---
title: "Perspective-taking and Pragmatics for Generating — Kim 2021"
description: "The paper addresses a gap in empathetic dialogue systems: their replies tend to be generic instead of addressing what actually triggered the user's…"
authors: ["Hyunwoo Kim", "Byeongchang Kim", "Gunhee Kim"]
year: 2021
venue: "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing"
source: "https://aclanthology.org/2021.emnlp-main.170/"
doi: "10.18653/v1/2021.emnlp-main.170"
arxiv: "2109.08828"
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/papers/kim-2021-perspective-taking-pragmatics-generating-empathetic/"
---
[Elamur Research](https://md.research.elamur.ai/) · [this page in HTML](https://research.elamur.ai/free/papers/kim-2021-perspective-taking-pragmatics-generating-empathetic/)

[home](https://md.research.elamur.ai/) / [papers](https://md.research.elamur.ai/free/papers/) / [2021](https://md.research.elamur.ai/free/papers/2021/page/3/) / Perspective-taking and Pragmatics for Generating Empathetic Responses Focused on Emotion Causes

# Perspective-taking and Pragmatics for Generating Empathetic Responses Focused on Emotion Causes

**Authors:** [Hyunwoo Kim](https://md.research.elamur.ai/free/authors/hyunwoo-kim/), [Byeongchang Kim](https://md.research.elamur.ai/free/authors/byeongchang-kim/), [Gunhee Kim](https://md.research.elamur.ai/free/authors/gunhee-kim/) · **Year:** 2021 · **Venue:** Proceedings of the 2021 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/2021.emnlp-main.170/) · [PDF](https://aclanthology.org/2021.emnlp-main.170.pdf) · [DOI 10.18653/v1/2021.emnlp-main.170](https://doi.org/10.18653/v1/2021.emnlp-main.170) · [arXiv 2109.08828](https://arxiv.org/abs/2109.08828) · [OpenAlex](https://openalex.org/W3201162576)

**Citations:** 57 citations (openalex-snapshot · 2026-10-14) · [33](#cited-by) in our library, of the 140673 papers whose bibliographies we read

## Summary
The paper addresses a gap in empathetic dialogue systems: their replies tend to be generic instead of addressing what actually triggered the user's emotion. The authors split this into two subproblems. The first is detecting emotion cause words without token-level annotation. The second is steering generation toward those words. For detection, they train a generative emotion estimator (GEE) on BART. The model learns to produce situation descriptions from EmpatheticDialogues conditioned on an emotion label. Bayes' rule then turns it into an emotion classifier and a per-word scorer of how strongly each word relates to the predicted emotion. For generation, they extend the Rational Speech Acts (RSA) framework so a pragmatic speaker emphasizes chosen input words. This works at inference time and needs no retraining. The authors also release EmoCause, human annotations of cause words for EmpatheticDialogues validation and test situations. Applied to MIME, DodecaTransformer and Blender, the "Focused S1" decoding raises model-based empathy scores and human ratings. This matters because it gives any existing dialogue agent more situation-specific empathy without extra labeled data.

## Key points
- GEE models P(C, E) = P(E)P(C|E) with BART. It reaches perplexity 13.6 on EmpatheticDialogues test situations, which cover 32 roughly balanced emotion labels. A uniform emotion prior is used, and the top-k scored words are taken as emotion cause words.
- Only sentence-level emotion labels are needed. According to the authors, this weakly supervised cause-word recognition outperforms other baselines.
- New resource: the EmoCause evaluation set, built from EmpatheticDialogues validation and test situations and publicly released.
- Focused S1 improves Exploration and Interpretation empathy scores (Sharma et al., 2020) over base S0 for all three agents. In contrast, simply adding emotion labels during finetuning (S0+Emotion) lowered these scores.
- Human evaluation used Amazon Mechanical Turk with 100 samples, 3 raters each, on 4-point Likert scales (Krippendorff's α of 0.26 for ratings and 0.27 for A/B tests). Raters judged Focused S1 more empathetic, relevant and fluent. In a 200-sample A/B test on Blender, its responses were also judged to reflect cause words better than plain RSA.

*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: [Linguistics & languages](https://md.research.elamur.ai/free/shelves/linguistics/)

## Cited by

Cited by

33 papers of our library cite it (of the 140673 whose bibliographies we read); 2 of them have a page here, 31 not yet.

- [Pragmatics in Language Grounding: Phenomena, Tasks, and Modeling Approaches](https://md.research.elamur.ai/free/papers/fried-2023-pragmatics-language-grounding-phenomena-tasks/)
- [RSA-Control: A Pragmatics-Grounded Lightweight Controllable Text Generation Framework](https://md.research.elamur.ai/free/papers/wang-2024-rsa-control-pragmatics-grounded-lightweight/)

## Cite

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

```bibtex
@inproceedings{kim2021perspective,
  title = {{Perspective-taking and Pragmatics for Generating Empathetic Responses Focused on Emotion Causes}},
  author = {Kim, Hyunwoo and Kim, Byeongchang and Kim, Gunhee},
  booktitle = {Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing},
  year = {2021},
  doi = {10.18653/v1/2021.emnlp-main.170},
  eprint = {2109.08828},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.18653/v1/2021.emnlp-main.170}
}
```

- [← previous Persistent Anti-Muslim Bias in Large Language Models](https://md.research.elamur.ai/free/papers/abid-2021-persistent-anti-muslim-bias-large/)
- [next → Points of Contact: The Shared Intellectual History of Vocalisation in Syriac, Arabic, and Hebrew](https://md.research.elamur.ai/free/papers/hbobook-obp0271-posegay-points-contact/)
- [↑ back to papers of 2021](https://md.research.elamur.ai/free/papers/2021/page/3/)

## References

48 references, 12 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Jacob Andreas and Dan Klein. 2016. Reasoning about Pragmatics with Neural Listeners and Speakers. In EMNLP. [find](https://scholar.google.com/scholar?q=Jacob+Andreas+and+Dan+Klein%2E+2016%2E+Reasoning+about+Pragmatics+with+Neural+Listeners+and+Speakers%2E+In+EMNLP%2E) [our card](https://md.research.elamur.ai/free/papers/andreas-2016-reasoning-about-pragmatics-neural-listeners/)
2. C Daniel Batson, Judy G Batson, Jacqueline K Slingsby, Kevin L Harrell, Heli M Peekna, and R Matthew Todd. 1991. Empathic Joy and the Empathy-Altruism Hypothesis. Journal of Personality and Social Psychology, 61(3):413. [find](https://scholar.google.com/scholar?q=C+Daniel+Batson%2C+Judy+G+Batson%2C+Jacqueline+K+Slingsby%2C+Kevin+L+Harrell%2C+Heli+M+Peekna%2C+and+R+Matthew+Todd%2E+1991%2E+Empathic+Joy+and+the+Empathy%2DAltruism+Hypothesis%2E+Journal+of+Personality+and+Social+Psy)
3. Carlos Busso, Murtaza Bulut, Chi-Chun Lee, Abe Kazemzadeh, Emily Mower, Samuel Kim, Jeannette N Chang, Sungbok Lee, and Shrikanth S Narayanan. 2008. IEMOCAP: Interactive Emotional Dyadic Motion Capture Database. Language Resources and Evaluation, 42(4):335–359. [find](https://scholar.google.com/scholar?q=Carlos+Busso%2C+Murtaza+Bulut%2C+Chi%2DChun+Lee%2C+Abe+Kazemzadeh%2C+Emily+Mower%2C+Samuel+Kim%2C+Jeannette+N+Chang%2C+Sungbok+Lee%2C+and+Shrikanth+S+Narayanan%2E+2008%2E+IEMOCAP%3A+Interactive+Emotional+Dyadic+Motion+Captur)
4. Ying Chen, Wenjun Hou, Xiyao Cheng, and Shoushan Li. 2018. Joint Learning for Emotion Classification and Emotion Cause Detection. In EMNLP. [find](https://scholar.google.com/scholar?q=Ying+Chen%2C+Wenjun+Hou%2C+Xiyao+Cheng%2C+and+Shoushan+Li%2E+2018%2E+Joint+Learning+for+Emotion+Classification+and+Emotion+Cause+Detection%2E+In+EMNLP%2E)
5. We studied how to use a generative estimator for Reuben Cohn-Gordon and Noah Goodman. 2019. Lost in Machine Translation: A Method to Reduce Mean-identifying emotion cause words from utterances ing Loss. In NAACL-HLT. based solely on emotion labels without word-level labels (i.e. weakly-supervised em… [find](https://scholar.google.com/scholar?q=We+studied+how+to+use+a+generative+estimator+for+Reuben+Cohn%2DGordon+and+Noah+Goodman%2E+2019%2E+Lost+in+Machine+Translation%3A+A+Method+to+Reduce+Mean%2Didentifying+emotion+cause+words+from+utterances+ing+Los) [our card](https://md.research.elamur.ai/free/papers/gordon-2018-pragmatically-informative-image-captioning-character/)
6. We Mark H Davis. 1983. Measuring Individual Differ-release the evaluation set to the public for future ences in Empathy: Evidence for a Multidimensional 2235 [find](https://scholar.google.com/scholar?q=We+Mark+H+Davis%2E+1983%2E+Measuring+Individual+Differ%2Drelease+the+evaluation+set+to+the+public+for+future+ences+in+Empathy%3A+Evidence+for+a+Multidimensional+2235)
7. Approach. Journal of Personality and Social Psychology, 44(1):113. [find](https://scholar.google.com/scholar?q=Approach%2E+Journal+of+Personality+and+Social+Psychology%2C+44%281%29%3A113%2E)
8. Jean Decety and Thierry Chaminade. 2003. Neural Correlates of Feeling Sympathy. Neuropsychologia, 41(2):127–138. [find](https://scholar.google.com/scholar?q=Jean+Decety+and+Thierry+Chaminade%2E+2003%2E+Neural+Correlates+of+Feeling+Sympathy%2E+Neuropsychologia%2C+41%282%29%3A127%E2%80%93138%2E)
9. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL-HLT. [find](https://scholar.google.com/scholar?q=Jacob+Devlin%2C+Ming%2DWei+Chang%2C+Kenton+Lee%2C+and+Kristina+Toutanova%2E+2019%2E+BERT%3A+Pre%2Dtraining+of+Deep+Bidirectional+Transformers+for+Language+Understanding%2E+In+NAACL%2DHLT%2E)
10. Chuang Fan, Hongyu Yan, Jiachen Du, Lin Gui, Lidong Bing, Min Yang, Ruifeng Xu, and Ruibin Mao. 2019. A Knowledge Regularized Hierarchical Approach for Emotion Cause Analysis. In EMNLP. [find](https://scholar.google.com/scholar?q=Chuang+Fan%2C+Hongyu+Yan%2C+Jiachen+Du%2C+Lin+Gui%2C+Lidong+Bing%2C+Min+Yang%2C+Ruifeng+Xu%2C+and+Ruibin+Mao%2E+2019%2E+A+Knowledge+Regularized+Hierarchical+Approach+for+Emotion+Cause+Analysis%2E+In+EMNLP%2E)
11. Michael C Frank and Noah D Goodman. 2012. Predicting Pragmatic Reasoning in Language Games. Science, 336(6084):998–998. [find](https://scholar.google.com/scholar?q=Michael+C+Frank+and+Noah+D+Goodman%2E+2012%2E+Predicting+Pragmatic+Reasoning+in+Language+Games%2E+Science%2C+336%286084%29%3A998%E2%80%93998%2E) [our card](https://md.research.elamur.ai/free/papers/frank-2012-predicting-pragmatic-reasoning-language-games/)
12. Daniel Fried, Ronghang Hu, Volkan Cirik, Anna Rohrbach, Jacob Andreas, Louis-Philippe Morency, Taylor Berg-Kirkpatrick, Kate Saenko, Dan Klein, and Trevor Darrell. 2018. Speaker-follower models for vision-and-language navigation. In NeurIPS. [find](https://scholar.google.com/scholar?q=Daniel+Fried%2C+Ronghang+Hu%2C+Volkan+Cirik%2C+Anna+Rohrbach%2C+Jacob+Andreas%2C+Louis%2DPhilippe+Morency%2C+Taylor+Berg%2DKirkpatrick%2C+Kate+Saenko%2C+Dan+Klein%2C+and+Trevor+Darrell%2E+2018%2E+Speaker%2Dfollower+models+for+vi)
13. Vittorio Gallese, Christian Keysers, and Giacomo Rizzolatti. 2004. A Unifying View of the Basis of Social Cognition. Trends in Cognitive Sciences, 8(9):396–403. [find](https://scholar.google.com/scholar?q=Vittorio+Gallese%2C+Christian+Keysers%2C+and+Giacomo+Rizzolatti%2E+2004%2E+A+Unifying+View+of+the+Basis+of+Social+Cognition%2E+Trends+in+Cognitive+Sciences%2C+8%289%29%3A396%E2%80%93403%2E)
14. Qinghong Gao, Jiannan Hu, Ruifeng Xu, Gui Lin, Yulan He, Qin Lu, and Kam-Fai Wong. 2017. Overview of NTCIR-13 ECA Task. In NTCIR-13. [find](https://scholar.google.com/scholar?q=Qinghong+Gao%2C+Jiannan+Hu%2C+Ruifeng+Xu%2C+Gui+Lin%2C+Yulan+He%2C+Qin+Lu%2C+and+Kam%2DFai+Wong%2E+2017%2E+Overview+of+NTCIR%2D13+ECA+Task%2E+In+NTCIR%2D13%2E)
15. Thomas L Griffiths, Charles Kemp, and Joshua B Tenenbaum. 2008. Bayesian Models of Cognition. Cambridge Handbook of Computational Cognitive Modeling, pages 115–126. [find](https://scholar.google.com/scholar?q=Thomas+L+Griffiths%2C+Charles+Kemp%2C+and+Joshua+B+Tenenbaum%2E+2008%2E+Bayesian+Models+of+Cognition%2E+Cambridge+Handbook+of+Computational+Cognitive+Modeling%2C+pages+115%E2%80%93126%2E)
16. Lin Gui, Jiannan Hu, Yulan He, Ruifeng Xu, Qin Lu, and Jiachen Du. 2017. A Question Answering Approach for Emotion Cause Extraction. In EMNLP. [find](https://scholar.google.com/scholar?q=Lin+Gui%2C+Jiannan+Hu%2C+Yulan+He%2C+Ruifeng+Xu%2C+Qin+Lu%2C+and+Jiachen+Du%2E+2017%2E+A+Question+Answering+Approach+for+Emotion+Cause+Extraction%2E+In+EMNLP%2E)
17. Lin Gui, Dongyin Wu, Ruifeng Xu, Qin Lu, and Yu Zhou. 2016. Event-Driven Emotion Cause Extraction with Corpus Construction. In EMNLP. [find](https://scholar.google.com/scholar?q=Lin+Gui%2C+Dongyin+Wu%2C+Ruifeng+Xu%2C+Qin+Lu%2C+and+Yu+Zhou%2E+2016%2E+Event%2DDriven+Emotion+Cause+Extraction+with+Corpus+Construction%2E+In+EMNLP%2E)
18. Lin Gui, Li Yuan, Ruifeng Xu, Bin Liu, Qin Lu, and Yu Zhou. 2014. Emotion Cause Detection with Linguistic Construction in Chinese Weibo Text. In NLPCC. [find](https://scholar.google.com/scholar?q=Lin+Gui%2C+Li+Yuan%2C+Ruifeng+Xu%2C+Bin+Liu%2C+Qin+Lu%2C+and+Yu+Zhou%2E+2014%2E+Emotion+Cause+Detection+with+Linguistic+Construction+in+Chinese+Weibo+Text%2E+In+NLPCC%2E)
19. Hyunwoo Kim, Byeongchang Kim, and Gunhee Kim. 2020. Will I Sound Like Me? Improving Persona Consistency in Dialogues through Pragmatic Self-Consciousness. In EMNLP. [find](https://scholar.google.com/scholar?q=Hyunwoo+Kim%2C+Byeongchang+Kim%2C+and+Gunhee+Kim%2E+2020%2E+Will+I+Sound+Like+Me%3F+Improving+Persona+Consistency+in+Dialogues+through+Pragmatic+Self%2DConsciousness%2E+In+EMNLP%2E) [our card](https://md.research.elamur.ai/free/papers/kim-2020-will-i-sound-like-me/)
20. Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Ves Stoyanov, and Luke Zettlemoyer. 2020. BART: Denoising Sequence-to-Sequence Pre-Training for Natural Language Generation, Translation, and Comprehension. In ACL. [find](https://scholar.google.com/scholar?q=Mike+Lewis%2C+Yinhan+Liu%2C+Naman+Goyal%2C+Marjan+Ghazvininejad%2C+Abdelrahman+Mohamed%2C+Omer+Levy%2C+Ves+Stoyanov%2C+and+Luke+Zettlemoyer%2E+2020%2E+BART%3A+Denoising+Sequence%2Dto%2DSequence+Pre%2DTraining+for+Natural+Langu) [our card](https://md.research.elamur.ai/free/papers/lewis-2020-bart-denoising-sequence-sequence-pre/)
21. Qintong Li, Hongshen Chen, Zhaochun Ren, Pengjie Ren, Zhaopeng Tu, and Zhumin Chen. 2020. EmpDG: Multi-resolution Interactive Empathetic Dialogue Generation. In COLING. [find](https://scholar.google.com/scholar?q=Qintong+Li%2C+Hongshen+Chen%2C+Zhaochun+Ren%2C+Pengjie+Ren%2C+Zhaopeng+Tu%2C+and+Zhumin+Chen%2E+2020%2E+EmpDG%3A+Multi%2Dresolution+Interactive+Empathetic+Dialogue+Generation%2E+In+COLING%2E)
22. Xiangju Li, Kaisong Song, Shi Feng, Daling Wang, and Yifei Zhang. 2018. A Co-Attention Neural Network Model for Emotion Cause Analysis with Emotional Context Awareness. In EMNLP. [find](https://scholar.google.com/scholar?q=Xiangju+Li%2C+Kaisong+Song%2C+Shi+Feng%2C+Daling+Wang%2C+and+Yifei+Zhang%2E+2018%2E+A+Co%2DAttention+Neural+Network+Model+for+Emotion+Cause+Analysis+with+Emotional+Context+Awareness%2E+In+EMNLP%2E)
23. Yanran Li, Hui Su, Xiaoyu Shen, Wenjie Li, Ziqiang Cao, and Shuzi Niu. 2017. DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset. In IJC-NLP. [find](https://scholar.google.com/scholar?q=Yanran+Li%2C+Hui+Su%2C+Xiaoyu+Shen%2C+Wenjie+Li%2C+Ziqiang+Cao%2C+and+Shuzi+Niu%2E+2017%2E+DailyDialog%3A+A+Manually+Labelled+Multi%2Dturn+Dialogue+Dataset%2E+In+IJC%2DNLP%2E) [our card](https://md.research.elamur.ai/free/papers/li-2017-dailydialog-manually-labelled-multi-turn/)
24. Zhaojiang Lin, Andrea Madotto, Jamin Shin, Peng Xu, and Pascale Fung. 2019. MoEL: Mixture of Empathetic Listeners. In EMNLP. [find](https://scholar.google.com/scholar?q=Zhaojiang+Lin%2C+Andrea+Madotto%2C+Jamin+Shin%2C+Peng+Xu%2C+and+Pascale+Fung%2E+2019%2E+MoEL%3A+Mixture+of+Empathetic+Listeners%2E+In+EMNLP%2E)
25. Zhaojiang Lin, Peng Xu, Genta Indra Winata, Zihan Liu, and Pascale Fung. 2020. CAiRE: An End-to-End Empathetic Chatbot. In AAAI. [find](https://scholar.google.com/scholar?q=Zhaojiang+Lin%2C+Peng+Xu%2C+Genta+Indra+Winata%2C+Zihan+Liu%2C+and+Pascale+Fung%2E+2020%2E+CAiRE%3A+An+End%2Dto%2DEnd+Empathetic+Chatbot%2E+In+AAAI%2E)
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:1907.11692. [find](https://scholar.google.com/scholar?q=Yinhan+Liu%2C+Myle+Ott%2C+Naman+Goyal%2C+Jingfei+Du%2C+Mandar+Joshi%2C+Danqi+Chen%2C+Omer+Levy%2C+Mike+Lewis%2C+Luke+Zettlemoyer%2C+and+Veselin+Stoyanov%2E+2019%2E+RoBERTa%3A+A+Robustly+Optimized+BERT+Pretraining+Approach%2E+a)
27. Navonil Majumder, Pengfei Hong, Shanshan Peng, Jiankun Lu, Deepanway Ghosal, Alexander Gelbukh, Rada Mihalcea, and Soujanya Poria. 2020. MIME: MIMicking Emotions for Empathetic Response Generation. In EMNLP. [find](https://scholar.google.com/scholar?q=Navonil+Majumder%2C+Pengfei+Hong%2C+Shanshan+Peng%2C+Jiankun+Lu%2C+Deepanway+Ghosal%2C+Alexander+Gelbukh%2C+Rada+Mihalcea%2C+and+Soujanya+Poria%2E+2020%2E+MIME%3A+MIMicking+Emotions+for+Empathetic+Response+Generation%2E+In)
28. A. H. Miller, W. Feng, A. Fisch, J. Lu, D. Batra, A. Bordes, D. Parikh, and J. Weston. 2017. ParlAI: A Dialog Research Software Platform. arXiv:1705.06476. [find](https://scholar.google.com/scholar?q=A%2E+H%2E+Miller%2C+W%2E+Feng%2C+A%2E+Fisch%2C+J%2E+Lu%2C+D%2E+Batra%2C+A%2E+Bordes%2C+D%2E+Parikh%2C+and+J%2E+Weston%2E+2017%2E+ParlAI%3A+A+Dialog+Research+Software+Platform%2E+arXiv%3A1705%2E06476%2E) [our card](https://md.research.elamur.ai/free/papers/miller-2017-parlai-dialog-research-software-platform/)
29. Saif M Mohammad and Peter D Turney. 2013. Crowdsourcing a Word-Emotion Association Lexicon. Computational Intelligence, 29(3):436–465. [find](https://scholar.google.com/scholar?q=Saif+M+Mohammad+and+Peter+D+Turney%2E+2013%2E+Crowdsourcing+a+Word%2DEmotion+Association+Lexicon%2E+Computational+Intelligence%2C+29%283%29%3A436%E2%80%93465%2E)
30. Desmond C Ong, Jamil Zaki, and Noah D Goodman. 2015. Affective Cognition: Exploring Lay Theories of Emotion. Cognition, 143:141–162. [find](https://scholar.google.com/scholar?q=Desmond+C+Ong%2C+Jamil+Zaki%2C+and+Noah+D+Goodman%2E+2015%2E+Affective+Cognition%3A+Exploring+Lay+Theories+of+Emotion%2E+Cognition%2C+143%3A141%E2%80%93162%2E)
31. Desmond C Ong, Jamil Zaki, and Noah D Goodman. 2019. Computational Models of Emotion Inference in Theory of Mind: A Review and Roadmap. Topics in Cognitive Science, 11(2):338–357. [find](https://scholar.google.com/scholar?q=Desmond+C+Ong%2C+Jamil+Zaki%2C+and+Noah+D+Goodman%2E+2019%2E+Computational+Models+of+Emotion+Inference+in+Theory+of+Mind%3A+A+Review+and+Roadmap%2E+Topics+in+Cognitive+Science%2C+11%282%29%3A338%E2%80%93357%2E)
32. Soujanya Poria, Navonil Majumder, Devamanyu Haz-arika, Deepanway Ghosal, Rishabh Bhardwaj, Samson Yu Bai Jian, Romila Ghosh, Niyati Chhaya, Alexander Gelbukh, and Rada Mihalcea. 2020. Recognizing Emotion Cause in Conversations. arXiv:2012.11820. — [arXiv:2012.11820](https://arxiv.org/abs/2012.11820) [find](https://scholar.google.com/scholar?q=Soujanya+Poria%2C+Navonil+Majumder%2C+Devamanyu+Haz%2Darika%2C+Deepanway+Ghosal%2C+Rishabh+Bhardwaj%2C+Samson+Yu+Bai+Jian%2C+Romila+Ghosh%2C+Niyati+Chhaya%2C+Alexander+Gelbukh%2C+and+Rada+Mihalcea%2E+2020%2E+Recognizing+Emot)
33. Hannah Rashkin, Eric Michael Smith, Margaret Li, and Y-Lan Boureau. 2019. Towards Empathetic Open-domain Conversation Models: A New Benchmark and Dataset. In ACL. [find](https://scholar.google.com/scholar?q=Hannah+Rashkin%2C+Eric+Michael+Smith%2C+Margaret+Li%2C+and+Y%2DLan+Boureau%2E+2019%2E+Towards+Empathetic+Open%2Ddomain+Conversation+Models%3A+A+New+Benchmark+and+Dataset%2E+In+ACL%2E)
34. Giacomo Rizzolatti and Laila Craighero. 2004. The Mirror-Neuron System. Annual Review of Neuroscience, 27:169–192. [find](https://scholar.google.com/scholar?q=Giacomo+Rizzolatti+and+Laila+Craighero%2E+2004%2E+The+Mirror%2DNeuron+System%2E+Annual+Review+of+Neuroscience%2C+27%3A169%E2%80%93192%2E)
35. Stephen Roller, Emily Dinan, Naman Goyal, Da Ju, Mary Williamson, Yinhan Liu, Jing Xu, Myle Ott, Kurt Shuster, Eric M Smith, et al. 2021. Recipes for Building an Open-Domain Chatbot. In EACL. [find](https://scholar.google.com/scholar?q=Stephen+Roller%2C+Emily+Dinan%2C+Naman+Goyal%2C+Da+Ju%2C+Mary+Williamson%2C+Yinhan+Liu%2C+Jing+Xu%2C+Myle+Ott%2C+Kurt+Shuster%2C+Eric+M+Smith%2C+et+al%2E+2021%2E+Recipes+for+Building+an+Open%2DDomain+Chatbot%2E+In+EACL%2E) [our card](https://md.research.elamur.ai/free/papers/roller-2021-recipes-building-open-domain-chatbot/)
36. Stuart Rose, Dave Engel, Nick Cramer, and Wendy Cowley. 2010. Automatic Keyword Extraction from Individual Documents. Text mining: applications and theory, 1:1–20. [find](https://scholar.google.com/scholar?q=Stuart+Rose%2C+Dave+Engel%2C+Nick+Cramer%2C+and+Wendy+Cowley%2E+2010%2E+Automatic+Keyword+Extraction+from+Individual+Documents%2E+Text+mining%3A+applications+and+theory%2C+1%3A1%E2%80%9320%2E)
37. Perrine Ruby and Jean Decety. 2004. How would You Feel Versus How do You Think She would Feel? A Neuroimaging Study of Perspective-taking with Social Emotions. Journal of Cognitive Neuroscience, 16(6):988–999. [find](https://scholar.google.com/scholar?q=Perrine+Ruby+and+Jean+Decety%2E+2004%2E+How+would+You+Feel+Versus+How+do+You+Think+She+would+Feel%3F+A+Neuroimaging+Study+of+Perspective%2Dtaking+with+Social+Emotions%2E+Journal+of+Cognitive+Neuroscience%2C+16%286%29)
38. Rebecca Saxe and Sean Dae Houlihan. 2017. Formalizing Emotion Concepts within a Bayesian Model of Theory of Mind. Current Opinion in Psychology, 17:15–21. [find](https://scholar.google.com/scholar?q=Rebecca+Saxe+and+Sean+Dae+Houlihan%2E+2017%2E+Formalizing+Emotion+Concepts+within+a+Bayesian+Model+of+Theory+of+Mind%2E+Current+Opinion+in+Psychology%2C+17%3A15%E2%80%9321%2E)
39. Ashish Sharma, Adam Miner, David Atkins, and Tim Althoff. 2020. A Computational Approach to Understanding Empathy Expressed in Text-Based Mental Health Support. In EMNLP. [find](https://scholar.google.com/scholar?q=Ashish+Sharma%2C+Adam+Miner%2C+David+Atkins%2C+and+Tim+Althoff%2E+2020%2E+A+Computational+Approach+to+Understanding+Empathy+Expressed+in+Text%2DBased+Mental+Health+Support%2E+In+EMNLP%2E) [our card](https://md.research.elamur.ai/free/papers/sharma-2020-computational-approach-understanding-empathy-expressed/)
40. Sheng Shen, Daniel Fried, Jacob Andreas, and Dan Klein. 2019. Pragmatically Informative Text Generation. In NAACL-HLT. [find](https://scholar.google.com/scholar?q=Sheng+Shen%2C+Daniel+Fried%2C+Jacob+Andreas%2C+and+Dan+Klein%2E+2019%2E+Pragmatically+Informative+Text+Generation%2E+In+NAACL%2DHLT%2E) [our card](https://md.research.elamur.ai/free/papers/shen-2019-pragmatically-informative-text-generation/)
41. Weiyan Shi and Zhou Yu. 2018. Sentiment Adaptive End-to-End Dialog Systems. In ACL. [find](https://scholar.google.com/scholar?q=Weiyan+Shi+and+Zhou+Yu%2E+2018%2E+Sentiment+Adaptive+End%2Dto%2DEnd+Dialog+Systems%2E+In+ACL%2E)
42. Kurt Shuster, Da Ju, Stephen Roller, Emily Dinan, Y-Lan Boureau, and Jason Weston. 2020. The Dialogue Dodecathlon: Open-domain Knowledge and Image Grounded Conversational Agents. In ACL. [find](https://scholar.google.com/scholar?q=Kurt+Shuster%2C+Da+Ju%2C+Stephen+Roller%2C+Emily+Dinan%2C+Y%2DLan+Boureau%2C+and+Jason+Weston%2E+2020%2E+The+Dialogue+Dodecathlon%3A+Open%2Ddomain+Knowledge+and+Image+Grounded+Conversational+Agents%2E+In+ACL%2E)
43. Farhad Bin Siddique, Onno Kampman, Yang Yang, Anik Dey, and Pascale Fung. 2017. Zara Returns: Improved Personality Induction and Adaptation by an Empathetic Virtual Agent. In ACL. [find](https://scholar.google.com/scholar?q=Farhad+Bin+Siddique%2C+Onno+Kampman%2C+Yang+Yang%2C+Anik+Dey%2C+and+Pascale+Fung%2E+2017%2E+Zara+Returns%3A+Improved+Personality+Induction+and+Adaptation+by+an+Empathetic+Virtual+Agent%2E+In+ACL%2E)
44. Eric Michael Smith, Mary Williamson, Kurt Shuster, Jason Weston, and Y-Lan Boureau. 2020. Can You Put it All Together: Evaluating Conversational Agents’ Ability to Blend Skills. In ACL. [find](https://scholar.google.com/scholar?q=Eric+Michael+Smith%2C+Mary+Williamson%2C+Kurt+Shuster%2C+Jason+Weston%2C+and+Y%2DLan+Boureau%2E+2020%2E+Can+You+Put+it+All+Together%3A+Evaluating+Conversational+Agents%E2%80%99+Ability+to+Blend+Skills%2E+In+ACL%2E) [our card](https://md.research.elamur.ai/free/papers/smith-2020-can-you-put-it-all/)
45. Ramakrishna Vedantam, Samy Bengio, Kevin Murphy, Devi Parikh, and Gal Chechik. 2017. Context-Aware Captions from Context-Agnostic Supervision. In CVPR. [find](https://scholar.google.com/scholar?q=Ramakrishna+Vedantam%2C+Samy+Bengio%2C+Kevin+Murphy%2C+Devi+Parikh%2C+and+Gal+Chechik%2E+2017%2E+Context%2DAware+Captions+from+Context%2DAgnostic+Supervision%2E+In+CVPR%2E)
46. Rui Xia and Zixiang Ding. 2019. Emotion-Cause Pair Extraction: A New Task to Emotion Analysis in Texts. In ACL. [find](https://scholar.google.com/scholar?q=Rui+Xia+and+Zixiang+Ding%2E+2019%2E+Emotion%2DCause+Pair+Extraction%3A+A+New+Task+to+Emotion+Analysis+in+Texts%2E+In+ACL%2E)
47. Sina Zarrieß and David Schlangen. 2019. Know What You Don’t Know: Modeling a Pragmatic Speaker that Refers to Objects of Unknown Categories. In ACL. [find](https://scholar.google.com/scholar?q=Sina+Zarrie%C3%9F+and+David+Schlangen%2E+2019%2E+Know+What+You+Don%E2%80%99t+Know%3A+Modeling+a+Pragmatic+Speaker+that+Refers+to+Objects+of+Unknown+Categories%2E+In+ACL%2E) [our card](https://md.research.elamur.ai/free/papers/zarrie-2019-know-what-you-don-t/)
48. Peixiang Zhong, Chen Zhang, Hao Wang, Yong Liu, and Chunyan Miao. 2020. Towards Persona-Based Empathetic Conversational Models. In EMNLP. [find](https://scholar.google.com/scholar?q=Peixiang+Zhong%2C+Chen+Zhang%2C+Hao+Wang%2C+Yong+Liu%2C+and+Chunyan+Miao%2E+2020%2E+Towards+Persona%2DBased+Empathetic+Conversational+Models%2E+In+EMNLP%2E)