LINGUIST List 32.2504

Wed Jul 28 2021

Calls: Cog Sci, Comp Ling, Neuroling, Pragmatics, Psycholing/Online

Editor for this issue: Lauren Perkins <laurenlinguistlist.org>



Date: 27-Jul-2021
From: Jennifer Hu <jennhumit.edu>
Subject: Meaning in Context Workshop NeurIPS 2021
E-mail this message to a friend

Full Title: Meaning in Context Workshop NeurIPS 2021
Short Title: MiC

Date: 13-Dec-2021 - 14-Dec-2021
Location: Virtual, USA
Contact Person: Jennifer Hu
Meeting Email: < click here to access email >
Web Site: https://mic-workshop.github.io/

Linguistic Field(s): Cognitive Science; Computational Linguistics; Neurolinguistics; Pragmatics; Psycholinguistics

Call Deadline: 10-Sep-2021

Meeting Description:

Pragmatics – the aspects of language use that involve reasoning about context and other agents’ goals and belief states – has traditionally been treated as the “wastebasket” of language research (Bar-Hillel 1971), posing a challenge for both cognitive theories and artificial intelligence systems. Ideas from theoretical linguistics have inspired computational applications, such as in referential expression generation (Krahmer and van Deemter, 2012) or computational models of dialogue and recognition of speech or dialogue acts (Bunt and Black, 2000; Jurafsky, 2006; Ginzburg and Fernández, 2010; Bunt, 2016). But only recently, powerful artificial models based on neural or subsymbolic architectures have come into focus that generate or interpret language in pragmatically sophisticated and potentially open-ended ways (Golland et al. 2010, Andreas and Klein 2016, Monroe et al. 2017, Fried et al. 2018), building upon simultaneous advances in the cognitive science of pragmatics (Franke 2011, Frank and Goodman 2012). However, such models still fall short of human pragmatic reasoning in several important aspects. For example, existing approaches are often tailored to, or even trained to excel on, a specific pragmatic task (e.g., Mao et al. (2016) on discriminatory object description), leaving human-like task flexibility unaccounted for. It also remains underexplored how pragmatics connects to domain-general reasoning, how it may be efficiently implemented, and how it may arise over the course of learning and evolution.

In this workshop, we aim to bring together researchers from Cognitive Science, Linguistics, and Machine Learning to think critically about the next generation of artificial pragmatic agents and theories of human pragmatic reasoning. This workshop will take place at the 2021 conference on Neural Information Processing Systems (NeurIPS).

Call for Papers:

We invite papers from Cognitive Science, Linguistics, and Machine Learning that explore synergies between pragmatics in humans and machines. In addition to theoretical or empirical findings, we welcome “blue sky” reflections upon open problems, prospects for future development, and positions on the current state of the art.

Topics of interest include but are not limited to:
- Successful or failed integrations of pragmatics into artificial agents
- Datasets, tasks, or evaluation metrics for measuring pragmatic reasoning
- Computational models of human pragmatic reasoning
- Applications of pragmatics in artificial agents in various domains
- Surveys or replication of existing work
- Proposals for longer-term research programs

Submission Instructions:
Authors may choose between two submission formats: short paper or abstract. Short papers are limited to 4 pages of content, with unlimited pages for references and appendices. Abstracts are limited to 1 page of content, with unlimited pages for references and appendices. We ask that authors use appendices only for minor details that are not necessary for understanding the paper. Submissions must be fully anonymized. The review process will be double-blind.

All accepted papers will be presented in a virtual poster session and listed on the website. A small number of accepted papers will be selected to be presented as contributed talks. We particularly encourage submissions from groups that are underrepresented at machine learning conferences based on factors including gender, gender identity, sexual orientation, race, ethnicity, nationality, disability, and institution.

The paper template and style files can be found on our website. Do not use the standard NeurIPS style files. Please refer to the NeurIPS 2021 formatting instructions (also available on our website) for best practices regarding style.

The submission link and details will be provided closer to the submission deadline.

Dual submission policy:
We welcome papers that are currently under review, but discourage submission of papers that will be presented at the main conference or have been previously published at an ML conference. Accepted papers will be published on the workshop homepage, but will not be part of the official proceedings and are to be considered non-archival.

Important dates:
Submission deadline: September 10, 2021
Author notification: October 22, 2021
Speaker videos due: November 8, 2021




Page Updated: 28-Jul-2021