A Bayesian Model for Joint Unsupervised Induction of Sentiment, Aspect and Discourse Representations

Angeliki Lazaridou, Ivan Titov, Caroline Sporleder

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

Abstract / Description of output

We propose a joint model for unsupervised induction of sentiment, aspect and
discourse information and show that by incorporating a notion of latent discourse relations in the model, we improve the prediction accuracy for aspect and sentiment polarity on the sub-sentential level. We deviate from the traditional view of discourse, as we induce types of discourse relations and associated discourse cues relevant to the considered opinion analysis task; consequently, the induced discourse relations play the role of opinion and aspect shifters. The quantitative analysis that we conducted indicated that the integration of a discourse model increased the prediction accuracy results with respect to the discourse-agnostic approach and the qualitative analysis suggests that the induced representations encode a meaningful discourse structure.
Original languageEnglish
Title of host publicationProceedings of the 51st Annual Meeting of the Association for Computational Linguistics, ACL 2013, 4-9 August 2013, Sofia, Bulgaria, Volume 1: Long Papers
PublisherAssociation for Computational Linguistics
Pages1630-1639
Number of pages10
ISBN (Print)978-1-937284-50-3
Publication statusPublished - Aug 2013

Fingerprint

Dive into the research topics of 'A Bayesian Model for Joint Unsupervised Induction of Sentiment, Aspect and Discourse Representations'. Together they form a unique fingerprint.

Cite this