( events)   Timezone: »  
Mon Dec 13 05:55 AM -- 02:05 PM (PST)
Meaning in Context: Pragmatic Communication in Humans and Machines
Jennifer Hu · Noga Zaslavsky · Aida Nematzadeh · Michael Franke · Roger Levy · Noah Goodman

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 largely 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.

Opening remarks
The Neurobiology of Pragmatics (Invited talk)
Perspective-taking and Pragmatics for Generating Empathetic Responses Focused on Emotion Causes (Contributed talk)
Lexical Pragmatics in the Wild: The Case of Complement Coercion (Contributed talk)
Human Production Strategies for Neural Language Generation (Invited talk)
Break / Meet-and-greet #1 (Break)
Panel (Discussion panel)
Underspecification in Executable Instructions (Poster)
The gap between QUD-based topic determination and learning-based topic extraction for NLG (Poster)
A model of contextual representations and their role for linguistic prediction (Poster)
Social inferencing in communication (Poster)
Ambiguity Advantage under Meaning Activation (Poster)
The role of joint utility and pragmatic reasoning in cooperative communication (Poster)
Context in Automated Affect Recognition (Poster)
Analysing Human Strategies of Information Transmission as a Function of Discourse Context (Poster)
Unveiling the Meaning Through Emotional Context (Poster)
The Right Words for the Job: Coordinating on Task-Relevant Conventions via Bayesian Program Learning (Invited talk)
Loopholes: a Window into Value Alignment and the Learning of Meaning (Contributed talk)
Intuitive Image Descriptions are Context-Sensitive (Contributed talk)
Incorporating Interaction in Models of Language Use (Invited talk)
Break / Meet-and-greet #2 (Break)
Living in the moment: Studying pragmatic inference with temporally sensitive measures of comprehension (Invited talk)
Efficient Pragmatic Program Synthesis with Informative Specifications (Contributed talk)
Multi-party referential communication in complex strategic games (Contributed talk)
Language, Context, and Action: A Semantic Machines View of Conversational AI (Invited talk)
Closing remarks