TY - GEN
T1 - Learning matching models with weak supervision for response selection in retrieval-based chatbots
AU - Wu, Yu
AU - Wu, Wei
AU - Li, Zhoujun
AU - Zhou, Ming
N1 - Publisher Copyright:
c 2018 Association for Computational Linguistics
PY - 2018
Y1 - 2018
N2 - We propose a method that can leverage unlabeled data to learn a matching model for response selection in retrieval-based chatbots. The method employs a sequence-to-sequence architecture (Seq2Seq) model as a weak annotator to judge the matching degree of unlabeled pairs, and then performs learning with both the weak signals and the unlabeled data. Experimental results on two public data sets indicate that matching models get significant improvements when they are learned with the proposed method.
AB - We propose a method that can leverage unlabeled data to learn a matching model for response selection in retrieval-based chatbots. The method employs a sequence-to-sequence architecture (Seq2Seq) model as a weak annotator to judge the matching degree of unlabeled pairs, and then performs learning with both the weak signals and the unlabeled data. Experimental results on two public data sets indicate that matching models get significant improvements when they are learned with the proposed method.
UR - https://www.scopus.com/pages/publications/85061749080
U2 - 10.18653/v1/p18-2067
DO - 10.18653/v1/p18-2067
M3 - 会议稿件
AN - SCOPUS:85061749080
T3 - ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
SP - 420
EP - 425
BT - ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Short Papers)
PB - Association for Computational Linguistics (ACL)
T2 - 56th Annual Meeting of the Association for Computational Linguistics, ACL 2018
Y2 - 15 July 2018 through 20 July 2018
ER -