Any Other Thoughts, Hedgehog? Linking Deliberation Chains in Collaborative Dialogues (2410.19301v1)
Abstract: Question-asking in collaborative dialogue has long been established as key to knowledge construction, both in internal and collaborative problem solving. In this work, we examine probing questions in collaborative dialogues: questions that explicitly elicit responses from the speaker's interlocutors. Specifically, we focus on modeling the causal relations that lead directly from utterances earlier in the dialogue to the emergence of the probing question. We model these relations using a novel graph-based framework of deliberation chains, and reframe the problem of constructing such chains as a coreference-style clustering problem. Our framework jointly models probing and causal utterances and the links between them, and we evaluate on two challenging collaborative task datasets: the Weights Task and DeliData. Our results demonstrate the effectiveness of our theoretically-grounded approach compared to both baselines and stronger coreference approaches, and establish a standard of performance in this novel task.
- Stergos Afantenos and Nicholas Asher. 2014. Counter-argumentation and discourse: A case study. CEUR Workshop Proceedings.
- Linear cross-document event coreference resolution with X-AMR. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 10517–10529, Torino, Italia. ELRA and ICCL.
- 2∗n2𝑛2*n2 ∗ italic_n is better than n2superscript𝑛2n^{2}italic_n start_POSTSUPERSCRIPT 2 end_POSTSUPERSCRIPT: Decomposing event coreference resolution into two tractable problems. In Findings of the Association for Computational Linguistics: ACL 2023, pages 1569–1583, Toronto, Canada. Association for Computational Linguistics.
- Aligning speech and co-speech gesture in a constraint-based grammar. Journal of Language Modelling, 5.
- Jessica Andrews-Todd and Carol M. Forsyth. 2020. Exploring social and cognitive dimensions of collaborative problem solving in an open online simulation-based task. Computers in Human Behavior, 104:105759.
- Modelling structures for situated discourse. Dialogue & Discourse, 11:89–121.
- Nicholas Asher and Alex Lascarides. 2003. Logics of conversation. Cambridge University Press.
- Combining discourse coherence with large language models for more inclusive, equitable, and robust task-oriented dialogue. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 3538–3552.
- Asking probing questions in web surveys: which factors have an impact on the quality of responses? Social Science Computer Review, 30(4):487–498.
- Longformer: The long-document transformer. arXiv e-prints, pages arXiv–2004.
- Breaking the subtopic barrier in cross-document event coreference resolution. In Text2Story @ ECIR, pages 23–29.
- Generalizing cross-document event coreference resolution across multiple corpora. Computational Linguistics, 47(3):575–614.
- Cdlm: Cross-document language modeling. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 2648–2662.
- Cross-document Coreference Resolution over Predicted Mentions. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 5100–5107.
- Measures and mechanisms of common ground: Backchannels, conversational repair, and interactive alignment in free and task-oriented social interactions. pages 2055–2060. Cognitive Science Society.
- Advancing the Science of Collaborative Problem Solving. Psychological Science in the Public Interest, 19(2):59–92. Publisher: SAGE Publications Inc.
- Barbara J Grosz and Candace L Sidner. 1986. Attention, intentions, and the structure of discourse. Computational linguistics, 12(3):175–204.
- Barbara Jean Grosz. 1977. The representation and use of focus in dialogue understanding. University of California, Berkeley.
- Focus on what matters: Applying discourse coherence theory to cross document coreference. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 1406–1417, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
- A Framework for Teachable Collaborative Problem Solving Skills. In Patrick Griffin and Esther Care, editors, Assessment and Teaching of 21st Century Skills: Methods and Approach, Educational Assessment in an Information Age, pages 37–56. Springer Netherlands, Dordrecht.
- Poly-encoders: Architectures and pre-training strategies for fast and accurate multi-sentence scoring. In International Conference on Learning Representations.
- A formal semantics for situated conversation. Semantics and Pragmatics, 11:1–52.
- What does bert learn about the structure of language? In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3651–3657.
- What makes you change your mind? an empirical investigation in online group decision-making conversations. In Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 552–563.
- Delidata: A dataset for deliberation in multi-party problem solving. Proceedings of the ACM on Human-Computer Interaction, 7(CSCW2):1–25.
- When text and speech are not enough: A multimodal dataset of collaboration in a situated task. Journal of open humanities data, 10(1).
- Common ground tracking in multimodal dialogue. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 3587–3602.
- Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.
- Fine-tuning can distort pretrained features and underperform out-of-distribution. Preprint, arXiv:2202.10054.
- Human ratings do not reflect downstream utility: A study of free-text explanations for model predictions. In Proceedings of the Fifth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, pages 164–177, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.
- Joint entity and event coreference resolution across documents. In Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, pages 489–500.
- End-to-end neural coreference resolution. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 188–197, Copenhagen, Denmark. Association for Computational Linguistics.
- Using automatically extracted minimum spans to disentangle coreference evaluation from boundary detection. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Florence, Italy. Association for Computational Linguistics.
- Nafise Sadat Moosavi and Michael Strube. 2016. Which coreference evaluation metric do you trust? a proposal for a link-based entity aware metric. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 632–642.
- Lampros Mouselimis. 2021. fuzzywuzzyR: Fuzzy String Matching. R package version 1.0.5.
- Okay, let’s do this! modeling event coreference with generated rationales and knowledge distillation. In Proceedings of the Meeting of the North American Chapter of the Association for Computational Linguistics.
- Vincent Ng and Claire Cardie. 2002. Improving machine learning approaches to coreference resolution. In Proceedings of the 40th annual meeting of the Association for Computational Linguistics, pages 104–111.
- OECD. 2017. PISA 2015 Assessment and Analytical Framework.
- Training language models to follow instructions with human feedback. Preprint, arXiv:2203.02155.
- Question decomposition improves the faithfulness of model-generated reasoning. arXiv preprint arXiv:2307.11768.
- What happens before and after: Multi-event commonsense in event coreference resolution. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 1700–1716.
- Robert C Stalnaker. 1978. Assertion. In Pragmatics, pages 315–332. Brill.
- Titin Suryati Sukmadewi. 2014. Improving students’ mathematical thinking and disposition through probing and pushing questions. Jurnal Matematika Integratif ISSN, 1412:6184.
- Towards a generalized competency model of collaborative problem solving. Computers & Education, 143:103672.
- Scaling within document coreference to long texts. Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 3921–3931.
- Dense paraphrasing for textual enrichment. In Proceedings of the 15th International Conference on Computational Semantics, pages 39–49.
- Propositional extraction from natural speech in small group collaborative tasks. In Proceedings of the International Conference on Educational Data Mining.
- Don’t annotate, but validate: A data-to-text method for capturing event data. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018).
- Reasoning in conversation: Solving subjective tasks through dialogue simulation for large language models. Preprint, arXiv:2402.17226.
- Peter C Wason. 1968. Reasoning about a rule. Quarterly journal of experimental psychology, 20(3):273–281.
- Chain-of-thought prompting elicits reasoning in large language models. Preprint, arXiv:2201.11903.
- Symbolic knowledge distillation: from general language models to commonsense models. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4602–4625, Seattle, United States. Association for Computational Linguistics.
- Measuring association between labels and free-text rationales. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 10266–10284.
- Pairwise representation learning for event coreference. In Proceedings of the 11th Joint Conference on Lexical and Computational Semantics, pages 69–78.
- Neural coreference resolution with deep biaffine attention by joint mention detection and mention clustering. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 102–107.
- Abductive commonsense reasoning exploiting mutually exclusive explanations. arXiv preprint arXiv:2305.14618.
Sponsor
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.