Dialogue Act-based Breakdown Detection in Negotiation Dialogues

Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics, pages 745–757 April 19 - 23, 2021. ©2021 Association for Computational Linguistics 745 Dialogue Act-based Breakdown Detection in Negotiation Dialogues Atsuki Yamaguchi♠∗, Kosui Iwasa♣ and Katsuhide Fujita♦ ♠Research and Development Group, Hitachi, Ltd. ♣Graduate School of Engineering, Tokyo University of Agriculture and Technology ♦Institute of Engineering, Tokyo University of Agriculture and Technology ♠atsuki.yamaguchi1@gmail.com ♣contact@iwasakosui.com ♦katfuji@cc.tuat.ac.jp Abstract Thanks to the success of goal-oriented nego- tiation dialogue systems, studies of negotia- tion dialogue have gained momentum in terms of both human-human negotiation support and dialogue systems. However, the field suffers from a paucity of available negotiation cor- pora, which hinders further development and makes it difficult to test new methodologies in novel negotiation settings. Here, we share a human-human negotiation dialogue dataset in a job interview scenario that features increased complexities in terms of the number of possi- ble solutions and a utility function. We test the proposed corpus using a breakdown de- tection task for human-human negotiation sup- port. We also introduce a dialogue act-based breakdown detection method, focusing on dia- logue flow that is applicable to various corpora. Our results show that our proposed method features comparable detection performance to text-based approaches in existing corpora and better results in the proposed dataset. 1 Introduction Negotiation is an essential task involved in our daily life. In negotiation, people work to maxi- mize their profits by bargaining; however, negoti- ation sometimes breaks down due to conflicts be- tween people’s competing interests. To help them to reach rational agreement, previous studies of multiagent systems have proposed the use of nego- tiating agents (Lin and Kraus, 2010; Jonker et al., 2017; Baarslag et al., 2013a). Recently, several studies have succeeded in modeling a negotiating agent in natural language that can control both text generation and reasoning in the context of goal- oriented dialogue systems, and such agents have produced better performance than human players ∗This work was conducted when the first author was a master’s student at the University of Sheffield, UK. in some cases (Lewis et al., 2017; He et al., 2018; Cheng et al., 2019). Further, support for human- human negotiation in natural language has also been tackled, involving negotiation corpora devel- oped for goal-oriented dialogue systems, such as a Nash bargaining solution estimation (Iwasa and Fujita, 2018), real-time negotiation coaching (Zhou et al., 2019), and negotiation breakdown detection (Yamaguchi and Fujita, 2020). Although they have recently attracted additional attention, there are only few negotiation corpora, as the most recent follow-up studies (Iwasa and Fujita, 2018; Cheng et al., 2019; Zhou et al., 2019; Yamaguchi and Fujita, 2020) have only utilized either the DEALORNODEAL (DN) (Lewis et al., 2017), CRAIGSLISTBARGAIN (CB) (He et al., 2018) datasets or both. Moreover, most existing corpora have simplified negotiation settings; for example, the DN dataset handles the negotiation of item division between humans with 22.5 possible solutions per dialogue and uses a standard linear additive utility function (Keeney and Raiffa, 1993; …

Content truncated to 500 words