TY - GEN
T1 - Siamese network-based supervised topic modeling
AU - HUANG, Minghui
AU - RAO, Yanghui
AU - LIU, Yuwei
AU - XIE, Haoran
AU - WANG, Fu Lee
N1 - We are grateful to the anonymous reviewers for their valuable comments on this manuscript. The research has been supported by the National Natural Science Foundation of China (61502545, U1711262, U1611264), a grant from the Research Grants Council of the Hong Kong Special Administrative Region, China (UGC/FDS11/E03/16), and the Innovation and Technology Fund (Project No. GHP/022/17GD) from the Innovation and Technology Commission of the Government of the Hong Kong Special Administrative Region.
PY - 2018
Y1 - 2018
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85076607221&partnerID=8YFLogxK
U2 - 10.18653/v1/D18-1494
DO - 10.18653/v1/D18-1494
M3 - Conference paper (refereed)
T3 - Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018
SP - 4652
EP - 4662
BT - Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018
A2 - Riloff, Ellen
A2 - Chiang, David
A2 - Hockenmaier, Julia
A2 - Tsujii, Jun'ichi
PB - Association for Computational Linguistics (ACL)
T2 - 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018
Y2 - 31 October 2018 through 4 November 2018
ER -