Learning non-cooperative dialogue behaviours

Ioannis Efstathiou, Oliver Lemon

Research output: Chapter in Book/Report/Conference proceedingConference contribution

14 Citations (Scopus)

Abstract

Non-cooperative dialogue behaviour has been identified as important in a variety of application areas, including education, military operations, video games and healthcare. However, it has not been addressed using statistical approaches to dialogue management, which have always been trained for co-operative dialogue. We develop and evaluate a statistical dialogue agent which learns to perform non-cooperative dialogue moves in order to complete its own objectives in a stochastic trading game. We show that, when given the ability to perform both cooperative and non-cooperative dialogue moves, such an agent can learn to bluff and to lie so as to win games more often -- against a variety of adversaries, and under various conditions such as risking penalties for being caught in deception. For example, we show that a non-cooperative dialogue agent can learn to win an additional 15.47% of games against a strong rule-based adversary, when compared to an optimised agent which cannot perform non-cooperative moves. This work is the first to show how an agent can learn to use non-cooperative dialogue to effectively meet its own goals.
Original languageEnglish
Title of host publication Proceedings of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue
PublisherAssociation for Computational Linguistics
Pages60-68
Number of pages9
ISBN (Print) 978-1-941643-21-1
Publication statusPublished - 18 Jun 2014
Event15th Annual Meeting of the Special Interest Group on Discourse and Dialogue 2014 - Philadelphia, PA, United States
Duration: 18 Jun 201420 Jun 2014

Conference

Conference15th Annual Meeting of the Special Interest Group on Discourse and Dialogue 2014
Abbreviated titleSIGDIAL 2014
CountryUnited States
CityPhiladelphia, PA
Period18/06/1420/06/14

Fingerprint Dive into the research topics of 'Learning non-cooperative dialogue behaviours'. Together they form a unique fingerprint.

Cite this