Siamese Network-Based Supervised Topic Modeling

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


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.
Anthology ID:
D18-1494
Volume:
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
Month:
October-November
Year:
2018
Address:
Brussels, Belgium
Editors:
Ellen Riloff, David Chiang, Julia Hockenmaier, Jun’ichi Tsujii
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
4652–4662
Language:
URL:
https://aclanthology.org/D18-1494
DOI:
10.18653/v1/D18-1494
Bibkey:
Cite (ACL):
Minghui Huang, Yanghui Rao, Yuwei Liu, Haoran Xie, and Fu Lee Wang. 2018. Siamese Network-Based Supervised Topic Modeling. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 4652–4662, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Siamese Network-Based Supervised Topic Modeling (Huang et al., EMNLP 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-2/D18-1494.pdf
Data
ISEAR