---
title: "Multi-Turn Response Selection for Chatbots with — Zhou 2018"
description: "The paper addresses multi-turn response selection: given a multi-utterance conversation history, a retrieval-based chatbot must pick the most suitable…"
authors: ["Xiangyang Zhou", "Lu Li", "Daxiang Dong", "Yi Liu", "Ying Chen", "Wayne Xin Zhao", "Dianhai Yu", "Hua Wu"]
year: 2018
venue: "Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/P18-1103/"
doi: "10.18653/v1/p18-1103"
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/zhou-2018-multi-turn-response-selection-chatbots/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/zhou-2018-multi-turn-response-selection-chatbots/)

[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/3/) / Multi-Turn Response Selection for Chatbots with Deep Attention Matching Network

# Multi-Turn Response Selection for Chatbots with Deep Attention Matching Network

**Authors:** Xiangyang Zhou, [Lu Li](https://md.research.elamur.ai/free/en/authors/lu-li/), [Daxiang Dong](https://md.research.elamur.ai/free/en/authors/daxiang-dong/), [Yi Liu](https://md.research.elamur.ai/free/en/authors/yi-liu/), Ying Chen, [Wayne Xin Zhao](https://md.research.elamur.ai/free/en/authors/wayne-xin-zhao/), [Dianhai Yu](https://md.research.elamur.ai/free/en/authors/dianhai-yu/), [Hua Wu](https://md.research.elamur.ai/free/en/authors/hua-wu/) · **Year:** 2018 · **Venue:** Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/P18-1103/) · [PDF](https://aclanthology.org/P18-1103.pdf) · [DOI 10.18653/v1/p18-1103](https://doi.org/10.18653/v1/p18-1103) · [OpenAlex](https://openalex.org/W2798456655)

**Citations:** 328 citations (openalex-snapshot · 2026-10-14) · [80](#cited-by) in our library, of the 140884 papers whose bibliographies we read

## Summary
The paper addresses multi-turn response selection: given a multi-utterance conversation history, a retrieval-based chatbot must pick the most suitable reply from a set of candidates. Earlier matching models were mostly RNN-based and relied on surface textual overlap. They often missed replies that link to the context only implicitly, for example through pronoun coreference or functional relations. The authors propose the Deep Attention Matching Network (DAM), which uses only attention and draws on the Transformer. Stacked self-attention layers build word-centred representations at increasingly coarse granularities. Cross-attention between each context utterance and the candidate then captures latent dependencies. Similarity matrices from both attention types, computed at every layer, form a 3D matching image. Convolution and max-pooling extract features from it, and a single-layer perceptron turns them into a matching score. On the Ubuntu Corpus v1 and the Douban Conversation Corpus, DAM beats the previous best systems, gaining more than 4% in R10@1 over the strongest baseline. Its attention computations can run in parallel, which should make deployment easier.

## Key points
- DAM uses one shared Attentive Module, modelled on the Transformer, for two roles: self-attention when building representations and cross-attention when matching.
- For each of the L stacked layers plus the embedding level, the model builds two matrices per utterance–response pair: a self-attention-match matrix for textual relevance and a cross-attention-match matrix for dependency information.
- The model was evaluated on two large public benchmarks, Ubuntu Corpus v1 and Douban Conversation Corpus, with improvements over the best baseline of more than 4% on R10@1.
- The authors examined 100 test cases where DAM failed at R10@5. Most errors fell into two types:
  - "fuzzy-candidate": the reply is mostly fitting but wrong in small details.
  - "logical-error": the reply contradicts the context.
- As future work, the authors suggest adversarial rather than random negative sampling during training, modelling logic-level information, and applying the attention scheme to dialogue state tracking, spoken language understanding and seq2seq generation.

*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

80 papers of our library cite it (of the 140884 whose bibliographies we read); 4 of them have a page here, 76 not yet.

- [MuTual: A Dataset for Multi-Turn Dialogue Reasoning](https://md.research.elamur.ai/free/en/papers/cui-2020-mutual-dataset-multi-turn-dialogue/)
- [ConveRT: Efficient and Accurate Conversational Representations from Transformers](https://md.research.elamur.ai/free/en/papers/henderson-2020-convert-efficient-accurate-conversational-representations/)
- [Is ChatGPT a General-Purpose Natural Language Processing Task Solver?](https://md.research.elamur.ai/free/en/papers/qin-2023-chatgpt-general-purpose-natural-language/)
- [Knowledge-Enriched Transformer for Emotion Detection in Textual Conversations](https://md.research.elamur.ai/free/en/papers/zhong-2019-knowledge-enriched-transformer-emotion-detection/)

## Cite

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

```bibtex
@inproceedings{zhou2018multi,
  title = {{Multi-Turn Response Selection for Chatbots with Deep Attention Matching Network}},
  author = {Zhou, Xiangyang and Li, Lu and Dong, Daxiang and Liu, Yi and Chen, Ying and Zhao, Wayne Xin and Yu, Dianhai and Wu, Hua},
  booktitle = {Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2018},
  doi = {10.18653/v1/p18-1103},
  url = {https://doi.org/10.18653/v1/p18-1103}
}
```

- [← previous Multi-task learning for historical text normalization: Size matters](https://md.research.elamur.ai/free/en/papers/aclbulk-2018-bollmann-multi-task-learning-historical-text/)
- [next → Multimodal Language Analysis in the Wild: CMU-MOSEI Dataset and Interpretable Dynamic Fusion Graph](https://md.research.elamur.ai/free/en/papers/zadeh-2018-multimodal-language-analysis-wild-cmu/)
- [↑ back to papers of 2018](https://md.research.elamur.ai/free/en/papers/2018/page/3/)

## References

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

1. David Ameixa, Luisa Coheur, Pedro Fialho, and Paulo Quaresma. 2014. Luke, i am your father: dealing with out-of-domain requests by using movies subtitles. In International Conference on Intelligent Virtual Agents, pages 13–21. Springer. [find](https://scholar.google.com/scholar?q=David+Ameixa%2C+Luisa+Coheur%2C+Pedro+Fialho%2C+and+Paulo+Quaresma%2E+2014%2E+Luke%2C+i+am+your+father%3A+dealing+with+out%2Dof%2Ddomain+requests+by+using+movies+subtitles%2E+In+International+Conference+on+Intelligent+Vi)
2. Jimmy Lei Ba, Jamie Ryan Kiros, and Geoffrey E Hinton. 2016. Layer normalization. arXiv preprint arXiv:1607.06450. [find](https://scholar.google.com/scholar?q=Jimmy+Lei+Ba%2C+Jamie+Ryan+Kiros%2C+and+Geoffrey+E+Hinton%2E+2016%2E+Layer+normalization%2E+arXiv+preprint+arXiv%3A1607%2E06450%2E) [our card](https://md.research.elamur.ai/free/en/papers/ba-2016-layer-normalization/)
3. Ricardo Baeza-Yates, Berthier Ribeiro-Neto, et al. 1999. Modern information retrieval, volume 463. ACM press New York. [find](https://scholar.google.com/scholar?q=Ricardo+Baeza%2DYates%2C+Berthier+Ribeiro%2DNeto%2C+et+al%2E+1999%2E+Modern+information+retrieval%2C+volume+463%2E+ACM+press+New+York%2E)
4. Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2015. Neural machine translation by jointly learning to align and translate. international conference on learning representations. [find](https://scholar.google.com/scholar?q=Dzmitry+Bahdanau%2C+Kyunghyun+Cho%2C+and+Yoshua+Bengio%2E+2015%2E+Neural+machine+translation+by+jointly+learning+to+align+and+translate%2E+international+conference+on+learning+representations%2E) [our card](https://md.research.elamur.ai/free/en/papers/bahdanau-2014-neural-machine-translation-jointly-learning/)
5. Rafael E Banchs and Haizhou Li. 2012. Iris: a chat-oriented dialogue system based on the vector space model. In Proceedings of the ACL 2012 System Demonstrations, pages 37–42. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Rafael+E+Banchs+and+Haizhou+Li%2E+2012%2E+Iris%3A+a+chat%2Doriented+dialogue+system+based+on+the+vector+space+model%2E+In+Proceedings+of+the+ACL+2012+System+Demonstrations%2C+pages+37%E2%80%9342%2E+Association+for+Computat)
6. Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770– 778. [find](https://scholar.google.com/scholar?q=Kaiming+He%2C+Xiangyu+Zhang%2C+Shaoqing+Ren%2C+and+Jian+Sun%2E+2016%2E+Deep+residual+learning+for+image+recognition%2E+In+Proceedings+of+the+IEEE+conference+on+computer+vision+and+pattern+recognition%2C+pages+770%E2%80%93+)
7. Zongcheng Ji, Zhengdong Lu, and Hang Li. 2014. An information retrieval approach to short text conversation. arXiv preprint arXiv:1408.6988. — [arXiv:1408.6988](https://arxiv.org/abs/1408.6988) [find](https://scholar.google.com/scholar?q=Zongcheng+Ji%2C+Zhengdong+Lu%2C+and+Hang+Li%2E+2014%2E+An+information+retrieval+approach+to+short+text+conversation%2E+arXiv+preprint+arXiv%3A1408%2E6988%2E+%E2%80%94+%5BarXiv%3A1408%2E6988%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F1408%2E6988%29)
8. Quoc V Le, Jiquan Ngiam, Adam Coates, Abhik Lahiri, Bobby Prochnow, and Andrew Y Ng. 2011. On optimization methods for deep learning. In Proceedings of the 28th International Conference on International Conference on Machine Learning, pages 265–272. [find](https://scholar.google.com/scholar?q=Quoc+V+Le%2C+Jiquan+Ngiam%2C+Adam+Coates%2C+Abhik+Lahiri%2C+Bobby+Prochnow%2C+and+Andrew+Y+Ng%2E+2011%2E+On+optimization+methods+for+deep+learning%2E+In+Proceedings+of+the+28th+International+Conference+on+Internation)
9. Yann LeCun, Yoshua Bengio, and Geoffrey Hinton. 2015. Deep learning. Nature, 521(7553):436–444. [find](https://scholar.google.com/scholar?q=Yann+LeCun%2C+Yoshua+Bengio%2C+and+Geoffrey+Hinton%2E+2015%2E+Deep+learning%2E+Nature%2C+521%287553%29%3A436%E2%80%93444%2E)
10. Alan Lee, Rashmi Prasad, Aravind Joshi, Nikhil Dinesh, and Bonnie Webber. 2006. Complexity of dependencies in discourse: Are dependencies in discourse more complex than in syntax. In Proceedings of the 5th International Workshop on Treebanks and Linguistic Theories, Prague, Czech Republic, page 12. [find](https://scholar.google.com/scholar?q=Alan+Lee%2C+Rashmi+Prasad%2C+Aravind+Joshi%2C+Nikhil+Dinesh%2C+and+Bonnie+Webber%2E+2006%2E+Complexity+of+dependencies+in+discourse%3A+Are+dependencies+in+discourse+more+complex+than+in+syntax%2E+In+Proceedings+of+th)
11. Jiwei Li, Will Monroe, Tianlin Shi, Alan Ritter, and Dan Jurafsky. 2017. Adversarial learning for neural dialogue generation. In EMNLP, pages 372–381. [find](https://scholar.google.com/scholar?q=Jiwei+Li%2C+Will+Monroe%2C+Tianlin+Shi%2C+Alan+Ritter%2C+and+Dan+Jurafsky%2E+2017%2E+Adversarial+learning+for+neural+dialogue+generation%2E+In+EMNLP%2C+pages+372%E2%80%93381%2E) [our card](https://md.research.elamur.ai/free/en/papers/li-2017-adversarial-learning-neural-dialogue-generation/)
12. Zhouhan Lin, Minwei Feng, Cicero Nogueira dos Santos, Mo Yu, Bing Xiang, Bowen Zhou, and Yoshua Bengio. 2017. A structured self-attentive sentence embedding. international conference on learning representations. [find](https://scholar.google.com/scholar?q=Zhouhan+Lin%2C+Minwei+Feng%2C+Cicero+Nogueira+dos+Santos%2C+Mo+Yu%2C+Bing+Xiang%2C+Bowen+Zhou%2C+and+Yoshua+Bengio%2E+2017%2E+A+structured+self%2Dattentive+sentence+embedding%2E+international+conference+on+learning+repre) [our card](https://md.research.elamur.ai/free/en/papers/lin-2017-structured-self-attentive-sentence-embedding/)
13. Ryan Lowe, Michael Noseworthy, Iulian V Serban, Nicolas Angelard-Gontier, Yoshua Bengio, and Joelle Pineau. 2017. Towards an automatic turing test: Learning to evaluate dialogue responses. In ACL, pages 372–381. [find](https://scholar.google.com/scholar?q=Ryan+Lowe%2C+Michael+Noseworthy%2C+Iulian+V+Serban%2C+Nicolas+Angelard%2DGontier%2C+Yoshua+Bengio%2C+and+Joelle+Pineau%2E+2017%2E+Towards+an+automatic+turing+test%3A+Learning+to+evaluate+dialogue+responses%2E+In+ACL%2C+pag) [our card](https://md.research.elamur.ai/free/en/papers/lowe-2017-towards-automatic-turing-test-learning/)
14. Ryan Lowe, Nissan Pow, Iulian Vlad Serban, and Joelle Pineau. 2015. The ubuntu dialogue corpus: A large dataset for research in unstructured multi-turn dialogue systems. annual meeting of the special interest group on discourse and dialogue, pages 285–294. [find](https://scholar.google.com/scholar?q=Ryan+Lowe%2C+Nissan+Pow%2C+Iulian+Vlad+Serban%2C+and+Joelle+Pineau%2E+2015%2E+The+ubuntu+dialogue+corpus%3A+A+large+dataset+for+research+in+unstructured+multi%2Dturn+dialogue+systems%2E+annual+meeting+of+the+special+) [our card](https://md.research.elamur.ai/free/en/papers/lowe-2015-ubuntu-dialogue-corpus-large-dataset/)
15. Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781. [find](https://scholar.google.com/scholar?q=Tomas+Mikolov%2C+Kai+Chen%2C+Greg+Corrado%2C+and+Jeffrey+Dean%2E+2013%2E+Efficient+estimation+of+word+representations+in+vector+space%2E+arXiv+preprint+arXiv%3A1301%2E3781%2E)
16. Lasguido Nio, Sakriani Sakti, Graham Neubig, Tomoki Toda, Mirna Adriani, and Satoshi Nakamura. 2014. Developing non-goal dialog system based on examples of drama television. In Natural Interaction with Robots, Knowbots and Smartphones, pages 355– 361. Springer. [find](https://scholar.google.com/scholar?q=Lasguido+Nio%2C+Sakriani+Sakti%2C+Graham+Neubig%2C+Tomoki+Toda%2C+Mirna+Adriani%2C+and+Satoshi+Nakamura%2E+2014%2E+Developing+non%2Dgoal+dialog+system+based+on+examples+of+drama+television%2E+In+Natural+Interaction+wit)
17. Rui Yan, Yiping Song, and Hua Wu. 2016. Learning to respond with deep neural networks for retrieval-based human-computer conversation system. In Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval, pages 55–64. [find](https://scholar.google.com/scholar?q=Rui+Yan%2C+Yiping+Song%2C+and+Hua+Wu%2E+2016%2E+Learning+to+respond+with+deep+neural+networks+for+retrieval%2Dbased+human%2Dcomputer+conversation+system%2E+In+Proceedings+of+the+39th+International+ACM+SIGIR+confere)
18. Liang Pang, Yanyan Lan, Jiafeng Guo, Jun Xu, Shengxian Wan, and Xueqi Cheng. 2016. Text matching as image recognition. In AAAI, pages 2793–2799. [find](https://scholar.google.com/scholar?q=Liang+Pang%2C+Yanyan+Lan%2C+Jiafeng+Guo%2C+Jun+Xu%2C+Shengxian+Wan%2C+and+Xueqi+Cheng%2E+2016%2E+Text+matching+as+image+recognition%2E+In+AAAI%2C+pages+2793%E2%80%932799%2E)
19. Wenpeng Yin, Hinrich Schütze, Bing Xiang, and Bowen Zhou. 2016. Abcnn: Attention-based convolutional neural network for modeling sentence pairs. Transactions of the Association of Computational Linguistics, 4(1):259–272. [find](https://scholar.google.com/scholar?q=Wenpeng+Yin%2C+Hinrich+Schu%CC%88tze%2C+Bing+Xiang%2C+and+Bowen+Zhou%2E+2016%2E+Abcnn%3A+Attention%2Dbased+convolutional+neural+network+for+modeling+sentence+pairs%2E+Transactions+of+the+Association+of+Computational+Lingu) [our card](https://md.research.elamur.ai/free/en/papers/yin-2016-abcnn-attention-based-convolutional-neural/)
20. Alan Ritter, Colin Cherry, and William B Dolan. 2011. Data-driven response generation in social media. In In Proc. EMNLP, pages 583–593. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Alan+Ritter%2C+Colin+Cherry%2C+and+William+B+Dolan%2E+2011%2E+Data%2Ddriven+response+generation+in+social+media%2E+In+In+Proc%2E+EMNLP%2C+pages+583%E2%80%93593%2E+Association+for+Computational+Linguistics%2E) [our card](https://md.research.elamur.ai/free/en/papers/ritter-2011-data-driven-response-generation-social/)
21. Xiangyang Zhou, Daxiang Dong, Hua Wu, Shiqi Zhao, Dianhai Yu, Hao Tian, Xuan Liu, and Rui Yan. 2016. Multi-view response selection for human-computer conversation. In EMNLP, pages 372–381. [find](https://scholar.google.com/scholar?q=Xiangyang+Zhou%2C+Daxiang+Dong%2C+Hua+Wu%2C+Shiqi+Zhao%2C+Dianhai+Yu%2C+Hao+Tian%2C+Xuan+Liu%2C+and+Rui+Yan%2E+2016%2E+Multi%2Dview+response+selection+for+human%2Dcomputer+conversation%2E+In+EMNLP%2C+pages+372%E2%80%93381%2E)
22. Andreas Stolcke, Klaus Ries, Noah Coccaro, Elizabeth Shriberg, Rebecca Bates, Daniel Jurafsky, Paul Taylor, Rachel Martin, Carol Van Ess-Dykema, and Marie Meteer. 2000. Dialogue act modeling for automatic tagging and recognition of conversational speech. Computational linguistics, 26(3):339–373. [find](https://scholar.google.com/scholar?q=Andreas+Stolcke%2C+Klaus+Ries%2C+Noah+Coccaro%2C+Elizabeth+Shriberg%2C+Rebecca+Bates%2C+Daniel+Jurafsky%2C+Paul+Taylor%2C+Rachel+Martin%2C+Carol+Van+Ess%2DDykema%2C+and+Marie+Meteer%2E+2000%2E+Dialogue+act+modeling+for+autom) [our card](https://md.research.elamur.ai/free/en/papers/prag-2000-stolcke-dialogue-act-modeling-automatic-tagging/)
23. David R Traum and Peter A Heeman. 1996. Utterance units in spoken dialogue. In Workshop on Dialogue Processing in Spoken Language Systems, pages 125–140. [find](https://scholar.google.com/scholar?q=David+R+Traum+and+Peter+A+Heeman%2E+1996%2E+Utterance+units+in+spoken+dialogue%2E+In+Workshop+on+Dialogue+Processing+in+Spoken+Language+Systems%2C+pages+125%E2%80%93140%2E)
24. Alan M Turing. 1950. Computing machinery and intelligence. Mind, 59(236):433–460. [find](https://scholar.google.com/scholar?q=Alan+M+Turing%2E+1950%2E+Computing+machinery+and+intelligence%2E+Mind%2C+59%28236%29%3A433%E2%80%93460%2E)
25. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems, pages 6000–6010. [find](https://scholar.google.com/scholar?q=Ashish+Vaswani%2C+Noam+Shazeer%2C+Niki+Parmar%2C+Jakob+Uszkoreit%2C+Llion+Jones%2C+Aidan+N+Gomez%2C+%C5%81ukasz+Kaiser%2C+and+Illia+Polosukhin%2E+2017%2E+Attention+is+all+you+need%2E+In+Advances+in+Neural+Information+Processi)
26. Ellen M Voorhees et al. 1999. The trec-8 question answering track report. In Trec, pages 77–82. [find](https://scholar.google.com/scholar?q=Ellen+M+Voorhees+et+al%2E+1999%2E+The+trec%2D8+question+answering+track+report%2E+In+Trec%2C+pages+77%E2%80%9382%2E) [our card](https://md.research.elamur.ai/free/en/papers/voorhees-2000-trec-8-question-answering-track/)
27. Hao Wang, Zhengdong Lu, Hang Li, and Enhong Chen. 2013. A dataset for research on short-text conversations. In EMNLP, pages 935–945. [find](https://scholar.google.com/scholar?q=Hao+Wang%2C+Zhengdong+Lu%2C+Hang+Li%2C+and+Enhong+Chen%2E+2013%2E+A+dataset+for+research+on+short%2Dtext+conversations%2E+In+EMNLP%2C+pages+935%E2%80%93945%2E)
28. Mingxuan Wang, Zhengdong Lu, Hang Li, and Qun Liu. 2015. Syntax-based deep matching of short texts. International Joint Conferences on Artificial Intelligence. [find](https://scholar.google.com/scholar?q=Mingxuan+Wang%2C+Zhengdong+Lu%2C+Hang+Li%2C+and+Qun+Liu%2E+2015%2E+Syntax%2Dbased+deep+matching+of+short+texts%2E+International+Joint+Conferences+on+Artificial+Intelligence%2E)
29. Shuohang Wang and Jing Jiang. 2017. Machine comprehension using match-lstm and answer pointer. international conference on learning representations. [find](https://scholar.google.com/scholar?q=Shuohang+Wang+and+Jing+Jiang%2E+2017%2E+Machine+comprehension+using+match%2Dlstm+and+answer+pointer%2E+international+conference+on+learning+representations%2E) [our card](https://md.research.elamur.ai/free/en/papers/wang-2016-machine-comprehension-using-match-lstm/)
30. Yu Wu, Wei Wu, Ming Zhou, and Zhoujun Li. 2017. Sequential match network: A new architecture for multi-turn response selection in retrieval-based chatbots. In ACL, pages 372–381. [find](https://scholar.google.com/scholar?q=Yu+Wu%2C+Wei+Wu%2C+Ming+Zhou%2C+and+Zhoujun+Li%2E+2017%2E+Sequential+match+network%3A+A+new+architecture+for+multi%2Dturn+response+selection+in+retrieval%2Dbased+chatbots%2E+In+ACL%2C+pages+372%E2%80%93381%2E)
31. Kelvin Xu, Jimmy Ba, Ryan Kiros, Kyunghyun Cho, Aaron Courville, Ruslan Salakhudinov, Rich Zemel, and Yoshua Bengio. 2015. Show, attend and tell: Neural image caption generation with visual attention. In International Conference on Machine Learning, pages 2048–2057. [find](https://scholar.google.com/scholar?q=Kelvin+Xu%2C+Jimmy+Ba%2C+Ryan+Kiros%2C+Kyunghyun+Cho%2C+Aaron+Courville%2C+Ruslan+Salakhudinov%2C+Rich+Zemel%2C+and+Yoshua+Bengio%2E+2015%2E+Show%2C+attend+and+tell%3A+Neural+image+caption+generation+with+visual+attention%2E) [our card](https://md.research.elamur.ai/free/en/papers/xu-2015-show-attend-tell-neural-image/)