---
title: "How About Kind of Generating Hedges using End-to-End Neural"
description: "The paper looks at a social side of dialogue generation: hedges. 81% accuracy. 68 references, cited by 3 papers here."
authors: ["Alafate Abulimiti", "Chloé Clavel", "Justine Cassell"]
year: 2023
venue: "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2023.acl-long.50/"
doi: "10.18653/v1/2023.acl-long.50"
arxiv: "2306.14696"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/abulimiti-2023-how-about-kind-generating-hedges/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/abulimiti-2023-how-about-kind-generating-hedges/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2023](https://md.research.elamur.ai/free/en/papers/2023/page/12/) / How About Kind of Generating Hedges using End-to-End Neural Models?

# How About Kind of Generating Hedges using End-to-End Neural Models?

**Authors:** [Alafate Abulimiti](https://md.research.elamur.ai/free/en/authors/alafate-abulimiti/), [Chloé Clavel](https://md.research.elamur.ai/free/en/authors/chloe-clavel/) and [Justine Cassell](https://md.research.elamur.ai/free/en/authors/justine-cassell/) · **Year:** 2023 · **Venue:** [Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2023](https://md.research.elamur.ai/free/en/venues/acl/2023/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2023.acl-long.50/) · [PDF](https://aclanthology.org/2023.acl-long.50.pdf) · [DOI 10.18653/v1/2023.acl-long.50](https://doi.org/10.18653/v1/2023.acl-long.50) · [arXiv 2306.14696](https://arxiv.org/abs/2306.14696) · [OpenAlex](https://openalex.org/W4385570258)

**Citations:** 4 citations (OpenAlex, 2026-10-14) · [3](https://md.research.elamur.ai/free/en/papers/abulimiti-2023-how-about-kind-generating-hedges/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
The paper looks at a social side of dialogue generation: hedges. These are softening devices such as "I think" or "could" in place of "should," which a tutor uses to reduce face threat when giving instructions. Working toward a virtual peer tutor, the authors ask two questions. Can fine-tuned end-to-end language models learn on their own when and how to hedge? And does reranking improve them? Their data is a corpus of spontaneous, face-to-face peer tutoring in linear algebra between teenagers. It is full of disfluencies, repetitions and self-repairs. Its hedge annotations were originally made per clause, and the authors merge them into turn-level labels. The generator sees a fixed window of preceding turns. A hedge classifier then reranks its candidates and keeps the one that matches the requested hedge or non-hedge label. With reranking, hedge generation works even on this noisy spoken data. The error analysis finds that most remaining failures arise when the model's drive to stay coherent clashes with the social aim of protecting face. The authors conclude that systems need an explicit social-state representation and a separate decision about when to hedge.

## Key points
- Corpus: 24 American teenagers aged 12–15 in same-gender pairs, swapping tutor and tutee roles over five weekly sessions (about 60 hours), with social periods between the tutoring blocks.
- The data has 6562 turns, of which only 936 contain hedges and 5626 do not. Hedge subtypes (propositional hedges, relational hedges/shields, attribution shields, apologizers) are collapsed into a binary label.
- Task: produce a tutor turn matching a given label, conditioned on a history window of ω previous turns. The history keeps both speakers' turns, but only tutor turns are generated.
- Pipeline: fine-tune a pretrained generator on the tutoring dialogues, then rerank a candidate pool with a hedge classifier. Earlier hedge detectors on this data reached 81% accuracy (Madaio et al., 2017) and 0.97 weighted F1 (Raphalen et al., 2022).
- Reranking errors fall into two kinds, Classification and Goal Mismatch, and Goal Mismatch accounts for the vast majority.

## Interesting ideas
- The system overgenerates and then picks with a separate attribute classifier, so all knowledge of the target style sits in the classifier and the generator stays generic; this makes the style easy to swap or audit.
- The error analysis separates failures where the classifier mislabeled a candidate from failures where the label was correct but the strategy did not fit the moment; this tells you which component to fix.
- The paper treats "how to hedge" and "when to hedge" as distinct problems, and argues that the second needs a tracked social state of the conversation rather than surface coherence alone.
- The hedge typology distinguishes approximators that blur content, shields that mark something as opinion, attribution to others, and apologizers; each attenuates force in a different way.

## For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

- **I1** (back): generate several surface realizations from the meaning graph and choose among them with an explicit checker, such as a hedge/politeness detector or a round-trip parse that must match the source graph.
- **I2** (learn): split generation and pragmatics evaluation errors by responsible component (detector versus decision policy), so self-induced repair rules target the right stage.
- **I3** (world): store dialogue-level social state (face-threatening acts such as instructions or corrections, prior strategies of each speaker) alongside entities and events, so later stages can reason about which delivery style fits.
- **I4** (frames): annotate frames with an attenuation or modality feature, instead of discarding hedge words as noise, so the answer layer knows how strongly a claim was asserted and by whose authority.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Carnegie Mellon University](https://md.research.elamur.ai/free/en/universities/carnegie-mellon-university/) — University, Pittsburgh, United States · 539 works · 179,533 citations
- [Institut national de recherche en sciences et technologies du numérique](https://md.research.elamur.ai/free/en/labs/institut-national-de-recherche-en-sciences-et-technologies-du-numerique/) — Research institute, Le Chesnay-Rocquencourt, France · 84 works · 25,414 citations
- [École Normale Supérieure - PSL](https://md.research.elamur.ai/free/en/labs/ecole-normale-superieure-psl/) — Research institute, Paris, France · 23 works · 4,357 citations
- [Université Paris Sciences et Lettres](https://md.research.elamur.ai/free/en/universities/universite-paris-sciences-et-lettres/) — University, Paris, France · 21 works · 3,290 citations
- [Institut Polytechnique de Paris](https://md.research.elamur.ai/free/en/universities/institut-polytechnique-de-paris/) — University, Palaiseau, France · 15 works · 1,612 citations
- [Laboratoire Traitement et Communication de l’Information](https://md.research.elamur.ai/free/en/labs/laboratoire-traitement-et-communication-de-l-information/) — Research institute, Palaiseau, France · 8 works · 378 citations
- [Télécom Paris](https://md.research.elamur.ai/free/en/universities/telecom-paris/) — University, Palaiseau, France · 11 works · 826 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works

## Cite

Cite as: Alafate Abulimiti, Chloé Clavel and Justine Cassell. 2023. How About Kind of Generating Hedges using End-to-End Neural Models?. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{abulimiti2023how,
  title = {{How About Kind of Generating Hedges using End-to-End Neural Models?}},
  author = {Alafate Abulimiti, Chloé Clavel and Justine Cassell},
  booktitle = {Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2023},
  doi = {10.18653/v1/2023.acl-long.50},
  eprint = {2306.14696},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.18653/v1/2023.acl-long.50}
}
```

- [← previous Hierarchical Fusion for Online Multimodal Dialog Act Classification](https://md.research.elamur.ai/free/en/papers/miah-2023-hierarchical-fusion-online-multimodal-dialog/)
- [next → Interventional Probing in High Dimensions: An NLI Case Study](https://md.research.elamur.ai/free/en/papers/rozanova-2023-interventional-probing-high-dimensions-nli/)
- [↑ back to papers of 2023](https://md.research.elamur.ai/free/en/papers/2023/page/12/)

## References

68 references, 23 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. John R Anderson, Albert T Corbett, Kenneth R Koedinger, and Ray Pelletier. 1995. Cognitive tutors: Lessons learned. The journal of the learning sciences, 4(2):167–207. [↗](https://doi.org/10.1207/s15327809jls0402_2)
2. Justine Cassell. 2022. Socially interactive agents as peers. In The Handbook on Socially Interactive Agents: 20 years of Research on Embodied Conversational Agents, Intelligent Virtual Agents, and Social Robotics Volume 2: Interactivity, Platforms, Application, pages 331–366. [↗](https://doi.org/10.1145/3563659.3563670)
3. Stanley F Chen, Douglas Beeferman, and Roni Rosenfeld. 1998. Evaluation metrics for language models. [find](https://scholar.google.com/scholar?q=Stanley+F+Chen%2C+Douglas+Beeferman%2C+and+Roni+Rosenfeld%2E+1998%2E+Evaluation+metrics+for+language+models%2E)
4. Herbert H Clark. 1979. Responding to indirect speech acts. Cognitive psychology, 11(4):430–477. [↗](https://doi.org/10.1016/0010-0285(79)90020-3)
5. Luis Fernando D’Haro, Rafael E Banchs, Chiori Hori, and Haizhou Li. 2019. Automatic evaluation of end-to-end dialog systems with adequacy-fluency metrics. Computer Speech & Language, 55:200–215. [↗](https://doi.org/10.1016/j.csl.2018.12.004)
6. M Robin DiMatteo. 1979. A social-psychological analysis of physician-patient rapport: toward a science of the art of medicine. Journal of Social Issues, 35(1):12–33. [↗](https://doi.org/10.1111/j.1540-4560.1979.tb00787.x)
7. Emily Dinan, Varvara Logacheva, Valentin Malykh, Alexander Miller, Kurt Shuster, Jack Urbanek, Douwe Kiela, Arthur Szlam, Iulian Serban, Ryan Lowe, et al. 2020. [The second conversational intelligence challenge (convai2)](https://md.research.elamur.ai/free/en/papers/dinan-2019-second-conversational-intelligence-challenge-convai2/). In The NeurIPS’18 Competition: From Machine Learning to Intelligent Conversations, pages 187–208. Springer. [↗](https://doi.org/10.1007/978-3-030-29135-8_7)
8. Angela Fan, Yacine Jernite, Ethan Perez, David Grangier, Jason Weston, and Michael Auli. 2019. [ELI5: Long form question answering](https://md.research.elamur.ai/free/en/papers/fan-2019-eli5-long-form-question-answering/). In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3558–3567, Florence, Italy. Association for Computational Linguistics. [↗](https://doi.org/10.18653/v1/p19-1346)
9. Chris Berry and Allen Brizee. 2010. Identifying independent and dependent clauses. Purdue OWL. [find](https://scholar.google.com/scholar?q=Chris+Berry+and+Allen+Brizee%2E+2010%2E+Identifying+independent+and+dependent+clauses%2E+Purdue+OWL%2E)
10. Bruce Fraser. 2010. Pragmatic competence: The case of hedging. new approaches to hedging. [↗](https://doi.org/10.1163/9789004253247_003)
11. Douglas Biber, Stig Johansson, Geoffrey Leech, Susan Conrad, Edward Finegan, and Randolph Quirk. 1999. Longman grammar of spoken and written English, volume 2. Longman London. [find](https://scholar.google.com/scholar?q=Douglas+Biber%2C+Stig+Johansson%2C+Geoffrey+Leech%2C+Susan+Conrad%2C+Edward+Finegan%2C+and+Randolph+Quirk%2E+1999%2E+Longman+grammar+of+spoken+and+written+English%2C+volume+2%2E+Longman+London%2E)
12. Rebecca A Glazier. 2016. Building rapport to improve retention and success in online classes. Journal of Political Science Education, 12(4):437–456. [↗](https://doi.org/10.1080/15512169.2016.1155994)
13. Gordon Briggs, Tom Williams, and Matthias Scheutz. 2017. Enabling robots to understand indirect speech acts in task-based interactions. Journal of Human-Robot Interaction, 6(1):64–94. [↗](https://doi.org/10.5898/jhri.6.1.briggs)
14. Pranav Goel, Yoichi Matsuyama, Michael Madaio, and Justine Cassell. 2019. i think it might help if we multiply, and not add. In Detecting indirectness in conversation. In 9th International Workshop on Spoken Dialogue System Technology, page 27–40. Springer. [find](https://scholar.google.com/scholar?q=Pranav+Goel%2C+Yoichi+Matsuyama%2C+Michael+Madaio%2C+and+Justine+Cassell%2E+2019%2E+i+think+it+might+help+if+we+multiply%2C+and+not+add%2E+In+Detecting+indirectness+in+conversation%2E+In+9th+International+Workshop+on)
15. Gretchen P Brown. 1980. [Characterizing indirect speech acts](https://md.research.elamur.ai/free/en/papers/brown-1980-characterizing-indirect-speech-acts/). American Journal of Computational Linguistics, 6(3-4):150–166.
16. Erving Goffman. 1967. Interaction Ritual, chapter On Face-Work. Pantheon, New York. [find](https://scholar.google.com/scholar?q=Erving+Goffman%2E+1967%2E+Interaction+Ritual%2C+chapter+On+Face%2DWork%2E+Pantheon%2C+New+York%2E)
17. Penelope Brown and Stephen C. Levinson. 1987. Politeness: Some universals in language usage, volume 4. Cambridge university press. [find](https://scholar.google.com/scholar?q=Penelope+Brown+and+Stephen+C%2E+Levinson%2E+1987%2E+Politeness%3A+Some+universals+in+language+usage%2C+volume+4%2E+Cambridge+university+press%2E)
18. Dwayne D Gremler and Kevin P Gwinner. 2008. Rapport-building behaviors used by retail employees. Journal of Retailing, 84(3):308–324. [↗](https://doi.org/10.1016/j.jretai.2008.07.001)
19. Andrew Caines, Helen Yannakoudakis, Helena Edmondson, Helen Allen, Pascual Pérez-Paredes, Bill Byrne, and Paula Buttery. 2020. The teacher-student chatroom corpus. In Proceedings of the 9th Workshop on NLP for Computer Assisted Language Learning, pages 10–20. [find](https://scholar.google.com/scholar?q=Andrew+Caines%2C+Helen+Yannakoudakis%2C+Helena+Edmondson%2C+Helen+Allen%2C+Pascual+P%C3%A9rez%2DParedes%2C+Bill+Byrne%2C+and+Paula+Buttery%2E+2020%2E+The+teacher%2Dstudent+chatroom+corpus%2E+In+Proceedings+of+the+9th+Workshop+o)
20. Nabil Hossain, Marjan Ghazvininejad, and Luke Zettlemoyer. 2020. Simple and effective retrieve-edit-rerank text generation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 2532–2538, Online. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Nabil+Hossain%2C+Marjan+Ghazvininejad%2C+and+Luke+Zettlemoyer%2E+2020%2E+Simple+and+effective+retrieve%2Dedit%2Drerank+text+generation%2E+In+Proceedings+of+the+58th+Annual+Meeting+of+the+Association+for+Computation)
21. Guolin Ke, Qi Meng, Thomas Finley, Taifeng Wang, Wei Chen, Weidong Ma, Qiwei Ye, and Tie-Yan Liu. 2017. Lightgbm: A highly efficient gradient boosting decision tree. Advances in neural information processing systems, 30. [find](https://scholar.google.com/scholar?q=Guolin+Ke%2C+Qi+Meng%2C+Thomas+Finley%2C+Taifeng+Wang%2C+Wei+Chen%2C+Weidong+Ma%2C+Qiwei+Ye%2C+and+Tie%2DYan+Liu%2E+2017%2E+Lightgbm%3A+A+highly+efficient+gradient+boosting+decision+tree%2E+Advances+in+neural+information+pro)
22. Klaus Krippendorff. 2004. Reliability in content analysis: Some common misconceptions and recommendations. Human communication research, 30(3):411– 433. [↗](https://doi.org/10.1093/hcr/30.3.411)
23. George Lakoff. 1975. [Hedges: A study in meaning criteria and the logic of fuzzy concepts](https://md.research.elamur.ai/free/en/papers/lakoff-1973-hedges-study-meaning-criteria/). In Contemporary research in philosophical logic and linguistic semantics, pages 221–271. Springer. [↗](https://doi.org/10.1007/978-94-010-1756-5_9)
24. Matthew J Leach. 2005. Rapport: A key to treatment success. Complementary therapies in clinical practice, 11(4):262–265. [↗](https://doi.org/10.1016/j.ctcp.2005.05.005)
25. Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Veselin Stoyanov, and Luke Zettlemoyer. 2020. [BART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension](https://md.research.elamur.ai/free/en/papers/lewis-2020-bart-denoising-sequence-sequence-pre/). In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7871–7880, Online. Association for Computational Linguistics. [↗](https://doi.org/10.18653/v1/2020.acl-main.703)
26. Yanran Li, Hui Su, Xiaoyu Shen, Wenjie Li, Ziqiang Cao, and Shuzi Niu. 2017. [DailyDialog: A manually labelled multi-turn dialogue dataset](https://md.research.elamur.ai/free/en/papers/li-2017-dailydialog-manually-labelled-multi-turn/). In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 986–995, Taipei, Taiwan. Asian Federation of Natural Language Processing. [↗](https://doi.org/10.48550/arxiv.1710.03957)
27. Zekang Li, Cheng Niu, Fandong Meng, Yang Feng, Qian Li, and Jie Zhou. 2019. Incremental transformer with deliberation decoder for document grounded conversations. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 12–21. [↗](https://doi.org/10.48550/arxiv.1907.08854)
28. Chin-Yew Lin. 2004. [ROUGE: A package for automatic evaluation of summaries](https://md.research.elamur.ai/free/en/papers/lin-2004-rouge-package-automatic-evaluation-summaries/). In Text Summarization Branches Out, pages 74–81, Barcelona, Spain. Association for Computational Linguistics.
29. Siyang Liu, Chujie Zheng, Orianna Demasi, Sahand Sabour, Yu Li, Zhou Yu, Yong Jiang, and Minlie Huang. 2021. [Towards emotional support dialog systems](https://md.research.elamur.ai/free/en/papers/liu-2021-emotional-support-dialog-systems/). In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 3469–3483, Online. Association for Computational Linguistics. [↗](https://doi.org/10.18653/v1/2021.acl-long.269)
30. Ilya Loshchilov and Frank Hutter. 2018. Decoupled weight decay regularization. In International Conference on Learning Representations. [↗](https://doi.org/10.48550/arxiv.1711.05101)
31. Aman Madaan, Amrith Setlur, Tanmay Parekh, Barnabas Poczos, Graham Neubig, Yiming Yang, Ruslan Salakhutdinov, Alan W Black, and Shrimai Prabhumoye. 2020. [Politeness transfer: A tag and generate approach](https://md.research.elamur.ai/free/en/papers/madaan-2020-politeness-transfer-tag-generate-approach/). In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 1869–1881, Online. Association for Computational Linguistics.
32. Michael Madaio, Justine Cassell, and Amy Ogan. 2017. The impact of peer tutors’ use of indirect feedback and instructions. Philadelphia, PA: International Society of the Learning Sciences. [↗](https://doi.org/10.22318/cscl2017.52)
33. Juliana Miehle, Wolfgang Minker, and Stefan Ultes. 2022. [When to say what and how: Adapting the elaborateness and indirectness of spoken dialogue systems](https://md.research.elamur.ai/free/en/papers/miehle-2022-when-say-what-how-adapting/). Dialogue & Discourse, 13(1):1–40. [↗](https://doi.org/10.5210/dad.2022.101)
34. Elizabeth Murphy and María A Rodríguez-Manzanares. 2012. Rapport in distance education. International Review of Research in Open and Distributed Learning, 13(1):167–190. [↗](https://doi.org/10.19173/irrodl.v13i1.1057)
35. Tong Niu and Mohit Bansal. 2018. Polite dialogue generation without parallel data. Transactions of the Association for Computational Linguistics, 6:373– 389. [↗](https://doi.org/10.1162/tacl_a_00027)
36. OpenAI. 2022. Chatgpt: Optimizing language models for dialogue. [find](https://scholar.google.com/scholar?q=OpenAI%2E+2022%2E+Chatgpt%3A+Optimizing+language+models+for+dialogue%2E)
37. Bo Pang, Erik Nijkamp, Wenjuan Han, Linqi Zhou, Yix-ian Liu, and Kewei Tu. 2020. Towards holistic and automatic evaluation of open-domain dialogue generation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 3619–3629. [find](https://scholar.google.com/scholar?q=Bo+Pang%2C+Erik+Nijkamp%2C+Wenjuan+Han%2C+Linqi+Zhou%2C+Yix%2Dian+Liu%2C+and+Kewei+Tu%2E+2020%2E+Towards+holistic+and+automatic+evaluation+of+open%2Ddomain+dialogue+generation%2E+In+Proceedings+of+the+58th+Annual+Meeting)
38. Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. [Bleu: a method for automatic evaluation of machine translation](https://md.research.elamur.ai/free/en/papers/papineni-2002-bleu-method-automatic-evaluation-machine/). In Proceedings of the 40th annual meeting of the Association for Computational Linguistics, pages 311–318. [↗](https://doi.org/10.3115/1073083.1073135)
39. C Raymond Perrault. 1980. [A plan-based analysis of indirect speech act](https://md.research.elamur.ai/free/en/papers/perrault-1980-plan-based-analysis-indirect-speech/). American Journal of Computational Linguistics, 6(3-4):167–182.
40. Brigitte Planken. 2005. Managing rapport in lingua franca sales negotiations: A comparison of professional and aspiring negotiators. English for Specific Purposes, 24(4):381–400. [↗](https://doi.org/10.1016/j.esp.2005.02.002)
41. Maja Popović. 2015. [chrF: character n-gram F-score for automatic MT evaluation](https://md.research.elamur.ai/free/en/papers/popovic-2015-chrf-character-n-gram-f/). In Proceedings of the Tenth Workshop on Statistical Machine Translation, pages 392–395, Lisbon, Portugal. Association for Computational Linguistics. [↗](https://doi.org/10.18653/v1/w15-3049)
42. Kaśka Porayska-Pomsta and Chris Mellish. 2004. Modelling politeness in natural language generation. In International Conference on Natural Language Generation, pages 141–150. Springer. [find](https://scholar.google.com/scholar?q=Kas%CC%81ka+Porayska%2DPomsta+and+Chris+Mellish%2E+2004%2E+Modelling+politeness+in+natural+language+generation%2E+In+International+Conference+on+Natural+Language+Generation%2C+pages+141%E2%80%93150%2E+Springer%2E)
43. Ellen F. Prince, Joel Frader, and Charles Bosk. 1982. On hedging in physician-physician discourse. Linguistics and the Professions, 8(1):83–97. [find](https://scholar.google.com/scholar?q=Ellen+F%2E+Prince%2C+Joel+Frader%2C+and+Charles+Bosk%2E+1982%2E+On+hedging+in+physician%2Dphysician+discourse%2E+Linguistics+and+the+Professions%2C+8%281%29%3A83%E2%80%9397%2E)
44. Scott Thornbury and Diana Slade. 2006. Conversation: From description to pedagogy. Cambridge University Press. [find](https://scholar.google.com/scholar?q=Scott+Thornbury+and+Diana+Slade%2E+2006%2E+Conversation%3A+From+description+to+pedagogy%2E+Cambridge+University+Press%2E)
45. Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, Ilya Sutskever, et al. 2019. Language models are unsupervised multitask learners. OpenAI blog, 1(8):9. [find](https://scholar.google.com/scholar?q=Alec+Radford%2C+Jeffrey+Wu%2C+Rewon+Child%2C+David+Luan%2C+Dario+Amodei%2C+Ilya+Sutskever%2C+et+al%2E+2019%2E+Language+models+are+unsupervised+multitask+learners%2E+OpenAI+blog%2C+1%288%29%3A9%2E)
46. Linda Tickle-Degnen and Robert Rosenthal. 1990. The nature of rapport and its nonverbal correlates. Psychological inquiry, 1(4):285–293. [↗](https://doi.org/10.1207/s15327965pli0104_1)
47. Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, and Percy Liang. 2016. [SQuAD: 100,000+ questions for machine comprehension of text](https://md.research.elamur.ai/free/en/papers/rajpurkar-2016-squad-100-000-questions-machine/). In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 2383–2392, Austin, Texas. Association for Computational Linguistics. [↗](https://doi.org/10.18653/v1/d16-1264)
48. Karen Tracy and Nikolas Coupland. 1990. Multiple goals in discourse: An overview of issues. Journal of Language and Social Psychology, 9(1-2):1–13. [↗](https://doi.org/10.1177/0261927x9091001)
49. Yann Raphalen, Chloé Clavel, and Justine Cassell. 2022. [”You might think about slightly revising the title”: Identifying hedges in peer-tutoring interactions](https://md.research.elamur.ai/free/en/papers/raphalen-2022-you-might-think-about-slightly/). In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2160–2174, Dublin, Ireland. Association for Computational Linguistics. [↗](https://doi.org/10.18653/v1/2022.acl-long.153)
50. Hannah Rashkin, Eric Michael Smith, Margaret Li, and Y-Lan Boureau. 2019. Towards empathetic open-domain conversation models: A new benchmark and dataset. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5370–5381. [↗](https://doi.org/10.18653/v1/p19-1534)
51. Stephen Roller, Emily Dinan, Naman Goyal, Da Ju, Mary Williamson, Yinhan Liu, Jing Xu, Myle Ott, Eric Michael Smith, Y-Lan Boureau, and Jason Weston. 2021. [Recipes for building an open-domain chatbot](https://md.research.elamur.ai/free/en/papers/roller-2021-recipes-building-open-domain-chatbot/). In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 300–325, Online. Association for Computational Linguistics.
52. Tim Rowland. 2007. well maybe not exactly, but it’s around fifty basically? In Vague language in mathematics classrooms. In Vague language explored, page 79–96. Springer. [find](https://scholar.google.com/scholar?q=Tim+Rowland%2E+2007%2E+well+maybe+not+exactly%2C+but+it%E2%80%99s+around+fifty+basically%3F+In+Vague+language+in+mathematics+classrooms%2E+In+Vague+language+explored%2C+page+79%E2%80%9396%2E+Springer%2E)
53. Abigail See, Stephen Roller, Douwe Kiela, and Jason Weston. 2019. [What makes a good conversation? how controllable attributes affect human judgments](https://md.research.elamur.ai/free/en/papers/see-2019-what-makes-good-conversation-how/). In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 1702–1723. [↗](https://doi.org/10.48550/arxiv.1902.08654)
54. Mayank Soni, Benjamin Cowan, and Vincent Wade. 2021. Enhancing self-disclosure in neural dialog models by candidate re-ranking. ArXiv preprint, abs/2109.05090. [↗](https://arxiv.org/abs/2109.05090)
55. Helen Spencer-Oatey. 2005. (im)politeness, face and perceptions of rapport: Unpackaging their bases and interrelationships. 1(1):95–119. [↗](https://doi.org/10.1515/jplr.2005.1.1.95)
56. Romal Thoppilan, Daniel De Freitas, Jamie Hall, Noam Shazeer, Apoorv Kulshreshtha, Heng-Tze Cheng, Alicia Jin, Taylor Bos, Leslie Baker, Yu Du, et al. 2022. [Lamda: Language models for dialog applications](https://md.research.elamur.ai/free/en/papers/thoppilan-2022-lamda-language-models-dialog-applications/). ArXiv preprint, abs/2201.08239. [↗](https://arxiv.org/abs/2201.08239)
57. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. [Attention is all you need](https://md.research.elamur.ai/free/en/papers/vaswani-2017-attention-all-need/). In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, USA, pages 5998–6008.
58. Veronika Vincze. 2014. Uncertainty detection in natural language texts. PhD, University of Szeged, 141. [↗](https://doi.org/10.14232/phd.2291)
59. Adina Williams, Nikita Nangia, and Samuel Bowman. 2018. [A broad-coverage challenge corpus for sentence understanding through inference](https://md.research.elamur.ai/free/en/papers/williams-2018-broad-coverage-challenge-corpus-sentence/). In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 1112–1122, New Orleans, Louisiana. Association for Computational Linguistics. [↗](https://doi.org/10.18653/v1/n18-1101)
60. Timothy Williamson. 2002. Vagueness. Routledge. [find](https://scholar.google.com/scholar?q=Timothy+Williamson%2E+2002%2E+Vagueness%2E+Routledge%2E)
61. Weizhe Yuan, Graham Neubig, and Pengfei Liu. 2021. [Bartscore: Evaluating generated text as text generation](https://md.research.elamur.ai/free/en/papers/yuan-2021-bartscore-evaluating-generated-text-text/). Advances in Neural Information Processing Systems, 34.
62. Saizheng Zhang, Emily Dinan, Jack Urbanek, Arthur Szlam, Douwe Kiela, and Jason Weston. 2018. [Personalizing dialogue agents: I have a dog, do you have pets too?](https://md.research.elamur.ai/free/en/papers/zhang-2018-personalizing-dialogue-agents-i-have/) In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2204–2213, Melbourne, Australia. Association for Computational Linguistics. [↗](https://doi.org/10.18653/v1/p18-1205)
63. Tianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q. Weinberger, and Yoav Artzi. 2020a. Bertscore: Evaluating text generation with BERT. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020. OpenReview.net. [↗](https://doi.org/10.48550/arxiv.1904.09675)
64. Yizhe Zhang, Siqi Sun, Michel Galley, Yen-Chun Chen, Chris Brockett, Xiang Gao, Jianfeng Gao, Jingjing Liu, and Bill Dolan. 2020b. [DIALOGPT : Large-scale generative pre-training for conversational response generation](https://md.research.elamur.ai/free/en/papers/zhang-2019-dialogpt-large-scale-generative-pre/). In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pages 270–278, Online. Association for Computational Linguistics. [↗](https://doi.org/10.48550/arxiv.1911.00536)
65. Ran Zhao, Alexandros Papangelis, and Justine Cassell. 2014. Towards a dyadic computational model of rapport management for human-virtual agent interaction. In International conference on intelligent virtual agents, pages 514–527. Springer. [↗](https://doi.org/10.1007/978-3-319-09767-1_62)
66. Ran Zhao, Tanmay Sinha, Alan Black, and Justine Cassell. 2016a. Automatic recognition of conversational strategies in the service of a socially-aware dialog system. In Proceedings of the 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 381–392, Los Angeles. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Ran+Zhao%2C+Tanmay+Sinha%2C+Alan+Black%2C+and+Justine+Cassell%2E+2016a%2E+Automatic+recognition+of+conversational+strategies+in+the+service+of+a+socially%2Daware+dialog+system%2E+In+Proceedings+of+the+17th+Annual+M)
67. Ran Zhao, Tanmay Sinha, Alan W. Black, and Justine Cassell. 2016b. Socially-aware virtual agents: Automatically assessing dyadic rapport from temporal patterns of behavior. In International conference on intelligent virtual agents, page 218–233. Springer. [find](https://scholar.google.com/scholar?q=Ran+Zhao%2C+Tanmay+Sinha%2C+Alan+W%2E+Black%2C+and+Justine+Cassell%2E+2016b%2E+Socially%2Daware+virtual+agents%3A+Automatically+assessing+dyadic+rapport+from+temporal+patterns+of+behavior%2E+In+International+conference)
68. Caleb Ziems, Minzhi Li, Anthony Zhang, and Diyi Yang. 2022. Inducing positive perspectives with text reframing. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3682–3700, Dublin, Ireland. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Caleb+Ziems%2C+Minzhi+Li%2C+Anthony+Zhang%2C+and+Diyi+Yang%2E+2022%2E+Inducing+positive+perspectives+with+text+reframing%2E+In+Proceedings+of+the+60th+Annual+Meeting+of+the+Association+for+Computational+Linguisti)

*Updated 1 November 2026*