Query-to-Session Matching: Do NOT Forget History and Future during Response Selection for Multi-Turn Dialogue Systems

Abstract

Given a user query, traditional multi-turn retrieval-based dialogue systems first retrieve a set of candidate responses from the historical dialogue sessions. Then the response selection models select the most appropriate response to the given query. However, previous work only considers the matching between the query and the response but ignores the informative dialogue session in which the response is located. Nevertheless, this session, composed of the response, the response's history and the response's future, always contains valuable contextual information which can help the response selection task. More specifically, if the current query and a response's history both refer to the same question, we can conclude that this response is quite likely to answer this query. As for the response's future, it can always provide contextual hints and supplementary information that might be omitted in the response. Inspired by such motivation, we propose a query-to-session matching (QSM) framework to make full use of the session information: matching the query with the candidate session instead of the response only. Different from the previous work which ranks response directly, the response in the session with the highest query-to-session matching score will be selected as the desired response. In our proposed framework, the query, history, and future are all sequences of utterances, which makes it necessary to model the relationships among the utterances. So we propose a novel dialogue flow aware queryto-session matching (DF-QSM) model. The dialogue flows model the relationships among the utterances through a memory network. To our best knowledge, our paper is the first work to utilize both the response's history and future in the response selection task. * This work was done when Zhenxin Fu was an intern at Alibaba Group.

Product-Aware Answer Generation in E-Commerce Question-Answering

“…In recent years, sequence-to-sequence (seq2seq) [61] based neural networks have been proved effective in generating a fluent sentence. The seq2seq model is originally proposed for machine translation and later adapted to various natural language generation tasks, such as text summarization [10,18,19,22,25,41,48,69,71] and dialogue generation [6,17,20,21,40,50,64,81,85,86]. Rush et al [53] apply the seq2seq mechanism with attention model to text summarization field.…”

Logic Unveils Truth, While Disguise Obscures It: Transition Logic Augmented Response Selection for Multi-Turn Dialogue

“…Close related to conversational recommendation and interactive large language model (Ope-nAI, 2022), it has extensive application in the commercial area. With the recent huge success of PLMs (Devlin et al, 2018;Liu et al, 2019), posttraining PLMs with diverse self-supervised tasks become a popular trend and achieve impressive performance (Xu et al, 2020;Gu et al, 2020;Whang et al, 2021;Fu et al, 2023).…”