--- title: "A Neural Conversational Model — Vinyals 2015" description: "Before this work, conversational agents were usually limited to narrow domains and depended on hand-built rules and multi-stage pipelines." authors: ["Oriol Vinyals", "Quoc Le"] year: 2015 venue: "arXiv:1506.05869" source: "https://arxiv.org/abs/1506.05869" doi: "10.48550/arxiv.1506.05869" arxiv: "1506.05869" licence: "arXiv — non-exclusive licence to distribute" licence_url: "http://arxiv.org/licenses/nonexclusive-distrib/1.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/vinyals-2015-neural-conversational-model/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/vinyals-2015-neural-conversational-model/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2015](https://md.research.elamur.ai/free/en/papers/2015/) / A Neural Conversational Model # A Neural Conversational Model **Authors:** [Oriol Vinyals](https://md.research.elamur.ai/free/en/authors/oriol-vinyals/), [Quoc Le](https://md.research.elamur.ai/free/en/authors/quoc-le/) · **Year:** 2015 · **Venue:** arXiv:1506.05869 · **Licence:** [arXiv — non-exclusive licence to distribute](http://arxiv.org/licenses/nonexclusive-distrib/1.0/) **Links:** [Publisher's page](https://arxiv.org/abs/1506.05869) · [PDF](https://arxiv.org/pdf/1506.05869) · [DOI 10.48550/arxiv.1506.05869](https://doi.org/10.48550/arxiv.1506.05869) · [arXiv 1506.05869](https://arxiv.org/abs/1506.05869) · [OpenAlex](https://openalex.org/W1591706642) **Citations:** 1345 citations (openalex-snapshot · 2026-10-14) · [414](#cited-by) in our library, of the 140884 papers whose bibliographies we read ## Summary Before this work, conversational agents were usually limited to narrow domains and depended on hand-built rules and multi-stage pipelines. Vinyals and Le test whether a generic sequence-to-sequence (seq2seq) LSTM, trained end-to-end without rules, can learn to hold a dialogue. They treat conversation as predicting the next utterance. The model encodes the preceding context and then generates the reply one token at a time. It is trained with cross-entropy, and replies are produced with greedy decoding or beam search. They use two corpora: a closed-domain IT helpdesk troubleshooting chat log and the large, noisy, open-domain OpenSubtitles collection of movie dialogue. On both, the network reaches lower perplexity than an n-gram baseline. On helpdesk data it sometimes guides a user to a working fix. On subtitles it answers factual, philosophical and common-sense questions, many of which never appear in training. Human judges preferred it to the rule-based CleverBot more often than the reverse. Its main weaknesses are short, generic answers and no consistent persona. The paper became a foundational baseline for neural dialogue generation. ## Key points - **IT helpdesk:** about 30M training tokens and 3M validation tokens. The model is a single-layer LSTM with 1024 cells and a 20K-word vocabulary. It reaches perplexity 8, compared with 18 for the n-gram model. - **OpenSubtitles (Tiedemann, 2009):** 62M training sentences (923M tokens) and 26M validation sentences (395M tokens). Because the subtitles don't mark speakers, each pair of consecutive sentences is treated as a turn between two people. - **Human evaluation:** 200 questions, each judged by four raters, counted only when at least three of them agreed. NCM won 97, CleverBot won 60, 20 were ties and 23 had no agreement. - **Known failure:** paraphrased questions can get contradictory answers. For example, the model says it is a lawyer in one reply and a doctor in the next. - **Open problem:** the authors say there is still no good automatic metric for dialogue quality. Perplexity and human judgments both have clear limitations. *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: [Other](https://md.research.elamur.ai/free/en/shelves/other/) ## Cited by Cited by 414 papers of our library cite it (of the 140884 whose bibliographies we read); 38 of them have a page here, 376 not yet. - [Towards a Human-like Open-Domain Chatbot](https://md.research.elamur.ai/free/en/papers/adiwardana-2020-towards-human-like-open-domain/) - [Massive Exploration of Neural Machine Translation Architectures](https://md.research.elamur.ai/free/en/papers/britz-2017-massive-exploration-neural-machine-translation/) - [Taskmaster-1: Toward a Realistic and Diverse Dialog Dataset](https://md.research.elamur.ai/free/en/papers/byrne-2019-taskmaster-1-realistic-diverse-dialog/) - [The Second Conversational Intelligence Challenge (ConvAI2)](https://md.research.elamur.ai/free/en/papers/dinan-2019-second-conversational-intelligence-challenge-convai2/) - [Incorporating Copying Mechanism in Sequence-to-Sequence Learning](https://md.research.elamur.ai/free/en/papers/gu-2016-incorporating-copying-mechanism-sequence-sequence/) - [Survey of Hallucination in Natural Language Generation](https://md.research.elamur.ai/free/en/papers/ji-2022-survey-hallucination-natural-language-generation/) - [Modeling Speech Acts in Asynchronous Conversations: A Neural-CRF Approach](https://md.research.elamur.ai/free/en/papers/joty-2018-modeling-speech-acts-asynchronous-conversations/) - [OpenNMT: Open-Source Toolkit for Neural Machine Translation](https://md.research.elamur.ai/free/en/papers/klein-2017-opennmt-open-source-toolkit-neural/) - [Syntax-Guided Controlled Generation of Paraphrases](https://md.research.elamur.ai/free/en/papers/kumar-2020-syntax-guided-controlled-generation-paraphrases/) - [Multi-Relational Question Answering from Narratives: Machine Reading and Reasoning in Simulated Worlds](https://md.research.elamur.ai/free/en/papers/labutov-2018-multi-relational-question-answering-narratives/) - [Deal or No Deal? End-to-End Learning of Negotiation Dialogues](https://md.research.elamur.ai/free/en/papers/lewis-2017-deal-or-no-deal-end/) - [Deep Reinforcement Learning for Dialogue Generation](https://md.research.elamur.ai/free/en/papers/li-2016-deep-reinforcement-learning-dialogue-generation/) - [A Diversity-Promoting Objective Function for Neural Conversation Models](https://md.research.elamur.ai/free/en/papers/li-2016-diversity-promoting-objective-function-neural/) - [A Persona-Based Neural Conversation Model](https://md.research.elamur.ai/free/en/papers/li-2016-persona-based-neural-conversation-model/) - [Visualizing and Understanding Neural Models in NLP](https://md.research.elamur.ai/free/en/papers/li-2016-visualizing-understanding-neural-models-nlp/) - [Adversarial Learning for Neural Dialogue Generation](https://md.research.elamur.ai/free/en/papers/li-2017-adversarial-learning-neural-dialogue-generation/) - [Paraphrase Generation with Deep Reinforcement Learning](https://md.research.elamur.ai/free/en/papers/li-2018-paraphrase-generation-deep-reinforcement-learning/) - [MoEL: Mixture of Empathetic Listeners](https://md.research.elamur.ai/free/en/papers/lin-2019-moel-mixture-empathetic-listeners/) - [LLM-Eval: Unified Multi-Dimensional Automatic Evaluation for Open-Domain Conversations with Large Language Models](https://md.research.elamur.ai/free/en/papers/lin-2023-llm-eval-unified-multi-dimensional/) - [OpenSubtitles2018: Statistical Rescoring of Sentence Alignments in Large, Noisy Parallel Corpora](https://md.research.elamur.ai/free/en/papers/lison-2018-opensubtitles2018-statistical-rescoring-sentence-alignments/) - [Towards an Automatic Turing Test: Learning to Evaluate Dialogue Responses](https://md.research.elamur.ai/free/en/papers/lowe-2017-towards-automatic-turing-test-learning/) - [MIME: MIMicking Emotions for Empathetic Response Generation](https://md.research.elamur.ai/free/en/papers/majumder-2020-mime-mimicking-emotions-empathetic-response/) - [Towards Exploiting Background Knowledge for Building Conversation Systems](https://md.research.elamur.ai/free/en/papers/moghe-2018-exploiting-background-knowledge-building-conversation/) - [The LAMBADA dataset: Word prediction requiring a broad discourse context](https://md.research.elamur.ai/free/en/papers/paperno-2016-lambada-dataset-word-prediction-requiring/) - [ToTTo: A Controlled Table-To-Text Generation Dataset](https://md.research.elamur.ai/free/en/papers/parikh-2020-totto-controlled-table-text-generation/) - [Style Transfer Through Back-Translation](https://md.research.elamur.ai/free/en/papers/prabhumoye-2018-style-transfer-through-back-translation/) - [GECOR: An End-to-End Generative Ellipsis and Co-reference Resolution Model for Task-Oriented Dialogue](https://md.research.elamur.ai/free/en/papers/quan-2019-gecor-end-end-generative-ellipsis/) - [What makes a good conversation? How controllable attributes affect human judgments](https://md.research.elamur.ai/free/en/papers/see-2019-what-makes-good-conversation-how/) - [Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models](https://md.research.elamur.ai/free/en/papers/serban-2015-building-end-end-dialogue-systems/) - [MASS: Masked Sequence to Sequence Pre-training for Language Generation](https://md.research.elamur.ai/free/en/papers/song-2019-mass-masked-sequence-sequence-pre/) - [LaMDA: Language Models for Dialog Applications](https://md.research.elamur.ai/free/en/papers/thoppilan-2022-lamda-language-models-dialog-applications/) - [Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models](https://md.research.elamur.ai/free/en/papers/vijayakumar-2016-diverse-beam-search-decoding-diverse/) - [Exploiting Cross-Sentence Context for Neural Machine Translation](https://md.research.elamur.ai/free/en/papers/wang-2017-exploiting-cross-sentence-context-neural/) - [Dialogue Natural Language Inference](https://md.research.elamur.ai/free/en/papers/welleck-2019-dialogue-natural-language-inference/) - [The Rise and Potential of Large Language Model Based Agents: A Survey](https://md.research.elamur.ai/free/en/papers/xi-2023-rise-potential-large-language/) - [Unsupervised Text Style Transfer using Language Models as Discriminators](https://md.research.elamur.ai/free/en/papers/yang-2018-unsupervised-text-style-transfer-using/) - [Personalizing Dialogue Agents: I have a dog, do you have pets too?](https://md.research.elamur.ai/free/en/papers/zhang-2018-personalizing-dialogue-agents-i-have/) - [Knowledge-Grounded Dialogue Generation with Pre-trained Language Models](https://md.research.elamur.ai/free/en/papers/zhao-2020-knowledge-grounded-dialogue-generation-pre/) ## Cite The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @misc{vinyals2015neural, title = {{A Neural Conversational Model}}, author = {Vinyals, Oriol and Le, Quoc}, year = {2015}, doi = {10.48550/arxiv.1506.05869}, eprint = {1506.05869}, archivePrefix = {arXiv}, url = {https://doi.org/10.48550/arxiv.1506.05869} } ``` - [← previous A Joint Framework for Coreference Resolution and Mention Head Detection](https://md.research.elamur.ai/free/en/papers/peng-2015-joint-framework-coreference-resolution-mention/) - [next → A Neural Network Approach to Context-Sensitive Generation of Conversational Responses](https://md.research.elamur.ai/free/en/papers/sordoni-2015-neural-network-approach-context-sensitive/) - [↑ back to papers of 2015](https://md.research.elamur.ai/free/en/papers/2015/) ## References 18 references, 7 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Bahdanau, D., Cho, K., and Bengio, Y. Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473, 2014. [find](https://scholar.google.com/scholar?q=Bahdanau%2C+D%2E%2C+Cho%2C+K%2E%2C+and+Bengio%2C+Y%2E+Neural+machine+translation+by+jointly+learning+to+align+and+translate%2E+arXiv+preprint+arXiv%3A1409%2E0473%2C+2014%2E) [our card](https://md.research.elamur.ai/free/en/papers/bahdanau-2014-neural-machine-translation-jointly-learning/) 2. Bengio, Y., Ducharme, R., Vincent, P., and Janvin, C. A neural probabilistic language model. The Journal of Machine Learning Research, 3:1137–1155, 2003. [find](https://scholar.google.com/scholar?q=Bengio%2C+Y%2E%2C+Ducharme%2C+R%2E%2C+Vincent%2C+P%2E%2C+and+Janvin%2C+C%2E+A+neural+probabilistic+language+model%2E+The+Journal+of+Machine+Learning+Research%2C+3%3A1137%E2%80%931155%2C+2003%2E) 3. Hochreiter, S. and Schmidhuber, J. Long short-term memory. Neural Computation, 1997. [find](https://scholar.google.com/scholar?q=Hochreiter%2C+S%2E+and+Schmidhuber%2C+J%2E+Long+short%2Dterm+memory%2E+Neural+Computation%2C+1997%2E) 4. Jean, S., Cho, K., Memisevic, R., and Bengio, Y. On using very large target vocabulary for neural machine translation. CoRR, abs/1412.2007, 2014. [find](https://scholar.google.com/scholar?q=Jean%2C+S%2E%2C+Cho%2C+K%2E%2C+Memisevic%2C+R%2E%2C+and+Bengio%2C+Y%2E+On+using+very+large+target+vocabulary+for+neural+machine+translation%2E+CoRR%2C+abs%2F1412%2E2007%2C+2014%2E) [our card](https://md.research.elamur.ai/free/en/papers/jean-2015-very-large-target-vocabulary-neural/) 5. Jurafsky, D. and Martin, J. Speech and language processing. Pearson International, 2009. [find](https://scholar.google.com/scholar?q=Jurafsky%2C+D%2E+and+Martin%2C+J%2E+Speech+and+language+processing%2E+Pearson+International%2C+2009%2E) 6. Kalchbrenner, N. and Blunsom, P. Recurrent continuous translation models. In EMNLP, 2013. [find](https://scholar.google.com/scholar?q=Kalchbrenner%2C+N%2E+and+Blunsom%2C+P%2E+Recurrent+continuous+translation+models%2E+In+EMNLP%2C+2013%2E) [our card](https://md.research.elamur.ai/free/en/papers/kalchbrenner-2013-recurrent-continuous-translation-models/) 7. Lester, J., Branting, K., and Mott, B. Conversational agents. In Handbook of Internet Computing. Chapman & Hall, 2004. [find](https://scholar.google.com/scholar?q=Lester%2C+J%2E%2C+Branting%2C+K%2E%2C+and+Mott%2C+B%2E+Conversational+agents%2E+In+Handbook+of+Internet+Computing%2E+Chapman+%26+Hall%2C+2004%2E) 8. Luong, T., Sutskever, I., Le, Q. V., Vinyals, O., and Zaremba, W. Addressing the rare word problem in neural machine translation. arXiv preprint arXiv:1410.8206, 2014. [find](https://scholar.google.com/scholar?q=Luong%2C+T%2E%2C+Sutskever%2C+I%2E%2C+Le%2C+Q%2E+V%2E%2C+Vinyals%2C+O%2E%2C+and+Zaremba%2C+W%2E+Addressing+the+rare+word+problem+in+neural+machine+translation%2E+arXiv+preprint+arXiv%3A1410%2E8206%2C+2014%2E) [our card](https://md.research.elamur.ai/free/en/papers/luong-2015-addressing-rare-word-problem-neural/) 9. Mikolov, T. Statistical Language Models based on Neural Networks. PhD thesis, Brno University of Technology, 2012. [find](https://scholar.google.com/scholar?q=Mikolov%2C+T%2E+Statistical+Language+Models+based+on+Neural+Networks%2E+PhD+thesis%2C+Brno+University+of+Technology%2C+2012%2E) 10. Mikolov, T., Karafiát, M., Burget, L., Cernockỳ, J., and Khudanpur, S. Recurrent neural network based language model. In INTERSPEECH, pp. 1045–1048, 2010. [find](https://scholar.google.com/scholar?q=Mikolov%2C+T%2E%2C+Karafia%CC%81t%2C+M%2E%2C+Burget%2C+L%2E%2C+Cernocky%CC%80%2C+J%2E%2C+and+Khudanpur%2C+S%2E+Recurrent+neural+network+based+language+model%2E+In+INTERSPEECH%2C+pp%2E+1045%E2%80%931048%2C+2010%2E) 11. Shang, L., Lu, Z., and Li, H. Neural responding machine for short-text conversation. In Proceedings of ACL, 2015. [find](https://scholar.google.com/scholar?q=Shang%2C+L%2E%2C+Lu%2C+Z%2E%2C+and+Li%2C+H%2E+Neural+responding+machine+for+short%2Dtext+conversation%2E+In+Proceedings+of+ACL%2C+2015%2E) [our card](https://md.research.elamur.ai/free/en/papers/shang-2015-neural-responding-machine-short-text/) 12. Sordoni, A., Galley, M., Auli, M., Brockett, C., Ji, Y., Mitchell, M., Gao, J., Dolan, B., and Nie, J.-Y. A neural network approach to context-sensitive generation of conversational responses. In Proceedings of NAACL, 2015. [find](https://scholar.google.com/scholar?q=Sordoni%2C+A%2E%2C+Galley%2C+M%2E%2C+Auli%2C+M%2E%2C+Brockett%2C+C%2E%2C+Ji%2C+Y%2E%2C+Mitchell%2C+M%2E%2C+Gao%2C+J%2E%2C+Dolan%2C+B%2E%2C+and+Nie%2C+J%2E%2DY%2E+A+neural+network+approach+to+context%2Dsensitive+generation+of+conversational+responses%2E+In+Proc) [our card](https://md.research.elamur.ai/free/en/papers/sordoni-2015-neural-network-approach-context-sensitive/) 13. Sutskever, I., Vinyals, O., and Le, Q. V. Sequence to sequence learning with neural networks. In NIPS, 2014. [find](https://scholar.google.com/scholar?q=Sutskever%2C+I%2E%2C+Vinyals%2C+O%2E%2C+and+Le%2C+Q%2E+V%2E+Sequence+to+sequence+learning+with+neural+networks%2E+In+NIPS%2C+2014%2E) 14. Tiedemann, J. News from OPUS - A collection of multilingual parallel corpora with tools and interfaces. In Nicolov, N., Bontcheva, K., Angelova, G., and Mitkov, R. (eds.), Recent Advances in Natural Language Processing, volume V, pp. 237–248. John Benjamins, Amsterdam/Philadelphia, Borovets, Bulgari… [find](https://scholar.google.com/scholar?q=Tiedemann%2C+J%2E+News+from+OPUS+%2D+A+collection+of+multilingual+parallel+corpora+with+tools+and+interfaces%2E+In+Nicolov%2C+N%2E%2C+Bontcheva%2C+K%2E%2C+Angelova%2C+G%2E%2C+and+Mitkov%2C+R%2E+%28eds%2E%29%2C+Recent+Advances+in+Natural+L) 15. Turing, A. M. Computing machinery and intelligence. Mind, pp. 433–460, 1950. [find](https://scholar.google.com/scholar?q=Turing%2C+A%2E+M%2E+Computing+machinery+and+intelligence%2E+Mind%2C+pp%2E+433%E2%80%93460%2C+1950%2E) 16. Vinyals, O., Kaiser, L., Koo, T., Petrov, S., Sutskever, I., and Hinton, G. Grammar as a foreign language. arXiv preprint arXiv:1412.7449, 2014a. [find](https://scholar.google.com/scholar?q=Vinyals%2C+O%2E%2C+Kaiser%2C+L%2E%2C+Koo%2C+T%2E%2C+Petrov%2C+S%2E%2C+Sutskever%2C+I%2E%2C+and+Hinton%2C+G%2E+Grammar+as+a+foreign+language%2E+arXiv+preprint+arXiv%3A1412%2E7449%2C+2014a%2E) 17. Vinyals, O., Toshev, A., Bengio, S., and Erhan, D. Show and tell: A neural image caption generator. arXiv preprint arXiv:1411.4555, 2014b. [find](https://scholar.google.com/scholar?q=Vinyals%2C+O%2E%2C+Toshev%2C+A%2E%2C+Bengio%2C+S%2E%2C+and+Erhan%2C+D%2E+Show+and+tell%3A+A+neural+image+caption+generator%2E+arXiv+preprint+arXiv%3A1411%2E4555%2C+2014b%2E) [our card](https://md.research.elamur.ai/free/en/papers/vinyals-2014-show-tell-neural-image-caption/) 18. Will, T. Creating a Dynamic Speech Dialogue. VDM Verlag Dr, 2007. [find](https://scholar.google.com/scholar?q=Will%2C+T%2E+Creating+a+Dynamic+Speech+Dialogue%2E+VDM+Verlag+Dr%2C+2007%2E)