Dialogue Act-based Breakdown Detection in Negotiation Dialogues

Yamaguchi, Atsuki; Iwasa, Kosui; Fujita, Katsuhide

doi:10.18653/v1/2021.eacl-main.63

Cited by 4 publications

(6 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DealOrNoDeal (Lewis et al, 2017) involves negotiations over three issues: books, balls, and hats. Other datasets define a more grounded scenario, such as symmetric CaSiNo (Chawla et al, 2021b) negotiations between two campsite neighbors and asymmetric JobInterview (Yamaguchi et al, 2021) negotiations between recruiters and applicants. Social Good: Social influence is critical for social good applications.…”

Section: Social Influence Across Diverse Application Areasmentioning

confidence: 99%

Social Influence Dialogue Systems: A Survey of Datasets and Models For Social Influence Tasks

Chawla,

Shi,

Zhang

et al. 2023

Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics

View full text Add to dashboard Cite

Dialogue systems capable of social influence such as persuasion, negotiation, and therapy, are essential for extending the use of technology to numerous realistic scenarios. However, existing research primarily focuses on either task-oriented or open-domain scenarios, a categorization that has been inadequate for capturing influence skills systematically. There exists no formal definition or category for dialogue systems with these skills and data-driven efforts in this direction are highly limited. In this work, we formally define and introduce the category of social influence dialogue systems that influence users' cognitive and emotional responses, leading to changes in thoughts, opinions, and behaviors through natural conversations. We present a survey of various tasks, datasets, and methods, compiling the progress across seven diverse domains. We discuss the commonalities and differences between the examined systems, identify limitations, and recommend future directions. This study serves as a comprehensive reference for social influence dialogue systems to inspire more dedicated research and discussion in this emerging area.

show abstract

Section: Social Influence Across Diverse Application Areasmentioning

confidence: 99%

Social Influence Dialogue Systems: A Survey of Datasets and Models For Social Influence Tasks

Chawla,

Shi,

Zhang

et al. 2023

Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics

View full text Add to dashboard Cite

show abstract

“…MIBT is a generic framework that can be useful for many negotiation tasks beyond these datasets as well, for instance, salary negotiations, or negotiations between art collectors distributing the items among each other. It is extensively used in NLP (Lewis et al, 2017;Chawla et al, 2021;Yamaguchi et al, 2021), beyond NLP (Mell and Gratch, 2017), and in the industry as well (e.g. iDecisionGames 5 ).…”

Section: Capturing Offersmentioning

confidence: 99%

Opponent Modeling in Negotiation Dialogues by Related Data Adaptation

Chawla¹,

Lucas²,

May³

et al. 2022

Preprint

View full text Add to dashboard Cite

Opponent modeling is the task of inferring another party's mental state within the context of social interactions. In a multi-issue negotiation, it involves inferring the relative importance that the opponent assigns to each issue under discussion, which is crucial for finding high-value deals. A practical model for this task needs to infer these priorities of the opponent on the fly based on partial dialogues as input, without needing additional annotations for training. In this work, we propose a ranker for identifying these priorities from negotiation dialogues. The model takes in a partial dialogue as input and predicts the priority order of the opponent. We further devise ways to adapt related data sources for this task to provide more explicit supervision for incorporating the opponent's preferences and offers, as a proxy to relying on granular utterancelevel annotations. We show the utility of our proposed approach through extensive experiments based on two dialogue datasets. We find that the proposed data adaptations lead to strong performance in zero-shot and fewshot scenarios. Moreover, they allow the model to perform better than baselines while accessing fewer utterances from the opponent. We release our code to support future work in this direction: https://github.com/ kushalchawla/opponent-modeling.

show abstract

“…We contribute to this line of research by exploring diverse dialogue agent personalities and studying their impact on negotiation performance. Several dialogue datasets (Lewis et al, 2017;Chawla et al, 2021;He et al, 2018;Yamaguchi et al, 2021) have fueled research into designing negotiation dialogue systems. RL has been a popular technique of choice in this space (Zhang et al, 2020;Yang et al, 2021).…”

Section: Related Workmentioning

confidence: 99%

“…One explanation for this is the relatively short conversations in DealOrN-oDeal, which makes it hard to infer the partner's personality implicitly. Hence, there is value in extending our analysis to other negotiation dialogue datasets (Yamaguchi et al, 2021;Chawla et al, 2021). In the future, we plan to integrate RL-based planning with Large Language Models (LLMs) for tackling these more complex scenarios, consisting of longer conversations and richer contexts.…”

Section: Measuring Successmentioning

confidence: 99%

“…Future work in data collection for negotiation tasks should consider such scenarios. Among the available datasets that use MIBT, more recent datasets capture richer negotiation contexts with relatively longer interactions, such as campsite negotiations in the CaSiNo dataset (Chawla et al, 2021) and salary negotiations in the JobInterview dataset (Yamaguchi et al, 2021) -We encourage future work to explore incorporating agent personalities for these datasets. Human Evaluation: Following the design of the DealOrNoDeal dataset that contains dialogues in English, our human evaluation involved workers from a restricted demographic pool -nationality as USA and English as the native language.…”

Section: Limitationsmentioning

confidence: 99%

See 1 more Smart Citation

Towards Emotion-Aware Agents for Negotiation Dialogues

Chawla¹,

Clever²,

Ramirez³

et al. 2022

Preprint

View full text Add to dashboard Cite

Negotiation is a complex social interaction that encapsulates emotional encounters in human decision-making. Virtual agents that can negotiate with humans are useful in pedagogy and conversational AI. To advance the development of such agents, we explore the prediction of two important subjective goals in a negotiation - outcome satisfaction and partner perception. Specifically, we analyze the extent to which emotion attributes extracted from the negotiation help in the prediction, above and beyond the individual difference variables. We focus on a recent dataset in chat-based negotiations, grounded in a realistic camping scenario. We draw extensive qualitative and quantitative comparisons between three types of emotion variables - emoticons, as well as lexical and contextual}variables, by leveraging affective lexicons and a state-of-the-art deep learning architecture. To further validate the findings, we analyze the prediction of these subjective negotiation goals after controlling for the objective performance of the participants. We also study the temporal effects, understanding the contribution of emotion expressed in the initial and latter parts of the conversation. Finally, we discuss our insights, which will be helpful for designing adaptive negotiation agents that interact through realistic communication interfaces.

show abstract

Dialogue Act-based Breakdown Detection in Negotiation Dialogues

Cited by 4 publications

References 33 publications

Social Influence Dialogue Systems: A Survey of Datasets and Models For Social Influence Tasks

Social Influence Dialogue Systems: A Survey of Datasets and Models For Social Influence Tasks

Opponent Modeling in Negotiation Dialogues by Related Data Adaptation

Towards Emotion-Aware Agents for Negotiation Dialogues

Contact Info

Product

Resources

About