CALC-09

From ACL Wiki
Jump to navigation Jump to search

Workshop on Computational Approaches to Linguistic Creativity

It is generally agreed upon that "linguistic creativity" is a unique property of human language. Some claim that linguistic creativity is expressed in our ability to combine known words in a new sentence, others refer to our skill to express thoughts in figurative language, and yet others talk about syntactic recursion and lexical creativity.

For the purpose of this workshop, we treat the term "linguistic creativity" to mean "creative language usage at different levels", from the lexicon to syntax to discourse and text (see also topics and references, below).

The recognition of instances of linguistic creativity and the computation of their meaning constitute one of the most challenging problems for a variety of Natural Language Processing tasks, such as machine translation, text summarization, information retrieval, question answering, and sentiment analysis. Computational systems incorporating models of linguistic creativity operate on different types of data (including written text, audio/speech/sound, and video/images/gestures). New approaches might combine information from different modalities. Creativity-aware systems will improve the contribution Computational Linguistics has to offer to many practical areas, including education, entertainment, and engineering.

Within the scope of the workshop, the event is intended to be interdisciplinary. Besides contributions from an NLP perspective, we also welcome the participation of researchers who deal with linguistic creativity from different perspectives, including psychology, neuroscience, or human-computer interaction.

Location

View of Boulder from Bear Peak. University of Colorado at the far left.

The CALC-09 workshop will be held in conjunction with NAACL HLT 2009 in Boulder, Colorado, on June 4, 2009.

Topics

We are particularly interested in work on the automatic detection, classification, understanding, or generation of:

  • neologisms;
  • figurative language, including metaphor, metonymy, personification, idioms;
  • new or unconventional syntactic constructions ("May I serve who's next?") and constructions defying traditional parsers (e.g. gapping: "Many words were spoken, and sentiments expressed");
  • indirect speech acts (such as curses, insults, sarcasm and irony);
  • verbally expressed humor;
  • poetry and fiction;
  • and other phenomena illustrating linguistic creativity.

Depending on the state of the art of approaches to the various phenomena and languages, preference will be given to work on deeper processing (e.g., understanding, goal-driven generation) rather than shallow approaches (e.g., binary classication, random generation). We also welcome descriptions and discussions of:

  • computational tools that support people in using language creatively (e.g. tools for computer-assisted creative writing, intelligent thesauri);
  • computational and/or cognitive models of linguistic creativity;
  • metrics and tools for evaluating the performance of creativity-aware systems;
  • specific application scenarios of computational linguistic creativity;
  • design and implementation of creativity-aware systems.

Related topics, including corpora collection, elicitation, and annotation of creative language usage, will also be considered, as long as their relevance to automatic systems is clearly pointed out.

A (non-exhaustive) list of recent references is provided below to further illustrate the range of possible workshop topics.

Invited Speaker

Nick Montfort, MIT

Curveship: A System for Interactive Fiction and Interactive Narrating

Interactive fiction (often called "IF") is a venerable thread of creative computing that includes Adventure, Zork, and the computer game The Hitchhiker's Guide to the Galaxy as well as innovative recent work. These programs are usually known as "games," appropriately, but they can also be rich forms of text-based computer simulation, dialog systems, and examples of computational literary art. Theorists of narrative have long distinguished between the level of underlying content or story (which can usefully be seen as corresponding to the simulated world in interactive fiction) and that of expression or discourse (corresponding to the textual exchange between computer and user). While IF development systems have offered a great deal of power and flexibility to author/programmers by providing a computational model of the fictional world, previous systems have not systematically distinguished between the telling and what is told. Developers were not able to control the content and expression levels independently so that they could, for instance, have a program relate events out of chronological order or have it relate events from the perspective of different characters. Curveship is an interactive fiction system which draws on narrative theory and computational linguistics to allow the transformation of the narrating in these ways. This talk will briefly describe interactive fiction and narrative variation and will detail how Curveship provides these new capabilities.

Submissions

Submissions should describe original, unpublished work. Papers are limited to 8 pages. The style files can be found here: [1]. No author information should be included in the papers, since reviewing will be blind. Papers not conforming to these requirements are subject to rejection without review. Papers should be submitted via START [2] in the .PDF format.

We encourage submissions from everyone. For those who are new to ACL conferences and workshops, or with special needs, we are planning to set up a lunch mentoring program. Let us know if you are interested.

Travel Grants

We are happy to announce that up to eight (8) travel grants can be awarded to CALC-09 participants, thanks to NSF award #IIS-0906244.

Candidates must apply by sending the workshop chairs a short motivation statement. The statement should be submitted electronically to the workshop organizers (Anna Feldman [feldmana at mail.montclair.edu] and Birte Loenneker-Rodman [birte.loenneker at uni-hamburg.de]), by April 12, 2009.

The following criteria will be considered when selecting the awardees:

  1. paper accepted for presentation at the CALC-09 workshop (single author, first author, or co-author, preferably with other students only);
  2. if not from the U.S., resident of a hard-currency problem country as defined by ACL (Mexico, Central or South America, Asia (excluding Japan, Hong Kong, Korea, and Singapore), Africa, Central/Eastern Europe (countries east of Finland, Germany, Austria, or Italy and north of Greece and Turkey));
  3. especially if from the U.S., minority background (e.g., based on gender, disabilities, race);
  4. absence of other means of funding, as documented by the applicants;
  5. status (full-time students have precedence over any other category).

If the number of eligible applicants exceeds the number of available travel funds, the decision will be based on a) the quality of the paper as judged by the reviewers and by the workshop organizers, in conjunction with b) the submitted motivation statement.

Consequently, travel grants to participants in the CALC workshop who do not have a paper at CALC can be awarded only in very exceptional cases. Please contact the workshop organizers before applying.

Important Dates

  • Nov 1, 2008: 1st Call for papers issued
  • Jan 15, 2009: 2nd Call for papers issued
  • Feb 15, 2009: 3rd and final CFP
  • Feb 27, 2009 Mar 5, 2009: Deadline for paper submissions
  • Mar 30, 2009: Notification of paper acceptances
  • Apr 12, 2009: Camera-ready copies due
  • ~ Apr 26, 2009: Call for participation
  • June 4, 2009: CALC-09 workshop at NAACL HLT 2009

Organizers

  • Anna Feldman, Montclair State University (anna.feldman@montclair.edu)
  • Birte Loenneker-Rodman, International Computer Science Institute/University of Hamburg, Germany (birte.loenneker@uni-hamburg.de)

Program Committee

Additional Reviewers

  • Carmen Banea
  • Alessandro Valitutti

References

Here are some recent papers, related to the topics of the CALC-2009 workshop.

And here are two papers on intriguing syntactic constructions in English: