SOTAVerified

Planning, Inference and Pragmatics in Sequential Language Games

2018-05-30TACL 2018Code Available0· sign in to hype

Fereshte Khani, Noah D. Goodman, Percy Liang

Code Available — Be the first to reproduce this paper.

Reproduce

Code

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.

Reproductions