2018Q1 Reports: ACL 2018

General Chair

Claire Cardie, Cornell University

The 56th annual meeting of the Association for Computational Linguistics (ACL 2018) will take place in Melbourne, Australia at the Melbourne Convention and Exhibition Centre July 15th-20th, 2018. I believe that we have an excellent team for putting together the conference. For the organizing positions that I had primary control over (Workshops, Tutorials, Demos, Publications, Student Research Workshop), I attempted to recruit an even number of women and men. Among these, there are 7 female organizers (not including me) and 8 male organizers.

We have been using Slack for most intra-committee communication, and especially for requests to the Webmaster.

This report is structured around the activities associated with each Chair position, each with a separate section below.

Aravind Joshi tribute: In addition to what is reported below, I am hoping that we can incorporate some kind of tribute to Aravind Joshi and am working with the Local Arrangements and Program Chairs to determine what would be best. One option would involve making use of about 30 minutes of an interview that Joel Tetrault and Ellie Pavlick did with Aravind in 2016 (as part of a funny video they did to introduce the Poster Madness session of NAACL 2016 (https://www.youtube.com/watch?v=vQxQ25x24nw). According to Joel,

“...I have a lot of unused footage from that interview - maybe 30+ minutes. At a certain point I just started asking him random questions about what he likes, his past, etc. I'll have to make sure I still have it (switched computers) but pretty sure I do. If this seems like it could be nice/fun to include as a memoriam, just let me know and I can find it and clean it up.”

The idea would be to run this video --- either as part of a plenary session or continuously at a location where people could view it at their leisure. Getting feedback on this from the Executive Committee would be great!

Program Co-Chairs

Iryna Gurevych, TU Darmstadt
Yusuke Miyao, National Institute of Informatics

This year, the program co-chairs requested nominations from the community for area chairs, reviewers and invited speakers through an open call publicized in the Latest News section of the ACL 2018 website: http://acl2018.org/2017/09/06/call-for-nominations/.

They recruited 61 area chairs for 21 areas, including 1-2 senior chairs per area. The senior chairs are responsible for maintaining the overall process of reviewing in each area, while each area chair is assigned around 30 submissions and is responsible for managing reviews for the assigned submissions.

Dialogue and Interactive Systems:

• Asli Celikyilma (senior chair)
• Verena Rieser (senior chair)
• Milica Gasic
• Jason Williams

Discourse and Pragmatics:

• Manfred Stede
• Ani Nenkova (senior chair)

Document Analysis:

• Hang Li (senior chair)
• Yiqun Liu
• Eugene Agichtein

Generation:

• Ioannis Konstas
• Claire Gardent (senior chair)

Information Extraction and Text Mining:

• Feiyu Xu
• Kevin Cohen
• Zhiyuan Liu
• Ralph Grishman (senior chair)
• Yi Yang
• Nazli Goharian

Linguistic Theories, Cognitive Modeling and Psycholinguistics:

• Shuly Wintner (senior chair)
• Tim O'Donnell (senior chair)

Machine Learning:

• Andre Martins
• Ariadna Quattoni
• Jun Suzuki (senior chair)

Machine Translation:

• Yang Liu
• Matt Post (senior chair)
• Lucia Specia
• Dekai Wu

Multidisciplinary (also for AC COI):

• Yoav Goldberg
• Anders Søgaard
• Mirella Lapata

Multilinguality:

• Bernardo Magnini (senior chair)

Phonology, Morphology and Word Segmentation:

• Graham Neubig
• Hai Zhao (senior chair)
• Question Answering:
• Lluís Màrquez (senior chair)
• Teruko Mitamura
• Zornitsa Kozareva
• Richard Socher

Resources and Evaluation:

• Gerard de Melo
• Karën Fort (senior chair)
• Sara Tonelli

Sentence-level Semantics:

• Luke Zettlemoyer (senior chair)
• Ellie Pavlick
• Jacob Uszkoreit

Sentiment Analysis and Argument Mining:

• Smaranda Muresan
• Benno Stein
• Yulan He (senior chair)

Social Media:

• David Jurgens
• Jing Jiang (Senior Chair)

Summarization:

• Kathleen McKeown (senior chair)
• Xiaodan Zhu

Tagging, Chunking, Syntax and Parsing:

• Liang Huang (senior chair)
• Weiwei Sun
• Željko Agić
• Yue Zhang

Textual Inference and Other Areas of Semantics:

• Michael Roth (senior chair)
• Fabio Massimo Zanzotto (senior chair)

Vision, Robotics, Multimodal, Grounding and Speech:

• Yoav Artzi (senior chair)
• Shinji Watanabe
• Timothy Hospedales

Word-level Semantics:

• Ekaterina Shutova
• Roberto Navigli (senior chair)

The call for nominations posted in September 2017 resulted in 752 responses in total. Regarding the area chairs, out of 388 valid nominations, 299 unique persons were suggested; 110 persons were self-nominations. About 70% of the final area chairs were nominated by the community. We collected 936 valid nominations for reviewers. At the PhD level, 139 persons were self-nominations and 129 were nominated by others. At the PostDoc/Ass.Prof. level, 160 were self-nominated, 112 nominated by others. At the Prof. level, 221 persons were self-nominated, 175 nominated by others. We also received 138 unique nominations for invited speakers.

As in ACL 2017, we introduced a special area for handling COI of area chairs. The strategy is that if AC has a COI in their area, we try to find another area that still fits the paper well. If this is not the case, the paper is moved to the “Multidisciplinary / COI” area. This area is handled by experienced area chairs.

Right after the submission deadline, there are 1045 long and 576 short papers. Several submissions have already been identified as desk reject, but the program chairs and area chairs are still working on cleaning them up at the moment. Areas with more than a hundred submissions include: Information Extraction and Text Mining, Machine Learning, Machine Translation, Document Analysis, and Dialogue and Interactive Systems.

Summary of upcoming deadlines:

• March 26th–28th, 2018 Author Response Period
• April 20th, 2018 Notification of Acceptance
• May 11th, 2018 Camera-ready Due
• July 15th, 2018 Tutorials
• July 16th–18th, 2018 Main Conference
• July 19th–20th, 2018 Tutorials and Workshops

We have already announced two invited speakers:

• Carolyn Penstein Rose, Language Technologies Institute at Carnegie Mellon University, USA
• Anton van den Hengel, Australian Centre for Visual Technologies at University of Adelaide, Australia

In a cooperation with NAACL 2018 Program Chairs, we implemented a structured review form that should guide reviewers to better assess strengths and weaknesses of the submissions as well as to help the area chairs in their acceptance/rejection decisions. The form has been made publicly available (http://acl2018.org/2018/02/20/sample-review-form/).

Summary of upcoming tasks

• Finish area re-assignments and desk rejects
• Initiate the review process
• Publish statistics on submissions
• Initiate Author response period
• Collect decisions from ACs
• Elicit meta-reviews
• Decide border cases
• Publish notification of acceptance
• Update financial picture
• Integrate TACL papers
• Collect camera ready submissions
• Create the conference program
• Recruit session chairs
• Compile statistics for ACL wiki + business meeting
• Compile report
• Publish updates on the ACL web site

Tutorial Chairs

Yoav Artzi, Cornell University
Jacob Eisenstein, Georgia Institute of Technology

In total, we received 49 submissions for the joint ACL/COLING/NAACL/EMNLP call, and we accepted 28 of them. 28 tutorials had ACL as the preferred conference: 13 were rejected, 6 were selected for their alternative choice, and the rest were accepted. Eight tutorials were selected for ACL:

1. Neural Approaches to Conversational AI

Jianfeng Gao, Michel Galley and Lihong Li

Developing an intelligent dialogue system that not only emulates human conversation, but also can answer questions of topics ranging from latest news of a movie star to Einstein's theory of relativity, and fulfill complex tasks such as travel planning, has been one of the longest running goals in AI. The goal remains elusive until recently when we started observing promising results in both the research community and industry as the large amount of conversation data is available for training and the breakthroughs in deep learning (DL) and reinforcement learning (RL) are applied to conversational AI. In this tutorial, we start with a brief introduction to the recent progress on DL and RL that is related to natural language processing and conversational AI. Then, we describe in detail the state-of-the-art neural approaches developed for three types of dialogue systems. The first is a question answering (QA) agent. Equipped with rich knowledge drawn from various data sources including Web documents and pre-complied knowledge graphs (KG's), the QA agent can provide concise direct answers to user queries. The second is a task-oriented dialogue system that can help users accomplish tasks ranging from meeting scheduling to vacation planning. The third is a social chat bot which can converse seamlessly and appropriately with humans, and often plays roles of a chat companion and a recommender. In the final part of the tutorial, we review attempts to developing open-domain conversational AI systems that combine the strengths of different types of dialogue systems.

2. Deep Reinforcement Learning for NLP

William Yang Wang, Jiwei Li and Xiaodong He

Many Natural Language Processing (NLP) tasks (including generation, language grounding, reasoning, information extraction, coreference resolution, and dialog) can be formulated as deep reinforcement learning (DRL) problems. However, since language is often discrete and the space for all sentences is infinite, there are many challenges for formulating reinforcement learning problems of NLP tasks. In this tutorial, we provide a gentle introduction to the foundation of deep reinforcement learning, as well as some practical DRL solutions in NLP. We describe recent advances in designing deep reinforcement learning for NLP, with a special focus on generation, dialogue, and information extraction. Finally, we discuss why they succeed, and when they may fail, aiming at providing some practical advice about deep reinforcement learning for solving real-world NLP problems.

3. Neural Semantic Parsing

Luke Zettlemoyer, Matt Gardner, Pradeep Dasigi, Srinivasan Iyer and Alane Suhr

Semantic parsers translate natural language utterances into machine-executable logical forms or programs, and are thus key components in natural language understanding systems. Semantic parsing is a well-established research area, with application in areas such as question answering, instruction following, voice assistants, and code generation. In the last two years, the models used for semantic parsing have changed dramatically,with the introduction of neural methods that allow us to rethink many of the previous assumptions underlying semantic parsing. Traditionally, the executable formalisms and models used in semantic parsing research have been heavily reliant on notions of formal semantics in linguistics, such as λ-calculus generated by a CCG parser. However, recent work with neural encoder-decoder semantic parsers allow for more accessible formalisms, such as standard programming languages, and NMT-style models that are much more approachable to a broader NLP audience. We will present an overview of modern neural methods for semantic parsing and how they have changed semantic parsing research.

4. Beyond Multiword Expressions: Processing Idioms and Metaphors

Valia Kordoni

Idioms and metaphors are characteristic to all areas of human activity and to all types of discourse. Their processing is a rapidly growing area in NLP, since they have become a big challenge for NLP systems. Their omnipresence in language has been established in a number of corpus studies and the role they play in human reasoning has also been confirmed in psychological experiments. This makes idioms and metaphors an important research area for computational and cognitive linguistics, and their automatic identification and interpretation indispensable for any semantics-oriented NLP application. This tutorial aims to provide attendees with a clear notion of the linguistic characteristics of idioms and metaphors, computational models of idioms and metaphors using state-of-the-art NLP techniques, their relevance for the intersection of deep learning and natural language processing, what methods and resources are available to support their use, and what more could be done in the future. Our target audience are researchers and practitioners in machine learning, parsing (syntactic and semantic) and language technology, not necessarily experts in idioms and metaphors, who are interested in tasks that involve or could benefit from considering idioms and metaphors as a pervasive phenomenon in human language and communication.

5. Connecting Language and Vision to Actions

Peter Anderson, Abhishek Das and Qi Wu

A long-term goal of AI research is to build intelligent agents that can see the rich visual environment around us, communicate this understanding in natural language to humans and other agents, and act in a physical or embodied environment. To this end, recent advances at the intersection of language and vision have made incredible progress -- from being able to generate natural language descriptions of images/videos, to answering questions about them, to even holding free-form conversations about visual content! However, while these agents can passively describe images or answer (a sequence of) questions about them, they cannot act in the world (what if I cannot answer a question from my current view, or I am asked to move or manipulate something?). Thus, the challenge now is to extend this progress in language and vision to embodied agents that take actions and actively interact with their visual environments. To reduce the entry barrier for new researchers, this tutorial will provide an overview of the growing number of multimodal tasks and datasets that combine textual and visual understanding. We will comprehensively review existing state-of-the-art approaches to selected tasks such as image captioning, visual question answering (VQA) and visual dialog, presenting the key architectural building blocks (such as co-attention) and novel algorithms (such as cooperative/adversarial games) used to train models for these tasks. We will then discuss some of the current and upcoming challenges of combining language, vision and actions, and introduce some recently-released interactive 3D simulation environments designed for this purpose.

6. 100 Things You Always Wanted to Know about Semantics & Pragmatics But Were Afraid to Ask

Emily M. Bender

Meaning is a fundamental concept in Natural Language Processing (NLP), given its aim to build systems that mean what they say to you, and understand what you say to them. In order for NLP to scale beyond partial, task-specific solutions, it must be informed by what is known about how humans use language to express and understand communicative intents. The purpose of this tutorial is to present a selection of useful information about semantics and pragmatics, as understood in linguistics, in a way that's accessible to and useful for NLP practitioners with minimal (or even no) prior training in linguistics. The tutorial content is based on a manuscript in progress I am co-authoring with Prof. Alex Lascarides of the University of Edinburgh.

7. Multi-lingual Entity Discovery and Linking

Avirup Sil, Heng Ji, Dan Roth and Silviu-Petru Cucerzan

The primary goals of this tutorial are to review the framework of cross-lingual EL and motivate it as a broad paradigm for the Information Extraction task. We will start by discussing the traditional EL techniques and metrics and address questions relevant to the adequacy of these to across domains and languages. We will then present more recent approaches such as Neural EL, discuss the basic building blocks of a state-of-the-art neural EL system and analyze some of the current results on English EL. We will then proceed to Cross-lingual EL and discuss methods that work across languages. In particular, we will discuss and compare multiple methods that make use of multi-lingual word embeddings. We will also present EL methods that work for both name tagging and linking in very low resource languages. Finally, we will discuss the uses of cross-lingual EL in a variety of applications like search engines and commercial product selling applications. Also, contrary to the 2014 EL tutorial, we will also focus on Entity Discovery which is an essential component of EL.

8. Variational Inference and Deep Generative Models

Wilker Aziz and Philip Schulz

NLP has seen a surge in neural network models in recent years. These models provide state-of-the-art performance on many supervised tasks. Unsupervised and semi-supervised learning has only been addressed scarcely, however. Deep generative models (DGMs) make it possible to integrate neural networks with probabilistic graphical models. Using DGMs one can easily design latent variable models that account for missing observations and thereby enable unsupervised and semi-supervised learning with neural networks. The method of choice for training these models is variational inference. This tutorial offers a general introduction to variational inference followed by a thorough and example-driven discussion of how to use variational methods for training DGMs. It provides both the mathematical background necessary for deriving the learning algorithms as well as practical implementation guidelines. Importantly, the tutorial will cover models with continuous and discrete variables. We provide practical coding exercises implemented in IPython notebooks as well as short notes on the more intricate mathematical details that the audience can use as a reference after the tutorial. We expect that with these additional materials the tutorial will have a long-lasting impact on the community.

Workshop Chairs

Brendan O’Connor, University of Massachusetts Amherst
Eva Maria Vecchi, University of Stuttgart / University of Cambridge

The workshop chairs selected 15 workshops to be held immediately following the ACL 2018 conference. There will be one additional workshop - the Student Research Workshop (SRW) which will be held during one of the evening poster sessions during the main conference. The workshops were selected using a joint call and review procedure, as a joint committee comprised of the workshop organizers of the 2018 editions of ACL, NAACL, COLING and EMNLP. The workshop review process followed the procedure of the previous year, namely: Each of the workshop proposals was initially reviewed by 2 members of the committee in the SoftConf system, with numerical scores and textual comments and most committee members reviewing around 15 proposals. To aid in the review process, we attempted to first categorize the workshop proposals, to help align proposals with areas of expertise on the committee. This categorization proved quite difficult because many proposals intentionally spanned several disciplines, but it did help identify proposals that were similar. As was done last year, we also conducted a web-based survey to ACL members to compare the popularity of workshops on similar topics and first-time workshops, as well as the past attendance numbers if available.

Before considering the bulk of the 58 submissions, we note that there are a handful of large, long-standing workshops that the ACL organization agrees to pre-admit, including *SEM, WMT, CoNLL, and SemEval. These were all placed at their first-choice venue.

Workshop proposers marked a first and second choice of conference; the workshops we accepted to ACL all had ACL as their first choice. (Two other submissions that had their first choice as ACL were instead accepted to their second choice. One submission with ACL as a first choice was rejected. 14 other submissions had ACL as a second choice; none of them was assigned to ACL.) Here are the 15 selected workshops / colocated conferences:

Thursday July 19, 2018

Abbreviation	Title	Organizers	Website
BioNLP	BioNLP 2018	Kevin Bretonnel Cohen, Dina Demner-Fushman, Sophia Ananiadou, and Jun-ichi Tsujii	https://aclweb.org/aclwiki/BioNLP_Workshop
DLNLPLR	Deep Learning Approaches for Low Resource Natural Language Processing	Reza Haffari, Colin Cherry, George Foster, Shahram Khadivi, Bahar Salehi	https://sites.google.com/site/dlnlplr18/home
CALCS	Third Workshop on Computational Approaches to Linguistic Code-Switching	Gustavo Aguilar, Fahad AlGhamdi, Victor Soto, Thamar Solorio, Mona Diab, Julia Hirschberg	https://code-switching.github.io/2018/
MSR	Multilingual Surface Realization: Shared Task and Beyond	Simon Mille, Bernd Bohnet, Leo Wanner, Anya Belz, Emily Pitler	http://taln.upf.edu/pages/msr2018-ws/
NLPTEA	The 5th Workshop on Natural Language Processing Techniques for Educational Applications	Yuen-Hsien Tseng, Hsin-Hsi Chen, Vincent Ng, Mamoru Komachi	https://sites.google.com/view/nlptea2018
CogCL	Cognitive Aspects of Computational Language Learning and Processing	Marco Idiart, Alessandro Lenci, Thierry Poibeau and Aline Villavicencio	https://sites.google.com/view/cognitivews2018/home
RELNLP	Workshop on Relevance of Linguistic Structure in Neural Architectures for NLP	Georgiana Dinu, Miguel Ballesteros, Yoav Goldberg, Avirup Sil, Tahira Naseem, Samuel Bowman, Wael Hamza, Anders Sogaard and Radu Florian	https://sites.google.com/view/relsnnlp
MRQA	Workshop on Machine Reading for Question Answering	Eunsol Choi, Minjoon Seo, Danqi Chen, Robin Jia and Jonathan Berant	https://mrqa2018.github.io/

Friday July 20, 2018

Abbreviation	Title	Organizers	Website
ECONLP	1st Workshop on Economics and Natural Language Processing	Udo Hahn and Ming-Feng Tsai	http://www.julielab.de/econlp2018.html
NEWS	The Seventh Named Entities Workshop	Nancy Chen, Xiangyu Duan, Rafael E. Banchs, Min Zhang and Haizhou Li	http://workshop.colips.org/news2018/
NLPOSS	Workshop for NLP Open Source Software	Masato Hagiwara, Dmitrijs Milajevs, Eunjeong Park and Liling Tan	https://nlposs.github.io/
SocialNLP	Sixth International Workshop on Natural Language Processing for Social Media	Lun-Wei Ku and Cheng-Te Li	https://sites.google.com/site/socialnlp2018/
MML_Challenge	First Workshop on Computational Modeling of Human Multimodal Language	AmirAli Bagher Zadeh, Louis-Philippe Morency, Soujanya Poria, Erik Cambria, Stefan Scherer and Paul Liang	http://multicomp.cs.cmu.edu/acl2018multimodalchallenge/
RepL4NLP	3rd Workshop on Representation Learning for NLP	Isabelle Augenstein, Kris Cao, He He, Felix Hill, Spandana Gella, Jamie Ryan Kiros, Hongyuan Mei and Dipendra Misra	https://sites.google.com/site/repl4nlp2018/
NMT	The 2nd Workshop on Neural Machine Translation and Generation	Alexandra Birch, Andrew Finch, Minh-Thang Luong, Graham Neubig and Yusuke Oda	https://sites.google.com/site/wnmt18/