---
title: "PEPDS — paper by Mishra et al. (2022)"
description: "The authors build PEPDS on the PersuasionForGood (P4G) corpus. 48 references, cited by 11 papers here."
authors: ["Kshitij Mishra", "Azlaan Mustafa Samad", "Palak Totala", "Asif Ekbal"]
year: 2022
venue: "Proceedings of the 29th International Conference on Computational Linguistics"
source: "https://aclanthology.org/2022.coling-1.34/"
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/mishra-2022-pepds-polite-empathetic-persuasive-dialogue/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/mishra-2022-pepds-polite-empathetic-persuasive-dialogue/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2022](https://md.research.elamur.ai/free/en/papers/2022/page/5/) / PEPDS: A Polite and Empathetic Persuasive Dialogue System for Charity Donation

# PEPDS: A Polite and Empathetic Persuasive Dialogue System for Charity Donation

**Authors:** Kshitij Mishra, Azlaan Mustafa Samad, Palak Totala and [Asif Ekbal](https://md.research.elamur.ai/free/en/authors/asif-ekbal/) · **Year:** 2022 · **Venue:** [Proceedings of the 29th International Conference on Computational Linguistics](https://md.research.elamur.ai/free/en/venues/coling/) ([COLING 2022](https://md.research.elamur.ai/free/en/venues/coling/2022/)) · **Publisher:** [International Committee on Computational Linguistics (ICCL)](https://md.research.elamur.ai/free/en/publishers/international-committee-on-computational-linguistics-iccl/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2022.coling-1.34/) · [PDF](https://aclanthology.org/2022.coling-1.34.pdf) · [OpenAlex](https://openalex.org/W6910503979)

**Citations:** 0 citations (OpenAlex, 2026-10-14) · 11 in our library, of the 141,840 papers whose bibliographies we read

## Summary
The paper argues that charity persuasion often fails when strong arguments come with a pushy or cold tone, so a persuader bot should also show empathy and pick a suitable politeness strategy. The authors build PEPDS on the PersuasionForGood (P4G) corpus. They manually add emotion and politeness-strategy labels to create EPP4G, and empathy labels to create ETP4G. RoBERTa-large classifiers trained on these labels score candidate responses. A language model first trained with MLE is then fine-tuned with reinforcement learning. Its reward combines five signals: persuasion strategy, emotion, consistency of politeness strategy, dialogue coherence and avoiding repetition. When an empathy classifier flags an output as non-empathetic, a BART-based empathetic transfer model rewrites it. Against the ARDM and RFI baselines, PEPDS gives more persuasive and more empathetic replies in both automatic and human evaluation. Human participants agreed to donate more often with PEPDS. The work matters because it treats tone as a separate, controllable layer on top of persuasive content.

## Key points
- New resources derived from P4G: EPP4G, labelled with emotion and politeness strategy and used for reward classifiers, and ETP4G, labelled for empathy and used for the transfer model. Three paid annotators did the labelling under university review.
- Four RoBERTa-large classifiers cover persuasion strategy, emotion, politeness strategy (three classes) and binary empathy.
- The BART-large empathetic transfer model beats a BERT-BERT alternative: empathy accuracy 0.894 vs 0.862, PPL 8.71 vs 9.82.
- Automatic evaluation:
  - Persuasion-strategy rate is 59.98%, compared with 51.2% for RFI and 49.2% for ARDM.
  - Empathy rises from 67.26% for the RL-only PDS to 78.1% for PEPDS.
  - Politeness-strategy consistency is 41.117%.
- Human evaluation:
  - Donation-agreement rate is 0.67, compared with 0.61 for RFI and 0.50 for ARDM.
  - PEPDS scores 3.77 for persuasiveness and 4.78 for fluency.
  - In the reward ablation, the lowest perplexity (11.0671) appears only when all five rewards are active.

## Interesting ideas
- The reward is assembled from several independent classifiers, each judging one aspect (strategy, emotion, tone, coherence, repetition) with its own weight, instead of relying on a single opaque score; this makes the reasons behind a reward traceable.
- The system first decides what to say and only then adjusts tone, applying a rewrite step solely when a detector says the style is missing; this keeps content generation separate from stylistic polishing.
- Politeness is treated as a strategy (positive, negative, etc.) that must stay consistent with the user's attitude across turns, not as a per-sentence surface feature.
- The ablation removes one reward at a time and checks the effect on a held-out split, revealing which signals actually help and which only interact with others.
- New annotation layers (emotion, politeness, empathy) were added on top of an existing dialogue corpus rather than collecting new dialogues from scratch.

## For Mova

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

- **I1** (learn): Self-play or repair-rule learning could be scored by a weighted sum of separate, inspectable checkers, such as role consistency and frame validity, so each training signal stays explainable.
- **I2** (back): Generation from the meaning graph could produce a neutral sentence first, then apply a register or politeness pass only when a check reports a mismatch, keeping the content layer untouched.
- **I3** (frames): Speech-act analysis in prag could tag each utterance with a face-saving or imposing strategy and track shifts across a dialogue, which also helps detect irony or tension between characters.
- **I4** (learn): Evaluation could routinely drop one witness parser or teacher tier at a time to measure its real contribution, acting as a built-in negative control.
- **I5** (world): Existing fable or tale corpora could be enriched with layers for character emotion and attitude, giving the world model labelled mental states without new text collection.

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

📚 Shelves (6): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 9,086 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 8,889 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 9,296 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 9,206 works · [💭 Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/) · 798 works · [💭 Social Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/social-psychology/) · 129 works

🧭 Topics (1): [🗨️ Dialogue systems](https://md.research.elamur.ai/free/en/topics/dialogue-systems/) · 401 works

## Cite

Cite as: Kshitij Mishra, Azlaan Mustafa Samad, Palak Totala and Asif Ekbal. 2022. PEPDS: A Polite and Empathetic Persuasive Dialogue System for Charity Donation. Proceedings of the 29th International Conference on Computational Linguistics.

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

```bibtex
@inproceedings{mishra2022pepds,
  title = {{PEPDS: A Polite and Empathetic Persuasive Dialogue System for Charity Donation}},
  author = {Kshitij Mishra, Azlaan Mustafa Samad, Palak Totala and Asif Ekbal},
  booktitle = {Proceedings of the 29th International Conference on Computational Linguistics},
  year = {2022},
  doi = {10.48448/85gn-je16},
  url = {https://doi.org/10.48448/85gn-je16}
}
```

- [← previous Disentangling Indirect Answers to Yes-No Questions in Real Conversations](https://md.research.elamur.ai/free/en/papers/sanagavarapu-2022-disentangling-indirect-answers-yes-no/)
- [next → Semantic properties of English nominal pluralization: Insights from word embeddings](https://md.research.elamur.ai/free/en/papers/shafaei-bajestan-2022-semantic-properties-english-nominal-pluralization/)
- [↑ back to papers of 2022](https://md.research.elamur.ai/free/en/papers/2022/page/5/)

## References

48 references, 13 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Satanjeev Banerjee and Alon Lavie. 2005. Meteor: An automatic metric for mt evaluation with improved correlation with human judgments. In Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and/or summarization, pages 65–72. [our card](https://md.research.elamur.ai/free/en/papers/banerjee-2005-meteor-automatic-metric-mt-evaluation/)
2. Dario Bertero, Farhad Bin Siddique, Chien-Sheng Wu, Yan Wan, Ricky Ho Yin Chan, and Pascale Fung. 2016. Real-time speech emotion and sentiment recognition for interactive dialogue systems. In Proceedings of the 2016 conference on empirical methods in natural language processing, pages 1042– 1047. [find](https://scholar.google.com/scholar?q=Dario+Bertero%2C+Farhad+Bin+Siddique%2C+Chien%2DSheng+Wu%2C+Yan+Wan%2C+Ricky+Ho+Yin+Chan%2C+and+Pascale+Fung%2E+2016%2E+Real%2Dtime+speech+emotion+and+sentiment+recognition+for+interactive+dialogue+systems%2E+In+Proceedi)
3. Gerd Bohner, Markus Ruder, and Hans-Peter Erb. 2002. When expertise backfires: Contrast and assimilation effects in persuasion. British Journal of Social Psychology, 41(4):495–519. [↗](https://doi.org/10.1348/014466602321149858)
4. In this work, persuasion is modelled using a publicly available dataset. We adhered to the policies of the dataset and have not violated any copyright Penelope Brown and Stephen C Levinson. 1978. Uni-issues. Dataset which has been used to model polite versals in language usage: Politeness phenomena. In 432 Questions and politeness: Strategies in social interaction, pages 56–311. Cambridge University Press. [find](https://scholar.google.com/scholar?q=In+this+work%2C+persuasion+is+modelled+using+a+publicly+available+dataset%2E+We+adhered+to+the+policies+of+the+dataset+and+have+not+violated+any+copyright+Penelope+Brown+and+Stephen+C+Levinson%2E+1978%2E+Uni%2D)
5. Penelope Brown, Stephen C Levinson, and Stephen C Levinson. 1987. Politeness: Some universals in language usage, volume 4. Cambridge university press. American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 851–860. [find](https://scholar.google.com/scholar?q=Penelope+Brown%2C+Stephen+C+Levinson%2C+and+Stephen+C+Levinson%2E+1987%2E+Politeness%3A+Some+universals+in+language+usage%2C+volume+4%2E+Cambridge+university+press%2E+American+Chapter+of+the+Association+for+Computati)
6. Peter F Brown, Stephen A Della Pietra, Vincent J Della Pietra, Jennifer C Lai, and Robert L Mercer. 1992. An estimate of an upper bound for the entropy of english. Computational Linguistics, 18(1):31–40. [↗](https://doi.org/10.5555/146680.146685) [our card](https://md.research.elamur.ai/free/en/papers/brown-1992-estimate-upper-bound-entropy-english/)
7. Navita Goyal, Balaji Vasan Srinivasan, N Anandhavelu, and Abhilasha Sancheti. 2021. Multi-style transfer with discriminative feedback on disjoint corpus. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3500–3510. [find](https://scholar.google.com/scholar?q=Navita+Goyal%2C+Balaji+Vasan+Srinivasan%2C+N+Anandhavelu%2C+and+Abhilasha+Sancheti%2E+2021%2E+Multi%2Dstyle+transfer+with+discriminative+feedback+on+disjoint+corpus%2E+In+Proceedings+of+the+2021+Conference+of+the+N)
8. Julio Castillo and Paula Estrella. 2012. Semantic textual similarity for mt evaluation. In Proceedings of the Seventh Workshop on Statistical Machine Translation, pages 52–58. [find](https://scholar.google.com/scholar?q=Julio+Castillo+and+Paula+Estrella%2E+2012%2E+Semantic+textual+similarity+for+mt+evaluation%2E+In+Proceedings+of+the+Seventh+Workshop+on+Statistical+Machine+Translation%2C+pages+52%E2%80%9358%2E)
9. Junxian He, Xinyi Wang, Graham Neubig, and Taylor Berg-Kirkpatrick. 2020. A probabilistic formulation of unsupervised text style transfer. arXiv preprint arXiv:2002.03912. [↗](https://arxiv.org/abs/2002.03912)
10. Lu Chen, Zhi Chen, Bowen Tan, Sishan Long, Milica Gašić, and Kai Yu. 2019. Agentgraph: Toward universal dialogue management with structured deep reinforcement learning. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 27(9):1378–1391. [↗](https://doi.org/10.1109/taslp.2019.2919872)
11. Arie Dijkstra. 2008. The psychology of tailoring-ingredients in computer-tailored persuasion. Social and personality psychology compass, 2(2):765–784. [↗](https://doi.org/10.1111/j.1751-9004.2008.00081.x)
12. George Doddington. 2002. Automatic evaluation of machine translation quality using n-gram co-occurrence statistics. In Proceedings of the second international conference on Human Language Technology Research, pages 138–145. [find](https://scholar.google.com/scholar?q=George+Doddington%2E+2002%2E+Automatic+evaluation+of+machine+translation+quality+using+n%2Dgram+co%2Doccurrence+statistics%2E+In+Proceedings+of+the+second+international+conference+on+Human+Language+Technology+R)
13. Ritam Dutt, Rishabh Joshi, and Carolyn Rose. 2020. Keeping up appearances: Computational modeling of face acts in persuasion oriented discussions. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 7473–7485. [find](https://scholar.google.com/scholar?q=Ritam+Dutt%2C+Rishabh+Joshi%2C+and+Carolyn+Rose%2E+2020%2E+Keeping+up+appearances%3A+Computational+modeling+of+face+acts+in+persuasion+oriented+discussions%2E+In+Proceedings+of+the+2020+Conference+on+Empirical+Me)
14. Ritam Dutt, Sayan Sinha, Rishabh Joshi, Surya Shekhar Chakraborty, Meredith Riggs, Xinru Yan, Haogang Bao, and Carolyn Rose. 2021. Resper: Computationally modelling resisting strategies in persuasive conversations. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 78– 90. [find](https://scholar.google.com/scholar?q=Ritam+Dutt%2C+Sayan+Sinha%2C+Rishabh+Joshi%2C+Surya+Shekhar+Chakraborty%2C+Meredith+Riggs%2C+Xinru+Yan%2C+Haogang+Bao%2C+and+Carolyn+Rose%2E+2021%2E+Resper%3A+Computationally+modelling+resisting+strategies+in+persuasive+)
15. Mauajama Firdaus, Hardik Chauhan, Asif Ekbal, and Pushpak Bhattacharyya. 2020. Emosen: Generating sentiment and emotion controlled responses in a multimodal dialogue system. IEEE Transactions on Affective Computing. [↗](https://doi.org/10.1109/taffc.2020.3015491)
16. Marian Friestad and Peter Wright. 1994. The persuasion knowledge model: How people cope with persuasion attempts. Journal of consumer research, 21(1):1–31. [↗](https://doi.org/10.1086/209380)
17. Hitesh Golchha, Mauajama Firdaus, Asif Ekbal, and Pushpak Bhattacharyya. 2019. Courteously yours: Inducing courteous behavior in customer care responses using reinforced pointer generator network. In Proceedings of the 2019 Conference of the North Ari Holtzman, Jan Buys, Li Du, Maxwell Forbes, and Yejin Choi. 2019. The curious case of neural text degeneration. arXiv preprint arXiv:1904.09751. [↗](https://arxiv.org/abs/1904.09751)
18. Di Jin, Zhijing Jin, Zhiting Hu, Olga Vechtomova, and Rada Mihalcea. 2022. Deep learning for text style transfer: A survey. Computational Linguistics, 48(1):155–205. [↗](https://doi.org/10.1162/coli_a_00426)
19. Jacob Devlin Ming-Wei Chang Kenton and Lee Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of NAACL-HLT, pages 4171–4186. [our card](https://md.research.elamur.ai/free/en/papers/devlin-2019-bert-pre-training-deep-bidirectional/)
20. Ahmet Baki Kocaballi, Shlomo Berkovsky, Juan C Quiroz, Liliana Laranjo, Huong Ly Tong, Dana Rezazadegan, Agustina Briatore, and Enrico Coiera. 2019. The personalization of conversational agents in health care: systematic review. Journal of medical Internet research, 21(11):e15360. [↗](https://doi.org/10.2196/15360)
21. Kalpesh Krishna, John Wieting, and Mohit Iyyer. 2020. Reformulating unsupervised style transfer as paraphrase generation. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 737–762. [our card](https://md.research.elamur.ai/free/en/papers/krishna-2020-reformulating-unsupervised-style-transfer-as/)
22. Huiyuan Lai, Antonio Toral, and Malvina Nissim. 2021. Thank you bart! rewarding pre-trained models improves formality style transfer. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 484–494. [↗](https://doi.org/10.48550/arxiv.2105.06947)
23. 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. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7871–7880. [our card](https://md.research.elamur.ai/free/en/papers/lewis-2020-bart-denoising-sequence-sequence-pre/)
24. Jiwei Li, Will Monroe, Alan Ritter, Dan Jurafsky, Michel Galley, and Jianfeng Gao. 2016. Deep reinforcement learning for dialogue generation. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 1192– 1202. [our card](https://md.research.elamur.ai/free/en/papers/li-2016-deep-reinforcement-learning-dialogue-generation/)
25. Chin-Yew Lin and Eduard Hovy. 2003. Automatic evaluation of summaries using n-gram co-occurrence statistics. In Proceedings of the 2003 Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, pages 150–157. [our card](https://md.research.elamur.ai/free/en/papers/lin-2003-automatic-evaluation-summaries-n-gram/)
26. Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692. [↗](https://arxiv.org/abs/1907.11692)
27. Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101. [↗](https://arxiv.org/abs/1711.05101)
28. Eric Malmi, Aliaksei Severyn, and Sascha Rothe. 2020. Unsupervised text style transfer with padded masked language models. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 8671–8680. [find](https://scholar.google.com/scholar?q=Eric+Malmi%2C+Aliaksei+Severyn%2C+and+Sascha+Rothe%2E+2020%2E+Unsupervised+text+style+transfer+with+padded+masked+language+models%2E+In+Proceedings+of+the+2020+Conference+on+Empirical+Methods+in+Natural+Languag)
29. Pierre-Emmanuel Mazare, Samuel Humeau, Martin Raison, and Antoine Bordes. 2018. Training millions of personalized dialogue agents. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 2775–2779. [our card](https://md.research.elamur.ai/free/en/papers/mazare-2018-training-millions-personalized-dialogue-agents/)
30. Mary L McHugh. 2012. Interrater reliability: the kappa statistic. Biochemia medica: Biochemia medica, 22(3):276–282. [↗](https://doi.org/10.11613/bm.2012.031)
31. John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347. [↗](https://arxiv.org/abs/1707.06347)
32. Weiyan Shi, Yu Li, Saurav Sahay, and Zhou Yu. 2021. Refine and imitate: Reducing repetition and inconsistency in persuasion dialogues via reinforcement learning and human demonstration. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 3478–3492. [find](https://scholar.google.com/scholar?q=Weiyan+Shi%2C+Yu+Li%2C+Saurav+Sahay%2C+and+Zhou+Yu%2E+2021%2E+Refine+and+imitate%3A+Reducing+repetition+and+inconsistency+in+persuasion+dialogues+via+reinforcement+learning+and+human+demonstration%2E+In+Findings+of)
33. Weiyan Shi, Xuewei Wang, Yoo Jung Oh, Jingwen Zhang, Saurav Sahay, and Zhou Yu. 2020. Effects of persuasive dialogues: testing bot identities and inquiry strategies. In Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems, pages 1–13. [find](https://scholar.google.com/scholar?q=Weiyan+Shi%2C+Xuewei+Wang%2C+Yoo+Jung+Oh%2C+Jingwen+Zhang%2C+Saurav+Sahay%2C+and+Zhou+Yu%2E+2020%2E+Effects+of+persuasive+dialogues%3A+testing+bot+identities+and+inquiry+strategies%2E+In+Proceedings+of+the+2020+CHI+Con)
34. Weiyan Shi and Zhou Yu. 2018. Sentiment adaptive end-to-end dialog systems. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1509– 1519. [find](https://scholar.google.com/scholar?q=Weiyan+Shi+and+Zhou+Yu%2E+2018%2E+Sentiment+adaptive+end%2Dto%2Dend+dialog+systems%2E+In+Proceedings+of+the+56th+Annual+Meeting+of+the+Association+for+Computational+Linguistics+%28Volume+1%3A+Long+Papers%29%2C+pages+15)
35. Satinder Singh, Michael Kearns, Diane Litman, and Marilyn Walker. 1999. Reinforcement learning for spoken dialogue systems. Advances in neural information processing systems, 12:956–962. [find](https://scholar.google.com/scholar?q=Satinder+Singh%2C+Michael+Kearns%2C+Diane+Litman%2C+and+Marilyn+Walker%2E+1999%2E+Reinforcement+learning+for+spoken+dialogue+systems%2E+Advances+in+neural+information+processing+systems%2C+12%3A956%E2%80%93962%2E)
36. Mohsen Mesgar, Edwin Simpson, and Iryna Gurevych. 2021. Improving factual consistency between a response and persona facts. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 549–562. [find](https://scholar.google.com/scholar?q=Mohsen+Mesgar%2C+Edwin+Simpson%2C+and+Iryna+Gurevych%2E+2021%2E+Improving+factual+consistency+between+a+response+and+persona+facts%2E+In+Proceedings+of+the+16th+Conference+of+the+European+Chapter+of+the+Associa)
37. Haoyu Song, Yan Wang, Kaiyan Zhang, Weinan Zhang, and Ting Liu. 2021. Bob: Bert over bert for training persona-based dialogue models from limited personalized data. 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 167–177. [↗](https://doi.org/10.48550/arxiv.2106.06169) [our card](https://md.research.elamur.ai/free/en/papers/song-2021-bob-bert-over-bert-training/)
38. Kshitij Mishra, Mauajama Firdaus, and Asif Ekbal. 2022. Please be polite: Towards building a politeness adaptive dialogue system for goal-oriented conversations. Neurocomputing, 494:242–254. [↗](https://doi.org/10.1016/j.neucom.2022.04.029)
39. John R Sparks and Charles S Areni. 2002. The effects of sales presentation quality and initial perceptions on persuasion: a multiple role perspective. Journal of Business Research, 55(6):517–528. [↗](https://doi.org/10.1016/s0148-2963(00)00173-9)
40. Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th annual meeting of the Association for Computational Linguistics, pages 311–318. [↗](https://doi.org/10.3115/1073083.1073135) [our card](https://md.research.elamur.ai/free/en/papers/papineni-2002-bleu-method-automatic-evaluation-machine/)
41. John R Sparks and Charles S Areni. 2008. Style versus substance: Multiple roles of language power in persuasion. Journal of Applied Social Psychology, 38(1):37–60. [↗](https://doi.org/10.1111/j.1559-1816.2008.00295.x)
42. Richard E Petty and John T Cacioppo. 1986. The elaboration likelihood model of persuasion. In Communication and persuasion, pages 1–24. Springer. [↗](https://doi.org/10.1016/s0065-2601(08)60214-2)
43. 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)
44. 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)
45. Xuewei Wang, Weiyan Shi, Richard Kim, Yoojung Oh, Sijia Yang, Jingwen Zhang, and Zhou Yu. 2019. Persuasion for good: Towards a personalized persuasive dialogue system for social good. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5635–5649. [our card](https://md.research.elamur.ai/free/en/papers/wang-2019-persuasion-good-personalized-persuasive-dialogue/)
46. Qingyang Wu, Yichi Zhang, Yu Li, and Zhou Yu. 2021. Alternating recurrent dialog model with large-scale pre-trained language models. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 1292–1301. [find](https://scholar.google.com/scholar?q=Qingyang+Wu%2C+Yichi+Zhang%2C+Yu+Li%2C+and+Zhou+Yu%2E+2021%2E+Alternating+recurrent+dialog+model+with+large%2Dscale+pre%2Dtrained+language+models%2E+In+Proceedings+of+the+16th+Conference+of+the+European+Chapter+of+th)
47. Jingjing Xu, Xu Sun, Qi Zeng, Xiaodong Zhang, Xuancheng Ren, Houfeng Wang, and Wenjie Li. 2018. Unpaired sentiment-to-sentiment translation: A cycled reinforcement learning approach. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 979–988. [↗](https://doi.org/10.60692/kzdbq-6en85) [our card](https://md.research.elamur.ai/free/en/papers/xu-2018-unpaired-sentiment-sentiment-translation-cycled/)
48. Zichao Yang, Zhiting Hu, Chris Dyer, Eric P Xing, and Taylor Berg-Kirkpatrick. 2018. Unsupervised text style transfer using language models as discriminators. Advances in Neural Information Processing Systems, 31. [↗](https://doi.org/10.48550/arxiv.1805.11749) [our card](https://md.research.elamur.ai/free/en/papers/yang-2018-unsupervised-text-style-transfer-using/)

*Updated 24 October 2026*