komet/kometpave-pics-96.html

Other relevant pages:

KPML basic:

http://www.stir.ac.uk/english/communication/Computational-tools/kpml.html

KPML documentation (online):

http://www.darmstadt.gmd.de/publish/komet/kpml-1-doc/kpml.html

KPML documentation (downloadable hardcopy):

file://ftp.darmstadt.gmd.de/pub/komet/KPML-1.0/

The Grammar Exploration Tool:

http://www.stir.ac.uk/english/communication/Computational-tools/Grexplorer/grexplorer.html

The generation grammar bank:

http://www.stir.ac.uk/english/communication/Computational-tools/generation-bank.html

This mailing list offers users of KPML the opportunity of exchanging information, seeking and giving advice in issues of linguistic specification and computational implementation, announcing and making available add-on functionalities and new resources etc. The list is managed by the department of English Linguistics, Institute of Applied Linguistics, Translation and Interpreting of the University of the Saarland, Saarbruecken, Germany (http://www.uni-sb.de/~sl16eset/elke.html).

Subscribe NOW and keep in touch!

To subscribe send e-mail to

elke(at)dude(dot)uni-sb(dot)de

by putting 'subscribe MY-E-MAIL-ADDRESS' in the subject field.

---

TOPIC 9:

P: Diana McKinnie [Generating reports from dictated X-ray reports]

From: Diana McKinnie <LDDMCKIN(at)ihc(dot)com>

I am a PhD student in the Medical Informatics program at the University of Utah. My project deals with generating natural language reports from parsed, dictated X-ray reports. I find the field of natural language generation fascinating and frustrating. I look forward to talking to others with the same fascinations and frustrations.

My e-mail address at the University is: d.mckinnie(at)m(dot)cc(dot)utah(dot)edu.

Thanks- Diana McKinnie

---

eof

---

1997

Issue 3

Date: 07 Dec 1997

---

TOPICS: 1. Q: Evaluation of NL dialogue systems?

2. CFP: COLING-ACL 98 -- Call for Workshop and tutorial proposals -- Deadline: 31 Dec 97

3. CFP: Book -- Advances in Scalable Text Summarization Deadline: 30 Dec 97

4. CFP: ETAI -- Electronic Transactions on AI

5. CFP: TAPD'98 -- Tabulation in Parsing and Deduction Deadline: 12 Dec 97

6. CFP: SIGDAT'98 -- Very Large Corpora Deadline: 20 Apr 98

7. CFP: FOIS'98 -- Formal Ontology in Information Systems Deadline: 15 Dec 97

8. CFP: Discourse Relations and Discourse Markers -- Coling/ACL'98 Deadline: 10 Mar 98

9. CFP: INLG'98 -- International Workshop on NL Generation Deadline: 28 Jan 98

10.JOB: ITRI, Brighton -- Research opportunities

11.JOB: ELRA/ELDA

---

---

Topic 1: Q: Evaluation of NL dialogue systems?

From: "gas0" <GAS0(at)elvira(dot)ugr(dot)es>

Ramon Lopez-Cozar Delgado

Electronics and Computer Technology Dept.

University of Granada

18071 Granada, Spain

e-mail: gas0(at)elvira(dot)ugr(dot)es

Fax: +34-58-243230

Dear SIGGEN colleagues:

I am a PhD student and a researcher in the Department of Electronics and Computer Technology at the University of Granada. I am working on a natural language dialogue system that aims to answer product orders and questions of clients in fast-food restaurants. It may be considered a rule-based expert system whose behaviour is decided from a recorded dialogue corpus obtained at a real restaurant. The system is quite developed at the moment, though it needs some improvement to enhance the level of understanding and naturalness.

I would like to get information about the available evaluation methods of such a system, as well as information about the evaluation of natural language dialogue systems in general (used techniques, bibliography, web sites, etc.).

In order to provide more information, I enclose a short abstract about the system I am working on.

--- Abstract ----

The system goal is to simulate the restaurant-clerk behaviour. It must be able to provide information and ask client questions similarly to how a human clerk does. In addition we want it to process spontaneous voiced-speech, which at a linguistic level means to consider phenomena such as unnecessary word repetition, grammatical order change, anaphora, discordances, context information, grammatical mistakes, etc. We also expect a learning ability for the system to allow new information (foods, drinks, ingredients, etc.) acquisition from client interaction.

The basis for the system development is as follows:

- Unnecessary information in client utterance: Usually, not all words in a sentence are necessary to obtain its semantic interpretation, which can be achieved from meaning words only (keywords). To obtain such interpretation, the system uses keywords and a keyword lattice analysis. This analysis is carried out by means of syntactic and semantic rules. From dialogue corpus we found out that clients usually use a small number of words in their utterances (communication client-clerk tends to be telegram-like), therefore a system dictionary can be size-reduced.

- Use of a small number of patterns: Clients tend to communicate using a small number of patterns to order products, ask questions, or modify previous product orders. Using these patterns the system can extract most semantic meanings from clients' utterances. In case the meaning cannot be obtained, clients are asked to help the system understanding process or to repeat the utterance input differently.

The system is a compound of several modules: Input Interface, Control Module, Memory Module, Restaurant-product Knowledge Base, Lexicon, and Output Interface.

At the moment the system takes about 30.000 C++ code lines. Its inputs and outputs are natural language text sentences.

Its Input interface is well developed but still needs to define some syntactic and semantic rules, since now only product orders and questions are carried out.

We are about to start the Modification Module set up. This module will be activated when the desire of modification of previous orders is detected in client input.

Also, the Learning Module needs to be started. This module will be activated when "possible" unknown foods, ingredients, drinks, etc. are detected in client input. These new products will be learnt, so they could be recognized the next time they appear in client sentences.

The Natural Language Generator needs improvement to enhance the expression power, though at the moment, the system can build both syntactically and semantically right sentences, in a very natural fashion, by using pronouns and context information available at the moment of the natural language generation.

The system uses a graphic interface that now is useful but simple. In future we would like to improve it by including product-pictures and graphics of the "artificial" restaurant-clerk face, in order to improve a friendly communication.

We think the integration of the system in a voice-controlled response system represents its best application. To do so, it would need a speech-to-text interface that provides a text-word sequence from client voice. A text-to-speech interface should transform the system output into synthesized voice. Theoretically the whole system could be part of an automatic front-end dialogue system for clients in restaurants, or for those at home who use telephone for ordering.

--- End of Abstract ---

I do not know if this short abstract would be enough for you to get an idea of the system, so in case you need any further information, or in case you have any comment or remark, please let me know.

I look forward to hearing from you soon. Thanks again.

Sincerely,

Ramon Lopez-Cozar Delgado

Electronics and Computer Technology Dept.

University of Granada

18071 Granada

Spain.

---

Topic 2: CFP: COLING-ACL 98 -- Call for Workshop and tutorial proposals

From: pete(at)sharp(dot)co(dot)uk (Pete Whitelock)

COLING-ACL '98 WORKSHOPS & TUTORIALS CALL FOR PROPOSALS University of Montreal Montreal Quebec Canada

The Programme Commitee would like to receive proposals for tutorials and workshops to be held in conjunction with the Joint COLING-ACL Conference.

TUTORIALS

Tutorials will be held on Sunday 9th August, the day preceeding the conference proper. Tutorials may address any topic of current or possible future relevance to the field. The duration of each tutorial should be approximately 3 hours. Those interested in presenting a tutorial should send a 300-500 word proposal to Pete Whitelock, pete(at)sharp(dot)co(dot)uk, describing the relevance of the subject matter to the conference participants, an outline of the tutorial's content, and a short statement of the proposer's relevant experience.

WORKSHOPS

Workshops will be held on Saturday 15th and Sunday 16th of August, immediately following the conference proper. Workshops will normally be one day in length, but may extend to a second day if required. Those interested in organising a workshop should send a brief proposal to Pete Whitelock, pete(at)sharp(dot)co(dot)uk, describing the topic of the workshop and its relevance to Coling, the approximate number of participants expected and the likely duration of the workshop, and a short statement of the proposer's relevant experience.

It is hoped that it will be possible to accomodate all proposals for tutorials and workshops, but the room space available will place an upper limit on the number. Since proposals will be accepted primarily on a first-come first-served basis, proposers are encouraged to submit as early as possible. Early submission is particularly important if workshop presentations are to be refereed. In any event, no proposals will be accepted after the final deadline of Dec 31st.

---

Topic 3: CFP: Book -- Advances in Scalable Text Summarization

From: Inderjeet Mani <mani(at)azrael(dot)mitre(dot)org>

CALL FOR PAPERS (BOOK) ADVANCES IN SCALABLE TEXT SUMMARIZATION Inderjeet Mani and Mark Maybury, editors

With the explosion in the quantity of on-line information in recent years, demand for text summarization technology appears to be growing. Commercial companies are starting to offer text summarization capabilities, often bundled with information retrieval tools. Further, there is considerable interest in mining information from large databases, many of which have text content. These recent developments offer opportunities as well as substantial challenges for research in text summarization. In general, such developments have created a practical need for summarization systems which scale up when applied to large volumes of unrestricted text.

In response to this challenge, a number of new approaches have emerged. Traditionally, shallower techniques have been leveraged to achieve the desired levels of scalability and domain-independence, but recent advances in robust information extraction as well as approaches integrating statistical and symbolic techniques have opened up possibilities for more powerful yet scalable summarization techniques.

With the renewed interest in text summarization, another challenge is to develop rigorous criteria to help evaluate different methodologies, in order to better advise investors and the interested public on technology choices. This state-of-the-art collection will bring together research aimed at advancing the scientific frontiers of text summarization to meet these new practical challenges and opportunities. **The principal aim of this book is to collect some of the key results to date and to identify promising research issues for the benefit of students, corporate researchers, and research program managers interested in learning more about this field.**

Submissions are invited on original research in all aspects of text summarization, including, but not limited to:

TECHNIQUES

* Statistical, linguistic, and knowledge-based techniques in intelligent summarization

* Text summary generation

* Capturing cohesion and coherence relations in text

* Exploiting advances in information extraction in summarization

* Exploiting domain knowledge in scalable text summarization

* Combining scalability with abstraction in summarization

* Tailoring summaries to particular users, tasks, and contexts

NEW PROBLEMS

* Multilingual summarization

* Multimodal summarization

* Multi-document/multi-source summarization

FUNDAMENTAL ISSUES in THEORY AND PRACTICE

* Classification of summarization systems

* Theoretical foundations, including cognitive models

* Evaluation methods and metrics

* Summarization in operational contexts: requirements, architectures, lessons learned

Criteria for selection will include clarity, originality, relevance, and significance of results. The papers will be reviewed by a committee of experts. In addition, authors will be asked to relate the content of their papers to other related papers in the book. In addition to new contributions, the book will also include reprints of classic papers in the field.

Submission Information

DEADLINE FOR SUBMISSION: December 30, 1997

PAPERS REVIEWED BY: March 15, 1997

DRAFT TO PUBLISHERS: July 15, 1997

Interested authors should submit to the address below three copies of a previously unpublished paper no more than 20 pages long, single-spaced, addressing a specific text summarization issue or reporting novel methods and results. Authors should indicate whether the paper is being submitted elsewhere. Please include your name and address on the first page.

For more information, please contact:

Dr. Inderjeet Mani

The MITRE Corporation, W640

11493 Sunset Hills Road

Reston, Virginia 22090, USA

Internet: imani(at)mitre(dot)org

Phone: (703) 883-6149

Fax: (703) 883-1379

---

Topic 4: CFP: ETAI -- Electronic Transactions on AI

From: Elisabeth Andre <Elisabeth.Andre(at)dfki(dot)de>

*** Call for Papers for the First Issues of the *** ETAI - ELECTRONIC TRANSACTIONS ON ARTIFICIAL INTELLIGENCE Organized and published under the auspices of the European Coordinating Committee for Artificial Intelligence (ECCAI) http://www.ida.liu.se/ext/etai

AREA: Intelligent User Interfaces

SCOPE:

The ETAI is organized into several specialized areas. The area of Intelligent User Interfaces focuses on design principles, methodologies and tools that make man-machine communication easier and more effective. For ETAI, papers are invited from the whole spectrum of Intelligent User Interfaces research. Topics of interest include, but are not restricted to:

- knowledge-based tools and environments for user interface design and development

- adaptive and customizable user interfaces

- user modeling

- intelligent interface agents and agent-based interaction

- knowledge-based presentation of information

- intelligent interfaces to the internet, for tasks such as design, presentation, access and navigation

- natural-language and multimodal interfaces

- intelligent front-ends to multimedia, hypermedia and virtual environments

- architectures for intelligent user interfaces

- evaluation and analysis of intelligent user interfaces applications, such as tutoring and advisory systems, computer-supported collaborative work, computer-aided design, decision-support systems, information kiosks

CONTRIBUTIONS:

The ETAI welcomes contributions for the first issues of the area: Intelligent User Interfaces. Beside high-quality papers, we seek conference and workshop reports, book reviews and links to software that is available and can be run over the net. Submission guidelines can be found under http://www.ida.liu.se/ext/etai/submission.html For more details contact the area editor (address see below).

AREA EDITOR: Elisabeth Andre, DFKI, Germany

AREA EDITORIAL COMMITTEE (as of September 1997):

Niels Ole Bernsen, Odense University, Denmark

Peter Brusilovsky, CMU, USA

Lynda Hardmann, CWI, NL

James Lester, North Carolina State University, USA

Joe Marks, MERL, USA

Chris Mellish, University of Edinburgh, UK

Ehud Reiter, University of Aberdeen, UK

Constantine Stephanidis, FORTH, Greece

Oliviero Stock, IRST, Italy

Annika Waern, SICS, Sweden

WHAT IS THE ETAI?

The ETAI represents a novel approach to electronic publishing. We do not simply inherit the patterns from the older technology, but instead we have rethought the structure of scientific communication in order to make the best possible use of international computer networks as well as electronic document and database technologies.

Articles submitted to the ETAI are reviewed in a 2-phase process. After submission, an article is open to public online discussion in the area's News Journal. After the discussion period of three months, and after the authors have had a chance to revise it, the article is reviewed for acceptance by the ETAI, using confidential peer review and journal level quality criteria. This second phase is expected to be rather short because of the preceding discussion and possible revision. During the entire reviewing process, the article is already published in a "First Publication Archive", which compares to publication as a departmental tech report.

Compared to mailgroups, the News Journals offer a more persistent and reputable forum of discussion. Discussion contributions are preserved in such a way that they are accessible and referencable for the future. In other words, they also are to be considered as "published".

One additional type of contributions in News Journals is for links to software that is available and can be run over the net. This is particularly valuable for software which can be run directly from a web page.

The creation of bibliographies, finally, is a traditional activity in research, but it is impractical in paper-based media since by their very nature, bibliographies ought to be updated as new articles arrive. The on-line maintenance of specialized bibliographies within each of its topic areas is a natural function in the ETAI.

For more details see: http://www.ida.liu.se/ext/etai/

ADDRESS FOR FURTHER INFORMATION:

Elisabeth Andre

DFKI GmbH

Stuhlsatzenhausweg 3

D-66123 Saarbruecken

Germany

Phone: +49 681 302 5267

Fax: +49 681 302 5341

email: andre(at)dfki(dot)de

---

Topic 5: CFP: TAPD'98 -- Tabulation in Parsing and Deduction

From: Eric Villemonte de la Clergerie <Eric.Clergerie(at)inria(dot)fr>

TAPD'98 1st Workshop on 'Tabulation in Parsing and Deduction' April 2-3, 1998 Paris, France Organized by INRIA in collaboration with CEDRIC of CNAM WEB page: http://pauillac.inria.fr/~clerger/tapd.html

MOTIVATIONS

Tabulation techniques are becoming a common way to deal with highly redundant computations occurring, for instance, in Natural Language Processing, Logic Programming, Deductive Databases, or Abstract Interpretation, and related to phenomena such as ambiguity, non-determinism or domain ordering.

Different approaches, including for example Chart Parsing, Magic-Set rewriting, Memoization, and Dynamic Programming, have been proposed whose key idea is to keep traces of computations to achieve computation sharing and loop detection. In addition, tabulation also offers more flexibility to investigate new parsing or proof strategies and to represent ambiguity by shared structures (Shared Proof or Parse Forest).

The first objective of this workshop is to compare and discuss these different approaches. The second objective is to present tabulation and tabular systems to potential users in different application areas. One major area of application is Natural Language Processing, where tabulation has been known for a long time (CKY, Earley, chart parsing). However, sophisticated tabulation techniques are required for the more and more complex grammatical formalisms now used in NLP (unification, constraints, structural complexity). Contributions in other areas, such as picture parsing, genome analysis, or complete deduction techniques, are also encouraged.

TOPICS (not exclusive)

-- Tabulation Techniques:

Chart Parsing, Tabling, Memoization, Dynamic Programming, Magic Set, Generic Fix-Point Algorithms

-- Applications:

Parsing, Generation, Logic Programming, Deductive Databases,Abstract Interpretation, Deduction in Knowledge Bases, Theorem Proving

-- Static Analysis:

Improving tabular evaluation

-- Parsing or resolution strategies.

-- Efficiency issues:

Dealing with large tables (structure sharing, term indexing), Execution models, Exploiting the domain ordering (subsumption).

-- Shared structures (parse or proof forest):

Formal analysis, representation and processing.

WORKSHOP FORMAT: The workshop will be a 2-day event that provides a forum for individual presentations of the accepted contributions as well as group discussions.

SUBMISSION PROCEDURE: Authors are invited to submit before December 12, 1997 a 4-page position paper or abstract concerning a theoretical contribution or a system to be presented. Due to tight time constraints, submissions will be handled exclusively electronically (LaTeX, PostScript, dvi or ascii format). Submissions should include the title, authors' names, affiliations, addresses, and e-mail.

Submissions must be sent to Eric.Clergerie(at)inria(dot)fr

The collection of selected papers will be available at the workshop. After the workshop, authors are invited to submit a full paper for publication in a special issue of the Journal of Logic Programming oriented towards Natural Language Processing. The authors should note that this second submission will be treated according to the standards of the Journal of Logic Programming.

SCHEDULE:

Submission of contributions:	12 December 1997
Notification of acceptance:	26 January 1998
Final versions due:	20 February 1998

PROGRAM COMMITTEE:

Bernard Lang (chairman)	-- INRIA, France
Francois Bry	-- University of Munich, Germany
Eric de la Clergerie	-- INRIA, France
Marc Dymetman	-- Xerox, France
Mark Johnson	-- Brown University, USA
Baudouin Le Charlier	-- University of Namur, Belgium
Mark Jan Nederhof	-- University of Groningen, NL
David Rosenblueth	-- University of Mexico, Mexico
Manuel Vilares	-- University of La Coruna, Spain
David S. Warren	-- University of New York at Stony Brook, USA

ORGANIZING COMMITTEE:

Francois Barthelemy	-- CNAM, Paris, France
Eric de la Clergerie	-- INRIA, Rocquencourt, France
Bernard Lang	-- INRIA, Rocquencourt, France
Manuel Vilares	-- University of La Coruna, Spain

LOCAL ORGANIZATION:

Claudie Thenault

--INRIA, Relations Exterieures, France

ORGANIZATION: Up-to-date information will be available at

http://pauillac.inria.fr/~clerger/tapd.html

For request, please contact:

Eric de la Clergerie
INRIA Rocquencourt	Tel: +33 1 39 63 54 10
Domaine de Voluceau - BP 105	Fax: +33 1 39 63 53 30
78153 Le Chesnay Cedex	E-mail: Eric.Clergerie(at)inria(dot)fr

---

Topic 6: CFP: SIGDAT'98 -- Very Large Corpora

From: Eugene Charniak <ec(at)cs(dot)brown(dot)edu>

SIXTH WORKSHOP ON VERY LARGE CORPORA Preliminary Call for Papers

WHEN: August 15-16, 1998 (immediately following ACL/COLING-98)

WHERE: University of Montreal, Montreal, Quebec, Canada

WORKSHOP DESCRIPTION:

As in past years, the workshop will offer a general forum for new research in corpus-based and statistical natural language processing. Areas of interest include (but are not limited to):

- robust parsing, phrase structure analysis

- part of speech tagging

- term and name identification

- word sense disambiguation

- morphological analysis

- anaphora resolution

- event categorization

- discourse structure identification

- alignment of parallel texts and bilingual terminology

- language modelling

- lexicography

- machine translation

- spelling and grammar correction

PROGRAM CHAIR:

Eugene Charniak

Brown University

SPONSOR: SIGDAT (ACL's special interest group for linguistic data and corpus-based approaches to NLP)

FORMAT FOR SUBMISSION:

Only hard-copy submissions will be accepted. Authors should submit six (6) copies of their full-length paper (3500-8000 words) to Eugene Charniak at the Johns Hopkins University address below. Authors should consult the primary call for papers in February for updated specifications.

SCHEDULE:

Submission Deadline:	April 20, 1998
Notification Date:	June 1, 1998
Camera ready copy due:	June 22, 1998

CONTACT:

Eugene Charniak

e-mail ec(at)cs(dot)brown(dot)edu

Address: Before February 1, 1998 and After June 1, 1998

Department of Computer Science

Brown University

Providence RI 02912-1910

Address: From February 1, 1998 until June 1, 1998

Department of Computer Science

Johns Hopkins University

NEB 224, 3400 N. Charles Street

Baltimore, MD 21218-2694

---

Topic 7: CFP: FOIS'98 -- Formal Ontology in Information Systems

From: Alessandro Artale <artale(at)irst(dot)itc(dot)it>

INTERNATIONAL CONFERENCE ON FORMAL ONTOLOGY IN INFORMATION SYSTEMS FOIS'98 In conjunction with the 6th International Conference on Principles of Knowledge Representation and Reasoning KR'98

TRENTO, ITALY, JUNE 6-8, 1998

Under the auspices of the Project ONTOINT (Ontological Tools for Heterogeneous Knowledge Organization and Integration) funded by the Italian National Research Council

Research on ontology is becoming increasingly widespread in the computer science community. Its importance has been recognized in fields as diverse as qualitative modelling of physical systems, natural language processing, knowledge engineering, information integration, database design, geographic information science, and intelligent information access. Various workshops addressing the engineering aspects of ontology have been held in the past few years. However, ontology - by its very nature - ought to be a unifying discipline. Insights in this field have potential impacts on the whole area of information systems. In order to provide a solid general foundation for this work, it is therefore important to focus on the common scientific principles and open problems arising from current tools, methodologies, and applications of ontology. The purpose of this conference is to take a first step in this direction.

As the heterogeneity of the program committee indicates, the conference will have a strongly interdisciplinary character. Expected participants include computer science practitioners as well as linguists, logicians, and philosophers. Although the primary focus of the conference is on theoretical issues, methodological proposals as well as papers addressing concrete applications from a well-founded theoretical perspective are welcome.

TOPICS

Examples of problem areas that may be addressed at the conference include:

THEORETICAL ISSUES

* Foundations:

parthood, constitution, identity, integrity, dependence, causality

* Kinds of entity:

particulars vs. universals, continuants vs. occurrents,

abstracta vs. concreta, attributes, relations, qualities,

quantities, tropes or moments, states, situations, environments

* Matter, space, time, motion, change

* Natural kinds, organisms, artifacts

* The ontology of social reality:

legal and administrative entities, artistic expressions

* The ontology of information and information processing:

representations, signs, software products, virtual reality, cyberspace

* Top-level ontological taxonomies:

new proposals or critical analyses of existing ones

* Cognitive foundations of ontological distinctions

* Kinds of ontology:

top-level ontologies, domain ontologies, task ontologies,application ontologies

* Ontological commitment

APPLICATION AREAS

* Knowledge organization, integration and standardization

* Intelligent information access

* Information systems design

* Knowledge engineering

* Conceptual modelling

* Qualitative modelling

* Lexical semantics

* Terminology integration

* Product knowledge integration

* Geographic information systems

* Legal information systems

TOOLS AND METHODOLOGIES

* Ontological and linguistic instruments for conceptual analysis

* Methodologies for ontology development, maintenance, and integration

SUBMISSION OF PAPERS

Papers will be selected on the basis of a rigorous review of full paper contributions. Authors should submit 5 copies to the Conference Chair by December 19, 1997. Papers received after the deadline or not conforming to the submission format will be rejected without review.

Submitted papers must be unpublished and substantially different from papers under review. Papers that have been or will be presented at small workshops/symposia whose proceedings are available only to attendees may be submitted.

Each submission should include a title page containing the title, author(s), affiliation(s), submitting author's mailing address, telephone number, fax number and e-mail address, as well as an abstract and keywords indicating the topic areas listed above that best describe the contribution. Submissions must be at most 16 pages, excluding the title page and the bibliography, with a maximum of 38 lines per page and an average of 75 characters per line (corresponding to the LaTeX article-style, 12pt) using LaTeX or Microsoft Word. Papers should be sent in 5 copies. Fax or electronic submissions will not be accepted.

Those proposing to submit papers must complete the form at the WWW address <http://mnemosyne.itc.it:1024/fois98/> by Monday December 15, 1997. If intending authors do not have WWW access, then an e-mail message must be sent to <fois98(at)irst(dot)itc(dot)it> by the same date, giving details of any proposed submission in the following format:

Title: <Title of paper>

Author: <Last name, initials>

Author: <Insert as many more author lines as necessary>

...

CorrespondingAuthor: <name of corresponding author>

CorrespondingEmail: <email of corresponding author>

CorrespondingAddress: <address of corresponding author>

Keywords: <insert list of keywords, preferably chosen from above list>

Abstract: <insert short abstract, max 200 words>

EndAbstract:

Should intending authors not have e-mail access, the information above should be sent by letter to arrive to the Conference Chair by Monday December 15, 1997.

The proceedings will be published in the IOS-Press (Amsterdam) bookseries 'Frontiers in Artificial Intelligence and Applications' and will be available at the conference. Final camera-ready copies of the accepted papers will be due by March 9, 1998. Authors will be responsible for preparing the final camera-ready in conformity with the formatting requirements laid down by the publisher (see instructions at the FOIS'98 web page http://mnemosyne.itc.it:1024/fois98/submissions.html). Final papers will be allowed at most fourteen (14) pages in the conference proceedings style (corresponding to approximately 20 article-style LaTex pages).

SCHEDULE

Monday, December	15, 1997 Electronic abstracts due
Friday, December	19, 1997 Papers due
Friday, February	6, 1998 Results sent to authors
Monday, March	9, 1998 Final papers due
Saturday-Monday, June	6-8, 1998 FOIS'98

CONFERENCE COMMITTEE

CONFERENCE CHAIR	ORGANIZATION CHAIR
Nicola Guarino	Alessandro Artale
National Research Council	ITC-IRST
LADSEB-CNR	Povo, I-38050 Trento, Italy
Corso Stati Uniti, 4	e-mail: artale(at)irst(dot)itc(dot)it
I-35127 Padova, Italy
e-mail: guarino(at)ladseb(dot)pd(dot)cnr(dot)it

ORGANIZING COMMITTEE

Alessandro Artale - Enrico Franconi	(ITC-IRST, Trento, Italy)
Nicola Guarino - Claudio Masolo	(LADSEB-CNR, Padova, Italy)
Luca Pazzi - Sonia Bergamaschi	(Univ. of Modena, Italy)
Geri Steve - Aldo Gangemi	(ITBM-CNR, Roma, Italy)
Cristiano Castelfranchi - Rino Falcone	(IP-CNR, Roma, Italy)

---

Topic 8: CFP: Discourse Relations and Discourse Markers -- Coling/ACL'98

From: Eduard Hovy <hovy(at)ISI(dot)EDU>

Coling/ACL 98 workshop Discourse Relations and Discourse Markers August 15, 1998 Universite de Montreal Montreal/Canada

The notion of discourse relation has received many interpretations, some of which are hardly compatible with one another. Nonetheless, there is a consensus among researchers that intersegment relations hold between adjacent portions of a text and that these relations may be signalled by linguistic means, including so-called cue phrases, aspect and mood shifts, theme inversions, and other markers.

The workshop intends to bring together researchers working on discourse relations and discourse markers in different linguistic traditions and different NLP applications. The particular focus of the workshop is the issue of discourse relations from the viewpoint of linguistic realization. Specifically, contributions should address one or more of the following questions:

* What are sound methodologies for comparing similar discourse markers

(contrastive studies, distribution analyses, etc.)?

* What are sound methodologies for relating discourse relations with

potential realizations?

* Are there discourse relations that are *always* lexically signalled?

Are there any that are *never* lexically signalled?

* What non-lexical (i.e., syntactic or prosodic) means are used to signal a relation?

* In production, how does one decide whether to signal a relation at all?

* In production, how does one motivate a choice among candidate signals for a given relation?

* In production, how does the choice of signal interact with other decisions (in particular, those of linearizing some tree or graph structure)?

* In analysis, is it possible to reliably infer discourse relations from surface cues?

* In analysis, how can one disambiguate polysemous signals such as "and", "since" (temporal or causal) etc.?

* What are useful lexical representations of discourse markers, for both analysis and production?

* What are useful representations of discourse relations (and the entities they relate), such that they facilitate the realization decision? What

features would one like to have handy in a representation so that choices can be made easily?

* Are there significant differences between realizations in spoken and written language?

* How do individual languages differ in terms of any of the above issues?

Organizing committee

The workshop is organized by

Manfred Stede (Technical University, Berlin)

Leo Wanner (University of Stuttgart)

Eduard Hovy (ISI/USC, Marina del Rey)

This call for papers as well as future information on the workshop can be found at http://www.cs.tu-berlin.de/~marker/aclcolingws.html

Timetable

Deadline for electronic submissions: March 10, 1998

Deadline for hardcopy submissions: March 13 (arrival date)

Notification of acceptance: May 1, 1998

Final manuscripts due: June 12, 1998

---

Topic 9: CFP: INLG'98 -- International Workshop on NL Generation

From: Graeme Hirst <gh(at)cs(dot)toronto(dot)edu>

============================= 9th International Workshop on NATURAL LANGUAGE GENERATION 5-7 August 1998 Prince of Wales Hotel Niagara-on-the-Lake, Ontario, Canada

SECOND CALL FOR PAPERS

(For more information, visit http://logos.uwaterloo.ca/~inlg98 )

The 9th biennial Workshop on Natural Language Generation will be held in the scenic town of Niagara-on-the-Lake, near Niagara Falls, in Ontario, Canada, on 5-7 August 1998.

The INLG workshop is the principal gathering for researchers in natural language generation, providing a pleasant atmosphere for stimulating and informative talks on all aspects of the topic. The workshop attracts a healthy mixture of researchers from both universities and research institutes, graduate students, and visitors from related fields such as machine translation, multimedia presentation planning, and parsing. About 65 people are expected to attend the workshop, which traditionally has had a very diverse international representation.

The town of Niagara-on-the-Lake is in the heart of one of Canada's major fruit-growing and wine regions, and is 30 minutes' drive from Niagara Falls. It is one of the oldest settlements in Canada, with many fine examples of Victorian architecture. Niagara-on-the-Lake bills itself as the prettiest town in Canada, and many would agree: its main streets are quaint and picturesque, with many interesting shops, cafes, and restaurants. It is also the home of the Shaw Festival, one of the top North American repertory theatre companies.

The workshop is sponsored by the Association for Computational Linguistics and ACL SIGGEN (Special Interest Group on Natural Language Generation).

The workshop is in the week immediately prior to the joint conference of COLING and ACL, in Montreal, Canada (10-14 August 1998). After the workshop, a bus will take participants who wish to attend COLING / ACL directly to the Toronto train station, for an express train to Montreal (approximately 4 hours).

TOPICS OF INTEREST

Of interest are papers on all topics relating to the automated production of natural language, including but not limited to: discourse structure; grammar; lexis and lexical choice; text planning and schemas (macroplanning); sentence planning (microplanning); semantics and knowledge representation; register, genre, and pragmatics; generator architecture; realization; generator applications; system descriptions; generator evaluation; planning of text formatting; generation in multimedia planning and presentation systems; speech synthesis.

Also welcomed are demonstrations of generation systems, or modules of systems, running either via the Web or on a Sun computer to be provided at the workshop.

REQUIREMENTS FOR SUBMISSION

Papers should describe unique work not published before. They should emphasize the creative and interesting aspects of the work, but should also describe empirical validation and testing as much as possible.

Papers that are being submitted to other conferences must state this fact on the first page.

FORMAT FOR SUBMISSION

Theoretical papers must not exceed 10 pages, including title, references, figures, etc. Please use no smaller than 11pt font, with margins of 1 inch / 2.5 cm all around. Papers not satisfying the specified length and formatting requirements will be rejected without review.

System demonstrations will be reviewed as well. Please send an outline, clearly marked as a system demonstration in the heading, that describes the demonstration, including if possible screen shots. Outlines may not exceed 4 pages, all included, using font no smaller than 11pt and margins of 1 in / 2.5 cm all around. Outlines not satisfying the specified length and formatting requirements will be rejected without review.

ELECTRONIC SUBMISSION

Electronic submissions should be in the form of a PostScript file. This file should be sent to hovy(at)isi(dot)edu, with the subject field "INLG submission".

SUBMISSION IN HARD COPY

Hardcopy submission is possible too. Five copies of the paper or demonstration outline should be sent to:

Eduard Hovy, INLG-98

Information Sciences Institute

4676 Admiralty Way

Marina del Rey, CA 90292-6695

U.S.A.

DEADLINES

Electronic submissions must be received by 28 January 1998, so that they can be printed and checked for completeness. Electronic submissions will be accepted only if they can be printed at ISI.

Hardcopy submissions must be received by 1 February 1998. Late papers will be returned unreviewed.

Notification of receipt will be e-mailed to the first author (or designated author) soon after receipt. Authors will be notified of acceptance before 10 March 1998. Camera-ready copies of final papers prepared in a format to be specified, preferably using a laser printer, must be received by 15 June 1998, along with a signed copyright release statement.

WORKSHOP ORGANIZERS

The workshop is being organized by Chrysanne DiMarco of the University of Waterloo, with the assistance of Graeme Hirst of the University of Toronto. The Program Chair is Eduard Hovy of USC/ISI.

General workshop questions:

Chrysanne DiMarco, cdimarco(at)logos(dot)uwaterloo(dot)ca, phone +1 519 888 4443

General paper-submission questions:

Eduard Hovy, hovy(at)isi(dot)edu, phone +1 310 822 1510 x731

PROGRAM COMMITTEE

Eduard Hovy, USC/ISI, Marina del Rey (chair)

Stephan Busemann, DFKI, Saarbruecken

Susan Haller, University of Wisconsin-Parkside

Helmut Horacek, University of the Saarland

Xiaorong Huang, Formal Systems, Toronto

Kristiina Jokinen, ATR, Kyoto

Guy Lapalme, University of Montreal

Elisabeth Maier, DFKI, Saarbruecken

Chris Mellish, University of Edinburgh

Marie Meteer, BBN

Jon Oberlander, University of Edinburgh

Cecile Paris, CSIRO, Sydney

Owen Rambow, CoGenTex Inc., Ithaca

Ehud Reiter, University of Aberdeen

Elke Teich, Macquarie University, Sydney

Marilyn Walker, AT&T Labs Research, Florham Park

For more information, visit the INLG-98 Website:

http://logos.uwaterloo.ca/~inlg98

---

Topic 10: JOB: ITRI, Brighton -- Research opportunities

From: Donia Scott <donia.scott(at)itri(dot)bton(dot)ac(dot)uk>

<http://www.itri.bton.ac.uk/posts/summer97.html>

ITRI, University of Brighton

The Information Technology Research Institute (ITRI) at the University of Brighton, is a major centre for research in Computational Linguistics and Language Engineering. Our principal research areas are natural language generation, lexicons, corpora and human computer interfaces. Our current research programme addresses the following theoretical issues: anaphora, architectures for natural language generation, automated interface design, constraint based reasoning, controlled languages, corpora, diagrammatic reasoning, discourse, document design, integrating text and graphics, lexical knowledge bases, lexical representation, multilinguality, natural language interfaces, text generation, underspecification, word sense disambiguation.

The Institute is comprised of around twenty staff and students: research professors, readers, research fellows, research assistants, postgraduate students and technical and administrative staff. We also regularly host visiting researchers from other universities worldwide.

The Institute is housed in a self-contained brand new office suite with excellent computing and network facilities and full administrative support. As a dedicated research department, we place great emphasis on career management and development, and participation in the wider research community.

We are currently recruiting to fill up to six fixed-term research posts over the next few months, ranging from research officers to principal research fellows for up to three or five years in duration. A number of PhD studentships may also be available.

If you are interested in working with us, we would be interested in hearing from you. Please address all enquiries, enclosing a CV if possible, to the address below. Suitable potential candidates will be sent further information. Meanwhile, more detailed information regarding the Institute is available on our web site.

Ms Vivienne Wicks, Research Administrator, Information Technology Research Institute, University of Brighton, Lewes Road, Brighton, BN2 4GJ, United Kingdom.

Tel: +44 1273 642900	Email: admin(at)itri(dot)brighton(dot)ac(dot)uk
Fax: +44 1273 642908	URL: http://www.itri.brighton.ac.uk/

---

Topic 11: JOB: ELRA/ELDA

From: elra-elda(at)calva(dot)net (Malin Nilsson)

===============================================

TECHNICAL ASSISTANT at ELRA/ELDA in Paris

===============================================

ELRA, the European Language Resources Association, has an immediate vacancy for a Technical assistant for ELDA, its Paris-based distribution agency. ELRA, a non-profit association registered in Luxembourg, was established in 1995 and receives financial support from the European Commission and national governments to promote the development and exploitation of Language Resources - monolingual and multilingual lexica, text corpora, speech databases and terminology - in Europe. Enjoying strong backing from the language engineering industry, ELRA's operations are conducted by the CEO and his team at ELDA.

The role of the new technical assistant will be to contribute to the work of a small support team in the development of the infrastructure for the collection, validation, and licensing of LR and in the interactions with the relevant players (i.e. producers, owners and users of LR who may be in the industrial, commercial or academic world; and governmental and non-governmental agencies), with a particular focus on textual and terminological resources.

This position yields excellent opportunities for young, creative, and motivated candidates wishing to participate actively in establishing/building the European Union Language Engineering field. Terms and conditions of employment are subject to negotiation, but will be commensurated with the responsibilities of the post and will include performance-based incentives. ELRA will pay relocation expenses for the selected candidate. This is initially a one-year appointment with a strong possibility of a further two years or permanent employment.

Qualifications:

- Excellent track record in Language Engineering and related fields.

- Technical experience in design and development of Language Engineering

solutions (preference for candidats with experience in the fields of written

text and/or terminology).

- Experience in collecting, validating, and marketing language resources,

software or other forms of intellectual property. =09

- Experience in packaging language resources for distribution using=

CD-ROM,

ftp facilities, etc.. will be a plus.

- Citizenship of, or residency papers for an EU country.

- Ability to work in at least two European languages including English.

Applicants should send a cover letter addressing the points listed above, together with a current Curriculum Vitae, to: ELRA Distribution Agency (ELDA), Dr. Khalid Choukri, 87, Avenue d'Italie F-75013 Paris, France Fax +33 1 45 86 44 88; e-mail: elra(at)calvanet(dot)calvacom(dot)fr For more information on ELRA, see:http://www.icp.grenet.fr/ELRA/home.html (English) or /ELRA/fr/home.html (French) Initial applications by e-mail will be accepted with follow-up by post/fax.

---

eof

---

Issue 2

============================= 9th International Workshop on NATURAL LANGUAGE GENERATION

5-7 August 1998

Prince of Wales Hotel Niagara-on-the-Lake, Ontario, Canada

CALL FOR PAPERS

(For more information, visit http://logos.uwaterloo.ca/~inlg98 )

The 9th biennial Workshop on Natural Language Generation will be held in the scenic town of Niagara-on-the-Lake, near Niagara Falls, in Ontario, Canada, on 5-7 August 1998.

The INLG workshop is the principal gathering for researchers in natural language generation, providing a pleasant atmosphere for stimulating and informative talks on all aspects of the topic. The workshop attracts a healthy mixture of researchers from both universities and research institutes, graduate students, and visitors from related fields such as machine translation, multimedia presentation planning, and parsing. About 65 people are expected to attend the workshop, which traditionally has had a very diverse international representation.

The town of Niagara-on-the-Lake is in the heart of one of Canada's major fruit-growing and wine regions, and is 30 minutes' drive from Niagara Falls. It is one of the oldest settlements in Canada, with many fine examples of Victorian architecture. Niagara-on-the-Lake bills itself as the prettiest town in Canada, and many would agree: its main streets are quaint and picturesque, with many interesting shops, cafes, and restaurants. It is also the home of the Shaw Festival, one of the top North American repertory theatre companies.

The workshop is sponsored by the Association for Computational Linguistics and ACL SIGGEN (Special Interest Group on Natural Language Generation).

The workshop is in the week immediately prior to the joint conference of COLING and ACL, in Montreal, Canada (10-14 August 1998). After the workshop, a bus will take participants who wish to attend COLING / ACL directly to the Toronto train station, for an express train to Montreal (approximately 4 hours).

TOPICS OF INTEREST

Of interest are papers on all topics relating to the automated production of natural language, including but not limited to: discourse structure; grammar; lexis and lexical choice; text planning and schemas (macroplanning); sentence planning (microplanning); semantics and knowledge representation; register, genre, and pragmatics; generator architecture; realization; generator applications; system descriptions; generator evaluation; planning of text formatting; generation in multimedia planning and presentation systems; speech synthesis.

Also welcomed are demonstrations of generation systems, or modules of systems, running either via the Web or on a Sun computer to be provided at the workshop.

REQUIREMENTS FOR SUBMISSION

Papers should describe unique work not published before. They should emphasize the creative and interesting aspects of the work, but should also describe empirical validation and testing as much as possible.

Papers that are being submitted to other conferences must state this fact on the first page.

FORMAT FOR SUBMISSION

Theoretical papers must not exceed 10 pages, including title, references, figures, etc. Please use no smaller than 11pt font, with margins of 1 inch / 2.5 cm all around. Papers not satisfying the specified length and formatting requirements will be rejected without review.

System demonstrations will be reviewed as well. Please send an outline, clearly marked as a system demonstration in the heading, that describes the demonstration, including if possible screen shots. Outlines may not exceed 4 pages, all included, using font no smaller than 11pt and margins of 1 in / 2.5 cm all around. Outlines not satisfying the specified length and formatting requirements will be rejected without review.

ELECTRONIC SUBMISSION

Electronic submissions should be in the form of a PostScript file. This file should be sent to hovy@isi.edu, with the subject field "INLG submission".

SUBMISSION IN HARD COPY

Hardcopy submission is possible too. Five copies of the paper or demonstration outline should be sent to:

Eduard Hovy, INLG-98

Information Sciences Institute

4676 Admiralty Way

Marina del Rey, CA 90292-6695

U.S.A.

DEADLINES

Electronic submissions must be received by 28 January 1998, so that they can be printed and checked for completeness. Electronic submissions will be accepted only if they can be printed at ISI.

Hardcopy submissions must be received by 1 February 1998. Late papers will be returned unreviewed.

Notification of receipt will be e-mailed to the first author (or designated author) soon after receipt. Authors will be notified of acceptance before 10 March 1998. Camera-ready copies of final papers prepared in a format to be specified, preferably using a laser printer, must be received by 15 June 1998, along with a signed copyright release statement.

WORKSHOP ORGANIZERS

The workshop is being organized by Chrysanne DiMarco of the University of Waterloo, with the assistance of Graeme Hirst of the University of Toronto. The Program Chair is Eduard Hovy of USC/ISI.

General workshop questions:

Chrysanne DiMarco, cdimarco@logos.uwaterloo.ca, phone +1 519 888 4443

General paper-submission questions:

Eduard Hovy, hovy@isi.edu, phone +1 310 822 1510 x731

PROGRAM COMMITTEE

Eduard Hovy, USC/ISI, Marina del Rey (chair)

Stephan Busemann, DFKI, Saarbruecken

Susan Haller, University of Wisconsin-Parkside

Helmut Horacek, University of the Saarland

Xiaorong Huang, Formal Systems, Toronto

Kristiina Jokinen, ATR, Kyoto

Guy Lapalme, University of Montreal

Elisabeth Maier, DFKI, Saarbruecken

Chris Mellish, University of Edinburgh

Marie Meteer, BBN

Jon Oberlander, University of Edinburgh

Cecile Paris, CSIRO, Sydney

Owen Rambow, CoGenTex Inc., Ithaca

Ehud Reiter, University of Aberdeen

Elke Teich, Macquarie University, Sydney

Marilyn Walker, AT&T Labs Research, Florham Park

For more information, visit the INLG-98 Website:

http://logos.uwaterloo.ca/~inlg98