Siamese network-based supervised topic modeling

Minghui Huang, Yanghui Rao, Yuwei Liu, Haoran Xie, Fu Lee Wang

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)

Abstract

Label-specific topics can be widely used for supporting personality psychology, aspect-level sentiment analysis, and cross-domain sentiment classification. To generate label-specific topics, several supervised topic models which adopt likelihood-driven objective functions have been proposed. However, it is hard for them to get a precise estimation on both topic discovery and supervised learning. In this study, we propose a supervised topic model based on the Siamese network, which can trade off label-specific word distributions with document-specific label distributions in a uniform framework. Experiments on real-world datasets validate that our model performs competitive in topic discovery quantitatively and qualitatively. Furthermore, the proposed model can effectively predict categorical or real-valued labels for new documents by generating word embeddings from a label-specific topical space.

Original languageEnglish
Title of host publicationProceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018
EditorsEllen Riloff, David Chiang, Julia Hockenmaier, Jun'ichi Tsujii
PublisherAssociation for Computational Linguistics (ACL)
Pages4652-4662
Number of pages11
ISBN (Electronic)9781948087841
Publication statusPublished - 2018
Externally publishedYes
Event2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018 - Brussels, Belgium
Duration: 31 Oct 20184 Nov 2018

Publication series

NameProceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018

Conference

Conference2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018
CountryBelgium
CityBrussels
Period31/10/184/11/18

    Fingerprint

Cite this

Huang, M., Rao, Y., Liu, Y., Xie, H., & Wang, F. L. (2018). Siamese network-based supervised topic modeling. In E. Riloff, D. Chiang, J. Hockenmaier, & J. Tsujii (Eds.), Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018 (pp. 4652-4662). (Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018). Association for Computational Linguistics (ACL). https://www.aclweb.org/anthology/D18-1494/