Learning language games through interaction

Sida I. Wang, Percy Liang, Christopher D. Manning

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

34 Scopus citations

Abstract

We introduce a new language learning setting relevant to building adaptive natural language interfaces. It is inspired by Wittgenstein's language games: a human wishes to accomplish some task (e.g., achieving a certain configuration of blocks), but can only communicate with a computer, who performs the actual actions (e.g., removing all red blocks). The computer initially knows nothing about language and therefore must learn it from scratch through interaction, while the human adapts to the computer's capabilities. We created a game called SHRDLURN in a blocks world and collected interactions from 100 people playing it. First, we analyze the humans' strategies, showing that using compositionality and avoiding synonyms correlates positively with task performance. Second, we compare computer strategies, showing that modeling pragmatics on a semantic parsing model accelerates learning for more strategic players.

Original languageEnglish (US)
Title of host publication54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers
PublisherAssociation for Computational Linguistics (ACL)
Pages2368-2378
Number of pages11
ISBN (Electronic)9781510827585
StatePublished - Jan 1 2016
Event54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Berlin, Germany
Duration: Aug 7 2016Aug 12 2016

Publication series

Name54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers
Volume4

Other

Other54th Annual Meeting of the Association for Computational Linguistics, ACL 2016
CountryGermany
CityBerlin
Period8/7/168/12/16

All Science Journal Classification (ASJC) codes

  • Language and Linguistics
  • Linguistics and Language

Fingerprint Dive into the research topics of 'Learning language games through interaction'. Together they form a unique fingerprint.

  • Cite this

    Wang, S. I., Liang, P., & Manning, C. D. (2016). Learning language games through interaction. In 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers (pp. 2368-2378). (54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers; Vol. 4). Association for Computational Linguistics (ACL).