A Co-Attentive Cross-Lingual Neural Model for Dialogue Breakdown Detection

Proceedings of the 28th International Conference on Computational Linguistics, pages 4201–4210 Barcelona, Spain (Online), December 8-13, 2020 4201 A Co-Attentive Cross-Lingual Neural Model for Dialogue Breakdown Detection Qian Lin†, Souvik Kundu‡∗, and Hwee Tou Ng† †Department of Computer Science, National University of Singapore ‡Microsoft Dynamics 365 AI qlin@u.nus.edu, sokun@microsoft.com, nght@comp.nus.edu.sg Abstract Ensuring smooth communication is essential in a chat-oriented dialogue system, so that a user can obtain meaningful responses through interactions with the system. Most prior work on dia- logue research does not focus on preventing dialogue breakdown. One of the major challenges is that a dialogue system may generate an undesired utterance leading to a dialogue breakdown, which degrades the overall interaction quality. Hence, it is crucial for a machine to detect di- alogue breakdowns in an ongoing conversation. In this paper, we propose a novel dialogue breakdown detection model that jointly incorporates a pretrained cross-lingual language model and a co-attention network. Our proposed model leverages effective word embeddings trained on one hundred different languages to generate contextualized representations. Co-attention aims to capture the interaction between the latest utterance and the conversation history, and thereby determines whether the latest utterance causes a dialogue breakdown. Experimental re- sults show that our proposed model outperforms all previous approaches on all evaluation metrics in both the Japanese and English tracks in Dialogue Breakdown Detection Challenge 4 (DBDC4 at IWSDS2019). 1 Introduction In today’s world, we often use interactive virtual conversational agents in our daily lives, such as Siri, Google Assistant, Alexa, etc. Such chat-oriented dialogue systems assist users in their daily lives through interaction in the form of conversations. Through information obtained via a conversation, a system can understand a user’s need and generate the corresponding response, such as reporting weather forecasts, booking tickets, or entertaining the user by chit-chatting. To facilitate hassle-free communication, the system needs to generate proper and rational responses without any ambiguity. Furthermore, while gen- erating a response, the system should consider not only the last turn in the conversation but also all previous utterances so that the response generated is coherent with the entire conversation history. The user experience degrades when a dialogue breakdown occurs, where the system generates an inappro- priate response which breaks the conversation flow. Dialogue breakdown detection is one of the major User utterances System utterances Breakdown? U1: What do you like to do? S1: I like to eat out and eat. NO U2: I like to eat too. Hamburgers and french fries are my favorite. S2: I love fries. I love cheese. NO U3: Where do you work? S3: I work for a company. NO U4: As a what? S4: I have a lot of friends. YES Table 1: An example dialogue where the last system-generated response causes a dialogue breakdown. Ui and Sj denote the i-th user utterance and the j-th system utterance in the dialogue, respectively. ∗ This work was done when Souvik Kundu was at the National University of Singapore. This work is licensed under a Creative Commons Attribution …

Content truncated to 500 words