---
title: "Decoupling Strategy and Generation in Negotiation — He 2018"
description: "End-to-end neural negotiation agents learn strategy and wording together."
authors: ["He He", "Derek Chen", "Anusha Balakrishnan", "Percy Liang"]
year: 2018
venue: "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing"
source: "https://aclanthology.org/D18-1256/"
doi: "10.18653/v1/d18-1256"
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/he-2018-decoupling-strategy-generation-negotiation-dialogues/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/he-2018-decoupling-strategy-generation-negotiation-dialogues/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2018](https://md.research.elamur.ai/free/en/papers/2018/page/2/) / Decoupling Strategy and Generation in Negotiation Dialogues

# Decoupling Strategy and Generation in Negotiation Dialogues

**Authors:** [He He](https://md.research.elamur.ai/free/en/authors/he-he/), [Derek Chen](https://md.research.elamur.ai/free/en/authors/derek-chen/), Anusha Balakrishnan, [Percy Liang](https://md.research.elamur.ai/free/en/authors/percy-liang/) · **Year:** 2018 · **Venue:** Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/D18-1256/) · [PDF](https://aclanthology.org/D18-1256.pdf) · [DOI 10.18653/v1/d18-1256](https://doi.org/10.18653/v1/d18-1256) · [OpenAlex](https://openalex.org/W2963170138)

**Citations:** 125 citations (openalex-snapshot · 2026-10-14) · [108](#cited-by) in our library, of the 140884 papers whose bibliographies we read

## Summary
End-to-end neural negotiation agents learn strategy and wording together. This makes their behaviour hard to steer or inspect, and reinforcement learning tends to collapse their language into repetitive or ungrammatical output. The authors separate the two concerns with a three-part pipeline:

- **Parser:** a deterministic parser uses keywords and entities to map each incoming message to a coarse dialogue act, such as propose(price=150).
- **Manager:** a sequence-to-sequence model over these acts chooses the next move. It can be trained with supervised learning, reinforcement learning, or hand-written rules.
- **Generator:** a retrieval-based generator writes the reply from the chosen act and the full conversation history.

The authors also release CraigslistBargain, a buyer–seller dataset built on real Craigslist listings and collected through Amazon Mechanical Turk. Human A/B evaluations were run on CraigslistBargain and DealOrNoDeal. Agents optimized at the act level achieved better task outcomes than earlier approaches and stayed human-like. Word-level RL agents, in contrast, degenerated. The work shows that controllable strategy and open-ended language generation can coexist in one system.

## Key points
- **Dataset:** CraigslistBargain has 6682 dialogues built from 1402 postings in 6 categories (housing, furniture, cars, bikes, phones, electronics). Each posting yields three scenarios, with the buyer's target set at 0.5x, 0.7x or 0.9x of the listing price.
- **Richer language than DealOrNoDeal:** CraigslistBargain averages 9.2 turns and 15.5 tokens per turn with a vocabulary of 13928. DealOrNoDeal averages 6.6 turns and 7.6 tokens per turn with a vocabulary of 2719. Observed tactics include embellishment, side offers, cheap talk and appeals to sympathy.
- **Word-level RL degenerates:** on CraigslistBargain, the most frequent sentences of the RL utility, fairness and length (word) models made up 81.6%, 100% and 100% of their utterances.
- **Act-level RL learns distinct strategies:** RL length (act) asked many questions, which made up 42.4% of its buyer turns versus 30.2% for the other models. RL utility (act) refused to concede, which lowered its agreement rate. SL(act)+rule combined high utility with human-likeness on both tasks.
- **Availability:** the data is at stanfordnlp.github.io/cocoa, and the code and experiments are on CodaLab.

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

Fields: [Natural language processing](https://md.research.elamur.ai/free/en/shelves/nlp/)

## Cited by

Cited by

108 papers of our library cite it (of the 140884 whose bibliographies we read); 7 of them have a page here, 101 not yet.

- [Experience Grounds Language](https://md.research.elamur.ai/free/en/papers/bisk-2020-experience-grounds-language/)
- [Conversational Assistants to Support Patients with Heart Failure: Comparing a Neurosymbolic Architecture with GPT](https://md.research.elamur.ai/free/en/papers/tayal-2026-conversational-assistants-support-patients-heart/)
- [Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Good](https://md.research.elamur.ai/free/en/papers/wang-2019-persuasion-good-personalized-persuasive-dialogue/)
- [Dialogue Act-based Breakdown Detection in Negotiation Dialogues](https://md.research.elamur.ai/free/en/papers/yamaguchi-2021-dialogue-act-based-breakdown-detection/)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://md.research.elamur.ai/free/en/papers/yao-2024-tau-bench-benchmark-tool/)
- [DiPS: Dialogue Policy Selection for High-Stakes Persuasion Agents](https://md.research.elamur.ai/free/en/papers/zhang-2026-dips-dialogue-policy-selection-high/)
- [SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents](https://md.research.elamur.ai/free/en/papers/zhou-2023-sotopia-interactive-evaluation-social-intelligence/)

## Cite

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

```bibtex
@inproceedings{he2018decoupling,
  title = {{Decoupling Strategy and Generation in Negotiation Dialogues}},
  author = {He, He and Chen, Derek and Balakrishnan, Anusha and Liang, Percy},
  booktitle = {Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing},
  year = {2018},
  doi = {10.18653/v1/d18-1256},
  url = {https://doi.org/10.18653/v1/d18-1256}
}
```

- [← previous DeClarE: Debunking Fake News and False Claims using Evidence-Aware Deep Learning](https://md.research.elamur.ai/free/en/papers/popat-2018-declare-debunking-fake-news-false/)
- [next → Deep Communicating Agents for Abstractive Summarization](https://md.research.elamur.ai/free/en/papers/celikyilmaz-2018-deep-communicating-agents-abstractive-summarization/)
- [↑ back to papers of 2018](https://md.research.elamur.ai/free/en/papers/2018/page/2/)

## References

32 references, 6 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. S. Afantenos, N. Asher, F. Benamara, A. Cadilhac, C. Dégremont, P. Denis, M. Guhe, S. Keizer, A. Lascarides, O. Lemon, et al. 2012. Modelling strategic conversation: Model, annotation design and corpus. In Proceedings of SemDial 2012: Workshop on the Semantics and Pragmatics of Dialogue, pages 167–… [find](https://scholar.google.com/scholar?q=S%2E+Afantenos%2C+N%2E+Asher%2C+F%2E+Benamara%2C+A%2E+Cadilhac%2C+C%2E+De%CC%81gremont%2C+P%2E+Denis%2C+M%2E+Guhe%2C+S%2E+Keizer%2C+A%2E+Lascarides%2C+O%2E+Lemon%2C+et+al%2E+2012%2E+Modelling+strategic+conversation%3A+Model%2C+annotation+design+and+corp)
2. N. Asher, J. Hunter, M. Morey, F. Benamara, and S. Afantenos. 2016. Discourse structure and dialogue acts in multiparty dialogue: the STAC corpus. In Language Resources and Evaluation Conference (LREC). [find](https://scholar.google.com/scholar?q=N%2E+Asher%2C+J%2E+Hunter%2C+M%2E+Morey%2C+F%2E+Benamara%2C+and+S%2E+Afantenos%2E+2016%2E+Discourse+structure+and+dialogue+acts+in+multiparty+dialogue%3A+the+STAC+corpus%2E+In+Language+Resources+and+Evaluation+Conference+%28LREC) [our card](https://md.research.elamur.ai/free/en/papers/asher-2016-discourse-structure-dialogue-acts-multiparty/)
3. A. Bordes and J. Weston. 2017. Learning end-to-end goal-oriented dialog. In International Conference on Learning Representations (ICLR). [find](https://scholar.google.com/scholar?q=A%2E+Bordes+and+J%2E+Weston%2E+2017%2E+Learning+end%2Dto%2Dend+goal%2Doriented+dialog%2E+In+International+Conference+on+Learning+Representations+%28ICLR%29%2E)
4. S. J. Brams. 2003. Negotiation Games: Applying Game Theory to Bargaining and Arbitration. Psychology Press. [find](https://scholar.google.com/scholar?q=S%2E+J%2E+Brams%2E+2003%2E+Negotiation+Games%3A+Applying+Game+Theory+to+Bargaining+and+Arbitration%2E+Psychology+Press%2E)
5. K. Cao and S. Clark. 2017. Latent variable dialogue models and their diversity. In European Association for Computational Linguistics (EACL). [find](https://scholar.google.com/scholar?q=K%2E+Cao+and+S%2E+Clark%2E+2017%2E+Latent+variable+dialogue+models+and+their+diversity%2E+In+European+Association+for+Computational+Linguistics+%28EACL%29%2E)
6. K. Cao, A. Lazaridou, M. Lanctot, J. Z. Leibo, K. Tuyls, and S. Clark. 2018. Emergent communication through negotiation. In International Conference on Learning Representations (ICLR). [find](https://scholar.google.com/scholar?q=K%2E+Cao%2C+A%2E+Lazaridou%2C+M%2E+Lanctot%2C+J%2E+Z%2E+Leibo%2C+K%2E+Tuyls%2C+and+S%2E+Clark%2E+2018%2E+Emergent+communication+through+negotiation%2E+In+International+Conference+on+Learning+Representations+%28ICLR%29%2E)
7. H. Cuayáhuitl, S. Keizer, and O. Lemon. 2015. Strategic dialogue management via deep reinforcement learning. In Advances in Neural Information Processing Systems (NIPS). [find](https://scholar.google.com/scholar?q=H%2E+Cuaya%CC%81huitl%2C+S%2E+Keizer%2C+and+O%2E+Lemon%2E+2015%2E+Strategic+dialogue+management+via+deep+reinforcement+learning%2E+In+Advances+in+Neural+Information+Processing+Systems+%28NIPS%29%2E)
8. D. DeVault, J. Mell, and J. Gratch. 2015. Toward natural turn-taking in a virtual human negotiation agent. In Association for the Advancement of Artificial Intelligence (AAAI). [find](https://scholar.google.com/scholar?q=D%2E+DeVault%2C+J%2E+Mell%2C+and+J%2E+Gratch%2E+2015%2E+Toward+natural+turn%2Dtaking+in+a+virtual+human+negotiation+agent%2E+In+Association+for+the+Advancement+of+Artificial+Intelligence+%28AAAI%29%2E)
9. B. Dhingra, L. Li, X. Li, J. Gao, Y. Chen, F. Ahmed, and L. Deng. 2017. End-to-end reinforcement learning of dialogue agents for information access. In Association for Computational Linguistics (ACL). [find](https://scholar.google.com/scholar?q=B%2E+Dhingra%2C+L%2E+Li%2C+X%2E+Li%2C+J%2E+Gao%2C+Y%2E+Chen%2C+F%2E+Ahmed%2C+and+L%2E+Deng%2E+2017%2E+End%2Dto%2Dend+reinforcement+learning+of+dialogue+agents+for+information+access%2E+In+Association+for+Computational+Linguistics+%28ACL%29%2E) [our card](https://md.research.elamur.ai/free/en/papers/dhingra-2017-end-end-reinforcement-learning-dialogue/)
10. J. Duchi, E. Hazan, and Y. Singer. 2010. Adaptive subgradient methods for online learning and stochastic optimization. In Conference on Learning Theory (COLT). [find](https://scholar.google.com/scholar?q=J%2E+Duchi%2C+E%2E+Hazan%2C+and+Y%2E+Singer%2E+2010%2E+Adaptive+subgradient+methods+for+online+learning+and+stochastic+optimization%2E+In+Conference+on+Learning+Theory+%28COLT%29%2E)
11. I. Efstathiou and O. Lemon. 2014. Learning non-cooperative dialogue behaviours. In Special Interest Group on Discourse and Dialogue (SIGDIAL). [find](https://scholar.google.com/scholar?q=I%2E+Efstathiou+and+O%2E+Lemon%2E+2014%2E+Learning+non%2Dcooperative+dialogue+behaviours%2E+In+Special+Interest+Group+on+Discourse+and+Dialogue+%28SIGDIAL%29%2E)
12. N. Elnaz, G. Kallirroi, and T. David. 2012. A cultural decision-making model for negotiation based on inverse reinforcement learning. In The Annual Meeting of the Cognitive Science Society. [find](https://scholar.google.com/scholar?q=N%2E+Elnaz%2C+G%2E+Kallirroi%2C+and+T%2E+David%2E+2012%2E+A+cultural+decision%2Dmaking+model+for+negotiation+based+on+inverse+reinforcement+learning%2E+In+The+Annual+Meeting+of+the+Cognitive+Science+Society%2E)
13. M. S. English and P. A. Heeman. 2005. Learning mixed initiative dialog strategies by using reinforcement learning on both conversants. In Empirical Methods in Natural Language Processing (EMNLP). [find](https://scholar.google.com/scholar?q=M%2E+S%2E+English+and+P%2E+A%2E+Heeman%2E+2005%2E+Learning+mixed+initiative+dialog+strategies+by+using+reinforcement+learning+on+both+conversants%2E+In+Empirical+Methods+in+Natural+Language+Processing+%28EMNLP%29%2E)
14. H. He, A. Balakrishnan, M. Eric, and P. Liang. 2017. Learning symmetric collaborative dialogue agents with dynamic knowledge graph embeddings. In Association for Computational Linguistics (ACL), pages 1766–1776. [find](https://scholar.google.com/scholar?q=H%2E+He%2C+A%2E+Balakrishnan%2C+M%2E+Eric%2C+and+P%2E+Liang%2E+2017%2E+Learning+symmetric+collaborative+dialogue+agents+with+dynamic+knowledge+graph+embeddings%2E+In+Association+for+Computational+Linguistics+%28ACL%29%2C+pages)
15. T. Hiraoka, K. Georgila, E. Nouri, and D. Traum. 2015. Reinforcement learning in multi-party trading dialog. In Special Interest Group on Discourse and Dialogue (SIGDIAL). [find](https://scholar.google.com/scholar?q=T%2E+Hiraoka%2C+K%2E+Georgila%2C+E%2E+Nouri%2C+and+D%2E+Traum%2E+2015%2E+Reinforcement+learning+in+multi%2Dparty+trading+dialog%2E+In+Special+Interest+Group+on+Discourse+and+Dialogue+%28SIGDIAL%29%2E)
16. S. Keizer, M. Guhe, H. Cuayahuitl, I. Efstathiou, K. Engelbrecht, M. Dobre, A. Lascarides, and O. Lemon. 2017. Evaluating persuasion strategies and deep reinforcement learning methods for negotiation dialogue agents. In European Association for Computational Linguistics (EACL). [find](https://scholar.google.com/scholar?q=S%2E+Keizer%2C+M%2E+Guhe%2C+H%2E+Cuayahuitl%2C+I%2E+Efstathiou%2C+K%2E+Engelbrecht%2C+M%2E+Dobre%2C+A%2E+Lascarides%2C+and+O%2E+Lemon%2E+2017%2E+Evaluating+persuasion+strategies+and+deep+reinforcement+learning+methods+for+negotiation+)
17. M. Lewis, D. Yarats, Y. N. Dauphin, D. Parikh, and D. Batra. 2017. Deal or no deal? end-to-end learning for negotiation dialogues. In Empirical Methods in Natural Language Processing (EMNLP). [find](https://scholar.google.com/scholar?q=M%2E+Lewis%2C+D%2E+Yarats%2C+Y%2E+N%2E+Dauphin%2C+D%2E+Parikh%2C+and+D%2E+Batra%2E+2017%2E+Deal+or+no+deal%3F+end%2Dto%2Dend+learning+for+negotiation+dialogues%2E+In+Empirical+Methods+in+Natural+Language+Processing+%28EMNLP%29%2E)
18. J. Li, W. Monroe, A. Ritter, D. Jurafsky, M. Galley, and J. Gao. 2016. Deep reinforcement learning for dialogue generation. In Empirical Methods in Natural Language Processing (EMNLP). [find](https://scholar.google.com/scholar?q=J%2E+Li%2C+W%2E+Monroe%2C+A%2E+Ritter%2C+D%2E+Jurafsky%2C+M%2E+Galley%2C+and+J%2E+Gao%2E+2016%2E+Deep+reinforcement+learning+for+dialogue+generation%2E+In+Empirical+Methods+in+Natural+Language+Processing+%28EMNLP%29%2E) [our card](https://md.research.elamur.ai/free/en/papers/li-2016-deep-reinforcement-learning-dialogue-generation/)
19. J. Li, W. Monroe, T. Shi, A. Ritter, and D. Jurafsky. 2017. Adversarial learning for neural dialogue generation. arXiv preprint arXiv:1701.06547. [find](https://scholar.google.com/scholar?q=J%2E+Li%2C+W%2E+Monroe%2C+T%2E+Shi%2C+A%2E+Ritter%2C+and+D%2E+Jurafsky%2E+2017%2E+Adversarial+learning+for+neural+dialogue+generation%2E+arXiv+preprint+arXiv%3A1701%2E06547%2E) [our card](https://md.research.elamur.ai/free/en/papers/li-2017-adversarial-learning-neural-dialogue-generation/)
20. R. T. Lowe, N. Pow, I. Serban, L. Charlin, C. Liu, and J. Pineau. 2017. Training end-to-end dialogue systems with the ubuntu dialogue corpus. Dialogue and Discourse, 8. [find](https://scholar.google.com/scholar?q=R%2E+T%2E+Lowe%2C+N%2E+Pow%2C+I%2E+Serban%2C+L%2E+Charlin%2C+C%2E+Liu%2C+and+J%2E+Pineau%2E+2017%2E+Training+end%2Dto%2Dend+dialogue+systems+with+the+ubuntu+dialogue+corpus%2E+Dialogue+and+Discourse%2C+8%2E)
21. J. Pennington, R. Socher, and C. D. Manning. 2014. GloVe: Global vectors for word representation. In Empirical Methods in Natural Language Processing (EMNLP), pages 1532–1543. [find](https://scholar.google.com/scholar?q=J%2E+Pennington%2C+R%2E+Socher%2C+and+C%2E+D%2E+Manning%2E+2014%2E+GloVe%3A+Global+vectors+for+word+representation%2E+In+Empirical+Methods+in+Natural+Language+Processing+%28EMNLP%29%2C+pages+1532%E2%80%931543%2E)
22. C. Potts. 2012. Goal-driven answers in the Cards dialogue corpus. In Proceedings of the 30th West Coast Conference on Formal Linguistics, pages 1–20. [find](https://scholar.google.com/scholar?q=C%2E+Potts%2E+2012%2E+Goal%2Ddriven+answers+in+the+Cards+dialogue+corpus%2E+In+Proceedings+of+the+30th+West+Coast+Conference+on+Formal+Linguistics%2C+pages+1%E2%80%9320%2E)
23. A. Sordoni, M. Galley, M. Auli, C. Brockett, Y. Ji, M. Mitchell, J. Nie, J. Gao, and B. Dolan. 2015. A neural network approach to context-sensitive generation of conversational responses. In North American Association for Computational Linguistics (NAACL). [find](https://scholar.google.com/scholar?q=A%2E+Sordoni%2C+M%2E+Galley%2C+M%2E+Auli%2C+C%2E+Brockett%2C+Y%2E+Ji%2C+M%2E+Mitchell%2C+J%2E+Nie%2C+J%2E+Gao%2C+and+B%2E+Dolan%2E+2015%2E+A+neural+network+approach+to+context%2Dsensitive+generation+of+conversational+responses%2E+In+North+Ame) [our card](https://md.research.elamur.ai/free/en/papers/sordoni-2015-neural-network-approach-context-sensitive/)
24. H. Takuya, N. Graham, S. Sakriani, T. Tomoki, and N. Satoshi. 2014. Reinforcement learning of cooperative persuasive dialogue policies using framing. In International Conference on Computational Linguistics (COLING). [find](https://scholar.google.com/scholar?q=H%2E+Takuya%2C+N%2E+Graham%2C+S%2E+Sakriani%2C+T%2E+Tomoki%2C+and+N%2E+Satoshi%2E+2014%2E+Reinforcement+learning+of+cooperative+persuasive+dialogue+policies+using+framing%2E+In+International+Conference+on+Computational+Lingu)
25. D. Traum, S. C. Marsella, J. Gratch, J. Lee, and A. Hartholt. 2008. Multi-party, multi-issue, multi-strategy negotiation for multi-modal virtual agents. In International Workshop on Intelligent Virtual Agents, pages 117–130. [find](https://scholar.google.com/scholar?q=D%2E+Traum%2C+S%2E+C%2E+Marsella%2C+J%2E+Gratch%2C+J%2E+Lee%2C+and+A%2E+Hartholt%2E+2008%2E+Multi%2Dparty%2C+multi%2Dissue%2C+multi%2Dstrategy+negotiation+for+multi%2Dmodal+virtual+agents%2E+In+International+Workshop+on+Intelligent+Virtua)
26. T. Wen, M. Gasic, N. Mrksic, L. M. Rojas-Barahona, P. Su, S. Ultes, D. Vandyke, and S. Young. 2017a. A network-based end-to-end trainable task-oriented dialogue system. In European Association for Computational Linguistics (EACL), pages 438–449. [find](https://scholar.google.com/scholar?q=T%2E+Wen%2C+M%2E+Gasic%2C+N%2E+Mrksic%2C+L%2E+M%2E+Rojas%2DBarahona%2C+P%2E+Su%2C+S%2E+Ultes%2C+D%2E+Vandyke%2C+and+S%2E+Young%2E+2017a%2E+A+network%2Dbased+end%2Dto%2Dend+trainable+task%2Doriented+dialogue+system%2E+In+European+Association+for+Com)
27. T. Wen, Y. Miao, P. Blunsom, and S. Young. 2017b. Latent intention dialogue models. In International Conference on Machine Learning (ICML). [find](https://scholar.google.com/scholar?q=T%2E+Wen%2C+Y%2E+Miao%2C+P%2E+Blunsom%2C+and+S%2E+Young%2E+2017b%2E+Latent+intention+dialogue+models%2E+In+International+Conference+on+Machine+Learning+%28ICML%29%2E)
28. J. D. Williams, K. Asadi, and G. Zweig. 2017. Hybrid code networks: Practical and efficient end-to-end dialog control with supervised and reinforcement learning. In Association for Computational Linguistics (ACL). [find](https://scholar.google.com/scholar?q=J%2E+D%2E+Williams%2C+K%2E+Asadi%2C+and+G%2E+Zweig%2E+2017%2E+Hybrid+code+networks%3A+Practical+and+efficient+end%2Dto%2Dend+dialog+control+with+supervised+and+reinforcement+learning%2E+In+Association+for+Computational+Lingu)
29. J. D. Williams, A. Raux, and M. Henderson. 2016. The dialog state tracking challenge series: A review. Dialogue and Discourse, 7. [find](https://scholar.google.com/scholar?q=J%2E+D%2E+Williams%2C+A%2E+Raux%2C+and+M%2E+Henderson%2E+2016%2E+The+dialog+state+tracking+challenge+series%3A+A+review%2E+Dialogue+and+Discourse%2C+7%2E)
30. R. J. Williams. 1992. Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine learning, 8(3):229–256. [find](https://scholar.google.com/scholar?q=R%2E+J%2E+Williams%2E+1992%2E+Simple+statistical+gradient%2Dfollowing+algorithms+for+connectionist+reinforcement+learning%2E+Machine+learning%2C+8%283%29%3A229%E2%80%93256%2E)
31. S. Young, M. Gašić, B. Thomson, and J. D. Williams. 2013. POMDP-based statistical spoken dialog systems: A review. In Proceedings of the IEEE, 5, pages 1160–1179. [find](https://scholar.google.com/scholar?q=S%2E+Young%2C+M%2E+Gas%CC%8Cic%CC%81%2C+B%2E+Thomson%2C+and+J%2E+D%2E+Williams%2E+2013%2E+POMDP%2Dbased+statistical+spoken+dialog+systems%3A+A+review%2E+In+Proceedings+of+the+IEEE%2C+5%2C+pages+1160%E2%80%931179%2E)
32. T. Zhao, R. Zhao, and M. Eskenazi. 2017. Learning discourse-level diversity for neural dialog models using conditional variational autoencoders. In Association for Computational Linguistics (ACL). [find](https://scholar.google.com/scholar?q=T%2E+Zhao%2C+R%2E+Zhao%2C+and+M%2E+Eskenazi%2E+2017%2E+Learning+discourse%2Dlevel+diversity+for+neural+dialog+models+using+conditional+variational+autoencoders%2E+In+Association+for+Computational+Linguistics+%28ACL%29%2E) [our card](https://md.research.elamur.ai/free/en/papers/zhao-2017-learning-discourse-level-diversity-neural/)