Modeling Non-Cooperative Dialogue: Theoretical and Empirical Insights
Not on the map. Why?
Abstract (arXiv)
Investigating cooperativity of interlocutors is central in studying pragmatics of dialogue. Models of conversation that only assume cooperative agents fail to explain the dynamics of strategic conversations. Thus, we investigate the ability of agents to identify non-cooperative interlocutors while completing a concurrent visual-dialogue task. Within this novel setting, we study the optimality of communication strategies for achieving this multi-task objective. We use the tools of learning theory to develop a theoretical model for identifying non-cooperative interlocutors and apply this theory to analyze different communication strategies. We also introduce a corpus of non-cooperative conversations about images in the GuessWhat?! dataset proposed by De Vries et al. (2017). We use reinforcement learning to implement multiple communication strategies in this context and find empirical results validate our theory.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 23 of its 69 references that are in the map. First posted on arXiv 15 Jul 2022.
Builds on
23 of 69 references.
References · 23
- 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
- 2017Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Datacited by 527
- 2016Visual Dialogcited by 377
- 2018Detecting and Correcting for Label Shift with Black Box Predictorscited by 364
- 2017Fake News Detection on Social Media: A Data Mining Perspectivecited by 334
- 2018Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shiftcited by 240
- 2016GuessWhat?! Visual object discovery through multi-modal dialoguecited by 112
- 2019Support and Invertibility in Domain-Invariant Representationscited by 87
- 2018Adversarial examples from computational constraintscited by 79
- 2019Domain Adaptation with Asymmetrically-Relaxed Distribution Alignmentcited by 61
- 2019The PhotoBook Dataset: Building Common Ground through Visually-Grounded Dialoguecited by 46
- 2020Reducing Adversarially Robust Learning to Non-Robust PAC Learningcited by 28
11 more
- 2017Deception Detection in Videoscited by 20
- 2019Multi-Domain Adversarial Learningcited by 19
- 2017End-to-end optimization of goal-driven and visually grounded dialogue systemscited by 17
- 2017PAC-Bayes and Domain Adaptationcited by 16
- 2020Resolving Intent Ambiguities by Retrieving Discriminative Clarifying Questionscited by 16
- 2022PAC-Bayesian Domain Adaptation Bounds for Multiclass Learnerscited by 13
- 2019Lower Bounds for Adversarially Robust PAC Learningcited by 12
- 2022The Change that Matters in Discourse Parsing: Estimating the Impact of Domain Shift on Parser Errorcited by 12
- 2018Adversarial Examples - A Complete Characterisation of the Phenomenoncited by 11
- 2019Grounded Agreement Games: Emphasizing Conversational Grounding in Visual Dialogue Settingscited by 10
- 2021PAC Bayesian Performance Guarantees for Deep (Stochastic) Networks in Medical Imagingcited by 3
Built on by
Citing papers per year: 2022: 1; 2023: 1.
2 papers.