Planning, Inference and Pragmatics in Sequential Language Games
This work addresses the challenge of understanding and simulating human-like communication in AI systems, but it appears incremental as it builds on existing concepts in language games and pragmatics.
The paper tackled the problem of modeling sequential language games where players with private information communicate to achieve a common goal, and the result was a proposed model that captures inference, planning, and pragmatic reasoning, demonstrating its importance in matching human behavior on a new crowdsourced dataset.
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.