Intra-/Inter-Interaction Network with Latent Interaction Modeling for Multi-turn Response Selection

Proceedings of the 28th International Conference on Computational Linguistics, pages 4981–4992 Barcelona, Spain (Online), December 8-13, 2020 4981 Intra-/Inter-Interaction Network with Latent Interaction Modeling for Multi-turn Response Selection∗ Yang Deng, Wenxuan Zhang, Wai Lam The Chinese University of Hong Kong {ydeng,wxzhang,wlam}@se.cuhk.edu.hk Abstract Multi-turn response selection has been extensively studied and applied to many real-world ap- plications in recent years. However, current methods typically model the interactions between multi-turn utterances and candidate responses with iterative approaches, which is not practical as the turns of conversations vary. Besides, some latent features, such as user intent and con- versation topic, are under-discovered in existing works. In this work, we propose Intra-/Inter- Interaction Network (I3) with latent interaction modeling to comprehensively model multi-level interactions between the utterance context and the response. In specific, we first encode the intra- and inter-utterance interaction with the given response from both individual utterance and the overall utterance context. Then we develop a latent multi-view subspace clustering module to model the latent interaction between the utterance and response. Experimental results show that the proposed method substantially and consistently outperforms existing state-of-the-art methods on three multi-turn response selection benchmark datasets. 1 Introduction Recent years have witnessed many successful real-world applications on chatbots and AI assistants, such as the XiaoIce (Shum et al., 2018) from Microsoft and the E-commerce assistant AliMe (Li et al., 2017) from Alibaba Group, which owe to the extensive researches on dialogue systems. Existing works on building conversational models mainly study generation-based (Wen et al., 2017; Xing et al., 2017) or retrieval-based methods (Lowe et al., 2015; Wu et al., 2017; Zhang et al., 2018). In this work, we focus on the problem of multi-turn response selection for retrieval-based dialogue systems, which aims at selecting appropriate responses from a set of candidates as the reply for the given multi-turn utterances. Measuring the matching degree between the utterance context and the candidate response is the core of multi-turn response selection task. Recent works develop a variety of interaction model to enhance the utterance-response interaction from a broader (Zhou et al., 2018b; Tao et al., 2019a) or deeper per- spective (Tao et al., 2019b; Wang et al., 2019; Yuan et al., 2019). Empirical evidences show that iterative architectures achieve state-of-the-art performance on multi-turn response selection, such as interaction- over-interaction (Tao et al., 2019b), iterated attentive matching (Wang et al., 2019), and multi-hop selec- tor (Yuan et al., 2019). Despite the effectiveness of these methods, multi-turn response selection task still remains some chal- lenges when modeling the interaction between the utterance context and response: (i) In order to capture the interaction information between a candidate response and multi-turn utterances, most of existing it- erative architectures may require deeper or more complex network structure along with the growth of the turns of conversations, which fall short to efficiently learn the multi-turn utterance representations. (ii) Existing methods mainly focus on measuring the semantic relevancy between the response and the given utterance context. Nevertheless, researchers observe that some latent features in the conversations, …

Content truncated to 500 words