Planning, Inference and Pragmatics in Sequential Language Games

Fereshte Khani,Percy Liang,Noah D Goodman

doi:10.1162/tacl_a_00037

Fereshte Khani, Percy Liang + Show 1 more

Open Access

https://doi.org/10.1162/tacl_a_00037

Copy DOI

Abstract

We study sequential language games in which two players, each with private information, communicate to achieve a common goal. In such games, a successful player must (i) infer the partner’s private information from the partner’s messages, (ii) generate messages that are most likely to help with the goal, and (iii) reason pragmatically about the partner’s strategy. We propose a model that captures all three characteristics and demonstrate their importance in capturing human behavior on a new goal-oriented dataset we collected using crowdsourcing.

Highlights

IntroductionPeople routinely choose what to say based on their goals (planning), figure out the state of the world based on what others say (inference), all while taking into account that others are strategizing agents too (pragmatics)
As our interest is in modeling human communication in sequential language games, we evaluate PIP on its ability to predict how humans play InfoJigsaw
We identified three salient aspects— planning, inference, pragmatics—and proposed a unified model, PIP, that captures all three aspects simultaneously

Summary

Introduction

People routinely choose what to say based on their goals (planning), figure out the state of the world based on what others say (inference), all while taking into account that others are strategizing agents too (pragmatics). All three aspects have been studied in both the linguistics and AI communities. Markov Decision Processes and their extensions can be used to compute utility-maximizing actions via forward-looking recurrences (e.g., Vogel et al (2013a)). Model-theoretic semantics (Montague, 1973) provides a mechanism for utterances to constrain possible worlds, and this has been implemented recently in semantic parsing (Matuszek et al, 2012; Krishnamurthy and Kollar, 2013). For pragmatics, the cooperative principle of Grice (1975) can be realized by models in which a speaker simulates a listener—e.g., Franke (2009) and Frank and Goodman (2012)

Objectives

Methods

Results

Conclusion