Publication

Embarrassingly Simple Unsupervised Aspect Extraction

Tulkens, S. & van Cranenburgh, A., 2020, Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Jurafsky, D., Chai, J., Schluter, N. & Tetreault, J. (eds.). ACL, p. 3182-3187 6 p.

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

We present a simple but effective method for aspect identification in sentiment analysis. Our unsupervised method only requires word embeddings and a POS tagger, and is therefore straightforward to apply to new domains and languages. We introduce Contrastive Attention (CAt), a novel single-head attention mechanism based on an RBF kernel, which gives a considerable boost in performance and makes the model interpretable. Previous work relied on syntactic features and complex neural models. We show that given the simplicity of current benchmark datasets for aspect extraction, such complex models are not needed. The code to reproduce the experiments reported in this paper is available at https://github.com/clips/cat.
Original languageEnglish
Title of host publicationProceedings of the 58th Annual Meeting of the Association for Computational Linguistics
EditorsDan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
PublisherACL
Pages3182-3187
Number of pages6
Publication statusPublished - 2020
Event58th Annual Meeting of the Association for Computational Linguistics -
Duration: 5-Jul-202010-Jul-2020

Conference

Conference58th Annual Meeting of the Association for Computational Linguistics
Period05/07/202010/07/2020

Event

58th Annual Meeting of the Association for Computational Linguistics

05/07/202010/07/2020

Event: Conference

Download statistics

No data available

ID: 129401782