Predicting the Resolution of Referring Expressions from User Behavior

Nikos Engonopoulos, Martin Villalba, Ivan Titov, Alexander Koller

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

Abstract / Description of output

We present a statistical model for predicting how the user of an interactive, situated NLP system resolved a referring expression. The model makes an initial prediction based on the meaning of the utterance, and revises it continuously based on the user behavior. The combined model outperforms its components in predicting reference resolution and when to give feedback.
Original languageEnglish
Title of host publicationProceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, EMNLP 2013, 18-21 October 2013, Grand Hyatt Seattle, Seattle, Washington, USA, A meeting of SIGDAT, a Special Interest Group of the ACL
PublisherAssociation for Computational Linguistics
Number of pages6
ISBN (Print)978-1-937284-97-8
Publication statusPublished - 2013


Dive into the research topics of 'Predicting the Resolution of Referring Expressions from User Behavior'. Together they form a unique fingerprint.

Cite this