TY - GEN
T1 - TripleNet
T2 - 23rd Conference on Computational Natural Language Learning, CoNLL 2019
AU - Ma, Wentao
AU - Cui, Yiming
AU - Shao, Nan
AU - He, Su
AU - Zhang, Wei Nan
AU - Liu, Ting
AU - Wang, Shijin
AU - Hu, Guoping
N1 - Publisher Copyright:
© 2019 Association for Computational Linguistics.
PY - 2019
Y1 - 2019
N2 - We consider the importance of different utterances in the context for selecting the response usually depends on the current query.1 In this paper, we propose the model TripleNet to fully model the task with the triple (context, query, response) instead of (context, response) in previous works. The heart of TripeNet is a novel attention mechanism named triple attention to model the relationships within the triple at four levels. The new mechanism updates the representation for each element based on the attention with the other two concurrently and symmetrically. We match the triple (C, Q, R) centered on the response from char to context level for prediction. Experimental results on two large-scale multi-turn response selection datasets show that the proposed model can significantly outperform the state-of-the-art methods.
AB - We consider the importance of different utterances in the context for selecting the response usually depends on the current query.1 In this paper, we propose the model TripleNet to fully model the task with the triple (context, query, response) instead of (context, response) in previous works. The heart of TripeNet is a novel attention mechanism named triple attention to model the relationships within the triple at four levels. The new mechanism updates the representation for each element based on the attention with the other two concurrently and symmetrically. We match the triple (C, Q, R) centered on the response from char to context level for prediction. Experimental results on two large-scale multi-turn response selection datasets show that the proposed model can significantly outperform the state-of-the-art methods.
UR - https://www.scopus.com/pages/publications/85084330883
U2 - 10.18653/v1/K19-1069
DO - 10.18653/v1/K19-1069
M3 - 会议稿件
AN - SCOPUS:85084330883
T3 - CoNLL 2019 - 23rd Conference on Computational Natural Language Learning, Proceedings of the Conference
SP - 737
EP - 746
BT - CoNLL 2019 - 23rd Conference on Computational Natural Language Learning, Proceedings of the Conference
PB - Association for Computational Linguistics
Y2 - 3 November 2019 through 4 November 2019
ER -