TY - GEN
T1 - Extended topic model forword dependency
AU - Wang, Tong
AU - Viswanath, Vish
AU - Chen, Ping
N1 - Publisher Copyright:
© 2015 Association for Computational Linguistics.
PY - 2015
Y1 - 2015
N2 - Topic Model such as Latent Dirichlet Allocation(LDA) makes assumption that topic assignment of different words are conditionally independent. In this paper, we propose a new model Extended Global Topic Random Field (EGTRF) to model non-linear dependencies between words. Specifically, we parse sentences into dependency trees and represent them as a graph, and assume the topic assignment of a word is influenced by its adjacent words and distance-2 words. Word similarity information learned from large corpus is incorporated to enhance word topic assignment. Parameters are estimated efficiently by variational inference and experimental results on two datasets show EGTRF achieves lower perplexity and higher log predictive probability.
AB - Topic Model such as Latent Dirichlet Allocation(LDA) makes assumption that topic assignment of different words are conditionally independent. In this paper, we propose a new model Extended Global Topic Random Field (EGTRF) to model non-linear dependencies between words. Specifically, we parse sentences into dependency trees and represent them as a graph, and assume the topic assignment of a word is influenced by its adjacent words and distance-2 words. Word similarity information learned from large corpus is incorporated to enhance word topic assignment. Parameters are estimated efficiently by variational inference and experimental results on two datasets show EGTRF achieves lower perplexity and higher log predictive probability.
UR - https://www.scopus.com/pages/publications/84944049639
UR - https://www.scopus.com/pages/publications/84944049639#tab=citedBy
U2 - 10.3115/v1/p15-2083
DO - 10.3115/v1/p15-2083
M3 - Conference contribution
AN - SCOPUS:84944049639
T3 - ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference
SP - 506
EP - 510
BT - ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference
PB - Association for Computational Linguistics (ACL)
T2 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, ACL-IJCNLP 2015
Y2 - 26 July 2015 through 31 July 2015
ER -