Uphill Battles in Language Processing
Scaling Early Achievements to Robust Methods


NSF-supported workshop to be held in conjunction with EMNLP in Austin, Texas, with partial funding available for students and post-docs presenting posters at the workshop


Early researchers in Natural Language Processing had lofty goals, including getting computers to understand stories, engage in natural, cooperative dialogues with people, and translate text and speech fluently and accurately from one human language to another. While there were significant early achievements (including systems such as SHRDLU, LUNAR and COOP), the knowledge they were based on and the techniques they employed could not be scaled up for practical use.

While much of what early researchers set out to achieve has been either forgotten or side-lined in favor of what can be done by exploiting large data sets and processing power, its potential value has not gone away: There is much to be gained from recognizing not just what was said, but why; from identifying conclusions people naturally draw from both what has been said and hasn't; and from representing domains in a sufficiently rich way to reduce reliance on what is explicit in a text. As such, we believe there can be a broad and positive impact of reviving early aspirations in the current context of large data sets, "deep" and probabilistic methods, and (especially) methods that aim to combine the capabilities of logical and data-driven conclusions.

This workshop will remind the community of early goals and attempts to achieve them, the uphill battles that remain, and hopefully revive them in a context in which much more can be done. The workshop will be split into four sessions, covering different areas and challenges. Each session will start with four short (10 minute) presentations, two by established researchers who carried out early work in the area, and two by more junior researchers who are known for their work on specific problems in the area. Each session will have a moderator, who will then invite the speakers and audience to discuss open questions. The four sessions and the invited speakers are listed below.


Text Understanding

Hal Daume III, University of Maryland, College Park
Andrew Kehler, University of California, San Diego
Chris Manning, Stanford University
Marie-Catherine de Marneffe, Ohio State University

Generation

Ioannis Konstas, University of Washington
Kathleen McKeown, Columbia University
Margaret Mitchell*, Microsoft Research
Donia Scott, University of Sussex
* Grounded language generation

Dialogue and Speech

David DeVault, University of Southern California
Mark Liberman, University of Pennsylvania
Diane Litman, University of Pittsburgh
Amanda Stent, Bloomberg

Grounded Language

James Allen, University of Rochester / IHMC
Joyce Chai, Michigan State University
Yejin Choi, University of Washington
Mark Steedman, University of Edinburgh


The workshop will also feature a poster session for students and researchers to present and discuss their current work. A short description of each poster will appear in the workshop proceedings.

9:00 Text Understanding
Invited talks, followed by discussion
Chairs: Annie Louis, Michael Roth
Reading between the Lines [abstract] [slides]
Hal Daume III
Opportunities and Challenges for a Bayesian Approach to Language Processing [abstract] [slides]
Andrew Kehler
A (maybe not yet) Unified Theory of Inference for Text Understanding [abstract] [slides]
Chris Manning
Drawing Inferences [abstract] [slides]
Marie-Catherine de Marneffe
10:20 Poster Boasters I
An Analysis of Prerequisite Skills for Reading Comprehension
Saku Sugawara, Akiko Aizawa
Bridging the gap between computable and expressive event representations in Social Media
Darina Benikova, Torsten Zesch
Statistical Script Learning with Recurrent Neural Networks
Karl Pichotta, Raymond Mooney
Moving away from semantic overfitting in disambiguation datasets
Marten Postma, Filip Ilievski, Piek Vossen, Marieke van Erp
Unsupervised Event Coreference for Abstract Words
Dheeraj Rajagopal, Eduard Hovy, Teruko Mitamura
Towards Broad-coverage Meaning Representation: The Case of Comparison Structures
Omid Bakhshandeh, James Allen
10:30 Coffee break
11:00 Natural Language Generation
Invited talks, followed by discussion
Chair: Michael White
Neural Natural Language Generation [abstract] [slides]
Ioannis Konstas
Uphill Battles in Language Generation: Sentence Planning and Lexical Choice [slides]
Kathleen McKeown
Strong Baselines, Evaluation, and the Role of Humans in Grounded Language Generation [abstract] [slides]
Margaret Mitchell
An Uphill Battle: Achieving Pragmatic Congruency in Multilingual Texts [abstract] [slides]
Donia Scott
12:20 Poster Boasters II
DialPort: A General Framework for Aggregating Dialog Systems
Tiancheng Zhao, Kyusong Lee, Maxine Eskenazi
C2D2E2: Using Call Centers to Motivate the Use of Dialog and Diarization in Entity Extraction
Ken Church, Weizhong Zhu, Jason Pelecanos
Visualizing the Content of a Children's Story in a Virtual World: Lessons Learned
Quynh Ngoc Thi Do, Steven Bethard, Marie-Francine Moens
Stylistic Transfer in Natural Language Generation Systems Using Recurrent Neural Networks
Jad Kabbara and Jackie Chi Kit Cheung
Using Language Groundings for Context-Sensitive Text Prediction
Timothy Lewis, Cynthia Matuszek, Amy Hurst, Matthew Taylor
Towards a continuous modeling of natural language domains
Sebastian Ruder, Parsa Ghaffari, John G. Breslin
12:30 Lunch break
14:00 Dialogue and Speech
Invited talks, followed by discussion
Chair: Bonnie Webber
Toward Fluid Conversational Interaction in Spoken Dialogue Systems [abstract] [slides]
David DeVault
Three Steps towards Real Artificial Speech Communication [abstract] [slides]
Mark Liberman
Cooperation in Dialogue Systems from Eliza to Alexa [abstract] [slides]
Diane Litman
Uphill Battles in Task Modeling and Grounding for Dialog [abstract] [slides]
Amanda Stent
15:20 Poster Session
including coffee break
16:30 Grounded Language
Invited talks, followed by discussion
Chair: Luke Zettlemoyer
Uphill Battles: Language Grounded in Reasoning Agents [abstract] [slides]
James Allen
Language Grounding towards Situated Human-Robot Communication [abstract] [slides]
Joyce Chai
Knowledge about the World [abstract] [slides]
Yejin Choi
Grounding Computational Linguistics in AI Planning [abstract] [slides]
Mark Steedman
17:50 Closing

Program Committee