2016/12/06 by Yu Wu, Wei Wu, Wu, Yu +8 · 9 citations
Computer Science · Mathematics · #Artificial intelligence #Artificial neural network #Communication #Computation and Language (cs.CL) #Computer science #Context (archaeology) #Conversation #Convolution (computer science) #FOS: Computer and information sciences #Machine learning #Matching (statistics) #Mathematics #Natural Language Processing Techniques #Natural language processing #Pooling #Recurrent neural network #Selection (genetic algorithm) #Speech and dialogue systems #Topic Modeling #Utterance #cs.CL
paper · pdf · doi:10.48550/arxiv.1612.01627
published in arXiv (Cornell University) (Cornell University) · ACL 2017
openalex publication_date 2016/12/06 · arxiv created 2017/05/15 · arxiv updated 2017/05/16 · openalex created_date 2019/07/12 · openalex updated_date 2026/08/08
We study response selection for multi-turn conversation in retrieval-based chatbots. Existing work either concatenates utterances in context or matches a response with a highly abstract context vector finally, which may lose relationships among utterances or important contextual information. We propose a sequential matching network (SMN) to address both problems. SMN first matches a response with each utterance in the context on multiple levels of granularity, and distills important matching information from each pair as a vector with convolution and pooling operations. The vectors are then accumulated in a chronological order through a recurrent neural network (RNN) which models relationships among utterances. The final matching score is calculated with the hidden states of the RNN. An empirical study on two public data sets shows that SMN can significantly outperform state-of-the-art methods for response selection in multi-turn conversation.