"Hiding in Plain Sight": Designing Synthetic Dialog Generation for Uncovering Socially Situated Norms

• URL: http://arxiv.org/abs/2410.00998v1
• Date: Tue, 1 Oct 2024 18:38:23 GMT
• Title: "Hiding in Plain Sight": Designing Synthetic Dialog Generation for Uncovering Socially Situated Norms
• Authors: Chengfei Wu, Dan Goldwasser,
• Abstract summary: This paper proposes a framework for controlled generation of dialogues, spanning a wide range of interlocutors attributes. We use this framework to generate NormHint, a collection of dialogues consistent with rich settings and analyzed for norm violation leading to conflicts. We show it captures a wide range of conversational topics and scored highly by humans for the naturalness of the conversations based on the prompted context.
• Score: 19.91823526731224
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Naturally situated conversations capture the underlying social norms appropriate for the topic of conversation, the relationship between interlocutors and their communicative intent. This paper proposes a framework for controlled generation of dialogues, spanning a wide range of interlocutors attributes (such as age group, profession and personality types), relationship types, conversation topics and conversational trajectories. We use this framework to generate NormHint, a collection of dialogues consistent with these rich settings and analyzed for norm violation leading to conflicts, and potential steps for avoiding these conflicts by adhering to social norms and preferring respectful utterances maintaining the communicative intents of the original utterance. We present the results of human validation and automated analysis of NormHint and show it captures a wide range of conversational topics and scored highly by humans for the naturalness of the conversations based on the prompted context.

Related papers

• Analysing Cross-Speaker Convergence in Face-to-Face Dialogue through the Lens of Automatically Detected Shared Linguistic Constructions [4.216085185442862]
  This study applies a methodology for automatically detecting shared lemmatised constructions to a referential communication corpus. Our analyses uncover the usage patterns of shared constructions in interaction and reveal that features such as their frequency and the amount of different constructions used for a referent are associated with the degree of object labelling convergence.
  arXiv  Detail & Related papers  (2024-05-14T12:34:25Z)
• NormDial: A Comparable Bilingual Synthetic Dialog Dataset for Modeling Social Norm Adherence and Violation [18.605252945314724]
  We present a high-quality dyadic dialogue dataset with turn-by-turn annotations of social norm adherences and violations for Chinese and American cultures. Our dataset is synthetically generated in both Chinese and English using a human-in-the-loop pipeline.
  arXiv  Detail & Related papers  (2023-10-23T04:38:34Z)
• Your spouse needs professional help: Determining the Contextual Appropriateness of Messages through Modeling Social Relationships [7.415975372963896]
  We introduce a new approach to identifying inappropriate communication by explicitly modeling the social relationship between the individuals. We show that large language models can readily incorporate relationship information to accurately identify appropriateness in a given context. We also demonstrate that contextual-appropriateness judgments are predictive of other social factors expressed in language such as condescension and politeness.
  arXiv  Detail & Related papers  (2023-07-06T04:06:05Z)
• Controllable Mixed-Initiative Dialogue Generation through Prompting [50.03458333265885]
  Mixed-initiative dialogue tasks involve repeated exchanges of information and conversational control. Agents gain control by generating responses that follow particular dialogue intents or strategies, prescribed by a policy planner. Standard approach has been fine-tuning pre-trained language models to perform generation conditioned on these intents. We instead prompt large language models as a drop-in replacement to fine-tuning on conditional generation.
  arXiv  Detail & Related papers  (2023-05-06T23:11:25Z)
• "How Robust r u?": Evaluating Task-Oriented Dialogue Systems on Spoken Conversations [87.95711406978157]
  This work presents a new benchmark on spoken task-oriented conversations. We study multi-domain dialogue state tracking and knowledge-grounded dialogue modeling. Our data set enables speech-based benchmarking of task-oriented dialogue systems.
  arXiv  Detail & Related papers  (2021-09-28T04:51:04Z)
• Who Responded to Whom: The Joint Effects of Latent Topics and Discourse in Conversation Structure [53.77234444565652]
  We identify the responding relations in the conversation discourse, which link response utterances to their initiations. We propose a model to learn latent topics and discourse in word distributions, and predict pairwise initiation-response links. Experimental results on both English and Chinese conversations show that our model significantly outperforms the previous state of the arts.
  arXiv  Detail & Related papers  (2021-04-17T17:46:00Z)
• Conversational Norms for Human-Robot Dialogues [0.32228025627337864]
  This paper describes a recently initiated research project aiming at supporting development of computerised dialogue systems that handle breaches of conversational norms. Our approach is to model dialogue and norms with co-operating distributed grammar systems (CDGSs)
  arXiv  Detail & Related papers  (2021-03-02T13:28:18Z)
• I like fish, especially dolphins: Addressing Contradictions in Dialogue Modeling [104.09033240889106]
  We introduce the DialoguE COntradiction DEtection task (DECODE) and a new conversational dataset containing both human-human and human-bot contradictory dialogues. We then compare a structured utterance-based approach of using pre-trained Transformer models for contradiction detection with the typical unstructured approach.
  arXiv  Detail & Related papers  (2020-12-24T18:47:49Z)
• Is this Dialogue Coherent? Learning from Dialogue Acts and Entities [82.44143808977209]
  We create the Switchboard Coherence (SWBD-Coh) corpus, a dataset of human-human spoken dialogues annotated with turn coherence ratings. Our statistical analysis of the corpus indicates how turn coherence perception is affected by patterns of distribution of entities. We find that models combining both DA and entity information yield the best performances both for response selection and turn coherence rating.
  arXiv  Detail & Related papers  (2020-06-17T21:02:40Z)
• Will I Sound Like Me? Improving Persona Consistency in Dialogues through Pragmatic Self-Consciousness [62.55060760615656]
  Recent models tackling consistency often train with additional Natural Language Inference (NLI) labels or attach trained extra modules to the generative agent for maintaining consistency. Inspired by social cognition and pragmatics, we endow existing dialogue agents with public self-consciousness on the fly through an imaginary listener. Our approach, based on the Rational Speech Acts framework, can enforce dialogue agents to refrain from uttering contradiction.
  arXiv  Detail & Related papers  (2020-04-13T08:16:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.