--- title: "The Ubuntu Dialogue Corpus — Lowe 2015" description: "Neural dialogue systems have advanced more slowly than vision or speech systems." authors: ["Ryan Lowe", "Nissan Pow", "Iulian Serban", "Joelle Pineau"] year: 2015 venue: "arXiv:1506.08909" source: "https://arxiv.org/abs/1506.08909" doi: "10.48550/arxiv.1506.08909" arxiv: "1506.08909" 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/lowe-2015-ubuntu-dialogue-corpus-large-dataset/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/lowe-2015-ubuntu-dialogue-corpus-large-dataset/) [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/page/2/) / The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systems # The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systems **Authors:** [Ryan Lowe](https://md.research.elamur.ai/free/en/authors/ryan-lowe/), Nissan Pow, [Iulian Serban](https://md.research.elamur.ai/free/en/authors/iulian-serban/), [Joelle Pineau](https://md.research.elamur.ai/free/en/authors/joelle-pineau/) · **Year:** 2015 · **Venue:** arXiv:1506.08909 · **Licence:** [arXiv — non-exclusive licence to distribute](http://arxiv.org/licenses/nonexclusive-distrib/1.0/) **Links:** [Publisher's page](https://arxiv.org/abs/1506.08909) · [PDF](https://arxiv.org/pdf/1506.08909) · [DOI 10.48550/arxiv.1506.08909](https://doi.org/10.48550/arxiv.1506.08909) · [arXiv 1506.08909](https://arxiv.org/abs/1506.08909) · [OpenAlex](https://openalex.org/W836999996) **Citations:** 199 citations (openalex-snapshot · 2026-10-14) · [275](#cited-by) in our library, of the 140673 papers whose bibliographies we read ## Summary Neural dialogue systems have advanced more slowly than vision or speech systems. The authors attribute this mainly to the lack of large public conversational datasets. Slot-filling corpora such as DSTC are small, and Twitter/Weibo collections are mostly unreleased and dominated by very short exchanges. To address this, the authors build the Ubuntu Dialogue Corpus from Ubuntu technical-support channels on the Freenode IRC network. These channels interleave many parallel conversations, so the authors use a heuristic disentanglement step. Each message becomes a (time, sender, recipient, utterance) tuple. Recipients are detected by matching the first word against recently seen usernames while excluding common English words. Two-person dialogues are then reassembled from these tuples. The authors also define a next-response selection task that requires no manual labeling and report TF-IDF, RNN and LSTM baselines, with the LSTM performing best. The corpus matters because it pairs the multi-turn nature of DSTC data with the open-ended style of microblogs, at a scale large enough to train neural models. ## Key points - **Scale:** The corpus contains roughly 930,000 dyadic dialogues, about 7.1 million utterances and around 100 million words. Dialogues average 8 turns, with at least 3 turns each. - **Source:** The data comes from Ubuntu IRC chat logs covering 2004–2015. It differs from the earlier Ubuntu Chat Corpus, which keeps the multi-party structure instead of isolating two-person conversations. - **Task and baselines:** The evaluation task is response selection, where the model ranks the true reply against randomly chosen false candidates (up to 1-in-10) and is scored with Recall@k. The baselines are TF-IDF, an RNN and an LSTM with one hidden layer of 200 units, and the LSTM is significantly better than the others. - **Why selection instead of generation:** The authors argue that BLEU/METEOR-style scoring of generated replies is unreliable for dialogue. Selection difficulty can also be tuned by changing the number of distractors or the value of k. - **Availability:** The code is at github.com/npow/ubottu. An updated, bug-fixed version of the dataset is at github.com/rkadlec/ubuntu-ranking-dataset-creator, and its results should not be compared directly with those on the original dataset. *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 275 papers of our library cite it (of the 140673 whose bibliographies we read); 19 of them have a page here, 256 not yet. - [Exploring the Potential of ChatGPT on Sentence Level Relations: A Focus on Temporal, Causal, and Discourse Relations](https://md.research.elamur.ai/free/en/papers/chan-2024-exploring-potential-chatgpt-sentence-level/) - [CONAN - COunter NArratives through Nichesourcing: a Multilingual Dataset of Responses to Fight Online Hate Speech](https://md.research.elamur.ai/free/en/papers/chung-2019-conan-counter-narratives-through-nichesourcing/) - [A Distance-Aware Multi-Task Framework for Conversational Discourse Parsing](https://md.research.elamur.ai/free/en/papers/fan-2022-distance-aware-multi-task-framework/) - [Findings of the WMT 2020 Shared Task on Chat Translation](https://md.research.elamur.ai/free/en/papers/farajian-2020-findings-wmt-2020-shared-task/) - [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/) - [DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset](https://md.research.elamur.ai/free/en/papers/li-2017-dailydialog-manually-labelled-multi-turn/) - [Task-Aware Self-Supervised Framework for Dialogue Discourse Parsing](https://md.research.elamur.ai/free/en/papers/li-2023-task-aware-self-supervised-framework/) - [Dialogue Discourse Parsing as Generation: A Sequence-to-Sequence LLM-based Approach](https://md.research.elamur.ai/free/en/papers/li-2024-dialogue-discourse-parsing-as-generation/) - [Discourse Relation Prediction and Discourse Parsing in Dialogues with Minimal Supervision](https://md.research.elamur.ai/free/en/papers/li-2024-discourse-relation-prediction-discourse-parsing/) - [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/) - [Generation-Augmented Retrieval for Open-domain Question Answering](https://md.research.elamur.ai/free/en/papers/mao-2020-generation-augmented-retrieval-open-domain/) - [USR: An Unsupervised and Reference Free Evaluation Metric for Dialog Generation](https://md.research.elamur.ai/free/en/papers/mehri-2020-usr-unsupervised-reference-free-evaluation/) - [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/) - [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/) - [A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues](https://md.research.elamur.ai/free/en/papers/serban-2016-hierarchical-latent-variable-encoder-decoder/) - [Speaker-Aware Discourse Parsing on Multi-Party Dialogues](https://md.research.elamur.ai/free/en/papers/yu-2022-speaker-aware-discourse-parsing-multi/) - [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/) - [GRICE: A Grammar-based Dataset for Recovering Implicature and Conversational rEasoning](https://md.research.elamur.ai/free/en/papers/zheng-2021-grice-grammar-based-dataset-recovering/) - [LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset](https://md.research.elamur.ai/free/en/papers/zheng-2023-lmsys-chat-1m-large-scale/) ## Cite The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @misc{lowe2015ubuntu, title = {{The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systems}}, author = {Lowe, Ryan and Pow, Nissan and Serban, Iulian and Pineau, Joelle}, year = {2015}, doi = {10.48550/arxiv.1506.08909}, eprint = {1506.08909}, archivePrefix = {arXiv}, url = {https://doi.org/10.48550/arxiv.1506.08909} } ``` - [← previous The Translation of Quotative Frames in the Hebrew Bible](https://md.research.elamur.ai/free/en/papers/miller-2026-naude-translation-quotative-frames-hebrew-bible/) - [next → The UniTN Discourse Parser in CoNLL 2015 Shared Task: Token-level Sequence Labeling with Argument-specific Models](https://md.research.elamur.ai/free/en/papers/stepanov-2015-unitn-discourse-parser-conll-2015/) - [↑ back to papers of 2015](https://md.research.elamur.ai/free/en/papers/2015/page/2/) ## References 33 references, 6 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Y. Bengio, A. Courville, and P. Vincent. Representation learning: A review and new perspectives. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 35(8):1798–1828, 2013. [find](https://scholar.google.com/scholar?q=Y%2E+Bengio%2C+A%2E+Courville%2C+and+P%2E+Vincent%2E+Representation+learning%3A+A+review+and+new+perspectives%2E+Pattern+Analysis+and+Machine+Intelligence%2C+IEEE+Transactions+on%2C+35%288%29%3A1798%E2%80%931828%2C+2013%2E) [our card](https://md.research.elamur.ai/free/en/papers/bengio-2012-representation-learning-review-new-perspectives/) 2. A. Bordes, J. Weston, and N. Usunier. Open question answering with weakly supervised embedding models. In MLKDD, pages 165– 180. Springer, 2014. [find](https://scholar.google.com/scholar?q=A%2E+Bordes%2C+J%2E+Weston%2C+and+N%2E+Usunier%2E+Open+question+answering+with+weakly+supervised+embedding+models%2E+In+MLKDD%2C+pages+165%E2%80%93+180%2E+Springer%2C+2014%2E) 3. J. Boyd-Graber, B. Satinoff, H. He, and H. Daume. Besting the quiz master: Crowdsourcing incremental classification games. In EMNLP, 2012. [find](https://scholar.google.com/scholar?q=J%2E+Boyd%2DGraber%2C+B%2E+Satinoff%2C+H%2E+He%2C+and+H%2E+Daume%2E+Besting+the+quiz+master%3A+Crowdsourcing+incremental+classification+games%2E+In+EMNLP%2C+2012%2E) 4. K. Cho, B. van Merrienboer, C. Gulcehre, F. Bougares, H. Schwenk, and Y. Bengio. Learning phrase representations using rnn encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078, 2014. [find](https://scholar.google.com/scholar?q=K%2E+Cho%2C+B%2E+van+Merrienboer%2C+C%2E+Gulcehre%2C+F%2E+Bougares%2C+H%2E+Schwenk%2C+and+Y%2E+Bengio%2E+Learning+phrase+representations+using+rnn+encoder%2Ddecoder+for+statistical+machine+translation%2E+arXiv+preprint+arXiv%3A140) 5. J. Deng, W. Dong, R. Socher, L.J. Li, K. Li, and L. Fei-Fei. Imagenet: A large-scale hierarchical image database. In CVPR, 2009. [find](https://scholar.google.com/scholar?q=J%2E+Deng%2C+W%2E+Dong%2C+R%2E+Socher%2C+L%2EJ%2E+Li%2C+K%2E+Li%2C+and+L%2E+Fei%2DFei%2E+Imagenet%3A+A+large%2Dscale+hierarchical+image+database%2E+In+CVPR%2C+2009%2E) 6. M. Elsner and E. Charniak. You talking to me? a corpus and algorithm for conversation disentanglement. In ACL, pages 834– 842, 2008. [find](https://scholar.google.com/scholar?q=M%2E+Elsner+and+E%2E+Charniak%2E+You+talking+to+me%3F+a+corpus+and+algorithm+for+conversation+disentanglement%2E+In+ACL%2C+pages+834%E2%80%93+842%2C+2008%2E) 7. M. Galley, C. Brockett, A. Sordoni, Y. Ji, M. Auli, C. Quirk, M. Mitchell, J. Gao, and B. Dolan. deltableu: A discriminative metric for generation tasks with intrinsically diverse targets. arXiv preprint arXiv:1506.06863, 2015. [find](https://scholar.google.com/scholar?q=M%2E+Galley%2C+C%2E+Brockett%2C+A%2E+Sordoni%2C+Y%2E+Ji%2C+M%2E+Auli%2C+C%2E+Quirk%2C+M%2E+Mitchell%2C+J%2E+Gao%2C+and+B%2E+Dolan%2E+deltableu%3A+A+discriminative+metric+for+generation+tasks+with+intrinsically+diverse+targets%2E+arXiv+prepr) 8. J.J. Godfrey, E.C. Holliman, and J. Mc-Daniel. Switchboard: Telephone speech corpus for research and development. In ICASSP, 1992. [find](https://scholar.google.com/scholar?q=J%2EJ%2E+Godfrey%2C+E%2EC%2E+Holliman%2C+and+J%2E+Mc%2DDaniel%2E+Switchboard%3A+Telephone+speech+corpus+for+research+and+development%2E+In+ICASSP%2C+1992%2E) 9. M. Henderson, B. Thomson, and J. Williams. Dialog state tracking challenge 2 & 3, 2014. [find](https://scholar.google.com/scholar?q=M%2E+Henderson%2C+B%2E+Thomson%2C+and+J%2E+Williams%2E+Dialog+state+tracking+challenge+2+%26+3%2C+2014%2E) 10. M. Henderson, B. Thomson, and J. Williams. The second dialog state tracking challenge. In SIGDIAL, page 263, 2014. [find](https://scholar.google.com/scholar?q=M%2E+Henderson%2C+B%2E+Thomson%2C+and+J%2E+Williams%2E+The+second+dialog+state+tracking+challenge%2E+In+SIGDIAL%2C+page+263%2C+2014%2E) 11. M. Henderson, B. Thomson, and S. Young. Word-based dialog state tracking with recurrent neural networks. In SIGDIAL, page 292, 2014. [find](https://scholar.google.com/scholar?q=M%2E+Henderson%2C+B%2E+Thomson%2C+and+S%2E+Young%2E+Word%2Dbased+dialog+state+tracking+with+recurrent+neural+networks%2E+In+SIGDIAL%2C+page+292%2C+2014%2E) [our card](https://md.research.elamur.ai/free/en/papers/henderson-2014-word-based-dialog-state-tracking/) 12. S. Hochreiter and J. Schmidhuber. Long short-term memory. Neural computation, 9(8):1735–1780, 1997. [find](https://scholar.google.com/scholar?q=S%2E+Hochreiter+and+J%2E+Schmidhuber%2E+Long+short%2Dterm+memory%2E+Neural+computation%2C+9%288%29%3A1735%E2%80%931780%2C+1997%2E) 13. S. Jafarpour, C. Burges, and A. Ritter. Filter, rank, and transfer the knowledge: Learning to chat. Advances in Ranking, 10, 2010. [find](https://scholar.google.com/scholar?q=S%2E+Jafarpour%2C+C%2E+Burges%2C+and+A%2E+Ritter%2E+Filter%2C+rank%2C+and+transfer+the+knowledge%3A+Learning+to+chat%2E+Advances+in+Ranking%2C+10%2C+2010%2E) 14. D.P. Kingma and J. Ba. Adam: A method for stochastic optimization. CoRR, abs/1412.6980, 2014. [find](https://scholar.google.com/scholar?q=D%2EP%2E+Kingma+and+J%2E+Ba%2E+Adam%3A+A+method+for+stochastic+optimization%2E+CoRR%2C+abs%2F1412%2E6980%2C+2014%2E) 15. A. Lavie and M.J. Denkowski. The ME-TEOR metric for automatic evaluation of Machine Translation. Machine Translation, 23(2-3):105–115, 2009. [find](https://scholar.google.com/scholar?q=A%2E+Lavie+and+M%2EJ%2E+Denkowski%2E+The+ME%2DTEOR+metric+for+automatic+evaluation+of+Machine+Translation%2E+Machine+Translation%2C+23%282%2D3%29%3A105%E2%80%93115%2C+2009%2E) 16. L.R. Medsker and L.C. Jain. Recurrent neural networks. Design and Applications, 2001. [find](https://scholar.google.com/scholar?q=L%2ER%2E+Medsker+and+L%2EC%2E+Jain%2E+Recurrent+neural+networks%2E+Design+and+Applications%2C+2001%2E) 17. K. Papineni, S. Roukos, T. Ward, and W.J. Zhu. Bleu: a method for automatic evaluation of machine translation. In ACL, 2002. [find](https://scholar.google.com/scholar?q=K%2E+Papineni%2C+S%2E+Roukos%2C+T%2E+Ward%2C+and+W%2EJ%2E+Zhu%2E+Bleu%3A+a+method+for+automatic+evaluation+of+machine+translation%2E+In+ACL%2C+2002%2E) [our card](https://md.research.elamur.ai/free/en/papers/papineni-2002-bleu-method-automatic-evaluation-machine/) 18. J. Pennington, R. Socher, and C.D. Manning. GloVe: Global Vectors for Word Representation. In EMNLP, 2014. [find](https://scholar.google.com/scholar?q=J%2E+Pennington%2C+R%2E+Socher%2C+and+C%2ED%2E+Manning%2E+GloVe%3A+Global+Vectors+for+Word+Representation%2E+In+EMNLP%2C+2014%2E) 19. J. Ramos. Using tf-idf to determine word relevance in document queries. In ICML, 2003. [find](https://scholar.google.com/scholar?q=J%2E+Ramos%2E+Using+tf%2Didf+to+determine+word+relevance+in+document+queries%2E+In+ICML%2C+2003%2E) 20. A. Ritter, C. Cherry, and W. Dolan. Unsupervised modeling of twitter conversations. 2010. [find](https://scholar.google.com/scholar?q=A%2E+Ritter%2C+C%2E+Cherry%2C+and+W%2E+Dolan%2E+Unsupervised+modeling+of+twitter+conversations%2E+2010%2E) 21. A. Ritter, C. Cherry, and W. Dolan. Data-driven response generation in social media. In EMNLP, pages 583–593, 2011. [find](https://scholar.google.com/scholar?q=A%2E+Ritter%2C+C%2E+Cherry%2C+and+W%2E+Dolan%2E+Data%2Ddriven+response+generation+in+social+media%2E+In+EMNLP%2C+pages+583%E2%80%93593%2C+2011%2E) 22. A.M. Saxe, J.L. McClelland, and S. Ganguli. Exact solutions to the nonlinear dynamics of learning in deep linear neural networks. arXiv preprint arXiv:1312.6120, 2013. [find](https://scholar.google.com/scholar?q=A%2EM%2E+Saxe%2C+J%2EL%2E+McClelland%2C+and+S%2E+Ganguli%2E+Exact+solutions+to+the+nonlinear+dynamics+of+learning+in+deep+linear+neural+networks%2E+arXiv+preprint+arXiv%3A1312%2E6120%2C+2013%2E) 23. J. Schatzmann, K. Georgila, and S. Young. Quantitative evaluation of user simulation techniques for spoken dialogue systems. In SIGDIAL, 2005. [find](https://scholar.google.com/scholar?q=J%2E+Schatzmann%2C+K%2E+Georgila%2C+and+S%2E+Young%2E+Quantitative+evaluation+of+user+simulation+techniques+for+spoken+dialogue+systems%2E+In+SIGDIAL%2C+2005%2E) 24. L. Shang, Z. Lu, and H. Li. Neural responding machine for short-text conversation. arXiv preprint arXiv:1503.02364, 2015. [find](https://scholar.google.com/scholar?q=L%2E+Shang%2C+Z%2E+Lu%2C+and+H%2E+Li%2E+Neural+responding+machine+for+short%2Dtext+conversation%2E+arXiv+preprint+arXiv%3A1503%2E02364%2C+2015%2E) [our card](https://md.research.elamur.ai/free/en/papers/shang-2015-neural-responding-machine-short-text/) 25. B. A. Shawar and E. Atwell. Chatbots: are they really useful? In LDV Forum, volume 22, pages 29–49, 2007. [find](https://scholar.google.com/scholar?q=B%2E+A%2E+Shawar+and+E%2E+Atwell%2E+Chatbots%3A+are+they+really+useful%3F+In+LDV+Forum%2C+volume+22%2C+pages+29%E2%80%9349%2C+2007%2E) 26. S. Singh, D. Litman, M. Kearns, and M. Walker. Optimizing dialogue management with reinforcement learning: Experiments with the NJFun system. Journal of Artificial Intelligence Research, 16:105–133, 2002. [find](https://scholar.google.com/scholar?q=S%2E+Singh%2C+D%2E+Litman%2C+M%2E+Kearns%2C+and+M%2E+Walker%2E+Optimizing+dialogue+management+with+reinforcement+learning%3A+Experiments+with+the+NJFun+system%2E+Journal+of+Artificial+Intelligence+Research%2C+16%3A105%E2%80%93133%2C+2) 27. A. Sordoni, M. Galley, M. Auli, C. Brockett, Y. Ji, M. Mitchell, J.Y. Nie, J. Gao, and W. Dolan. A neural network approach to context-sensitive generation of conversational responses. 2015. [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%2EY%2E+Nie%2C+J%2E+Gao%2C+and+W%2E+Dolan%2E+A+neural+network+approach+to+context%2Dsensitive+generation+of+conversational+responses%2E+2015%2E) [our card](https://md.research.elamur.ai/free/en/papers/sordoni-2015-neural-network-approach-context-sensitive/) 28. D.C. Uthus and D.W. Aha. Extending word highlighting in multiparticipant chat. Technical report, DTIC Document, 2013. [find](https://scholar.google.com/scholar?q=D%2EC%2E+Uthus+and+D%2EW%2E+Aha%2E+Extending+word+highlighting+in+multiparticipant+chat%2E+Technical+report%2C+DTIC+Document%2C+2013%2E) 29. D.C. Uthus and D.W Aha. The ubuntu chat corpus for multiparticipant chat analysis. In AAAI Spring Symposium on Analyzing Microtext, pages 99–102, 2013. [find](https://scholar.google.com/scholar?q=D%2EC%2E+Uthus+and+D%2EW+Aha%2E+The+ubuntu+chat+corpus+for+multiparticipant+chat+analysis%2E+In+AAAI+Spring+Symposium+on+Analyzing+Microtext%2C+pages+99%E2%80%93102%2C+2013%2E) 30. H. Wang, Z. Lu, H. Li, and E. Chen. A dataset for research on short-text conversations. In EMNLP, 2013. [find](https://scholar.google.com/scholar?q=H%2E+Wang%2C+Z%2E+Lu%2C+H%2E+Li%2C+and+E%2E+Chen%2E+A+dataset+for+research+on+short%2Dtext+conversations%2E+In+EMNLP%2C+2013%2E) 31. J. Williams, A. Raux, D. Ramachandran, and A. Black. The dialog state tracking challenge. In SIGDIAL, pages 404–413, 2013. [find](https://scholar.google.com/scholar?q=J%2E+Williams%2C+A%2E+Raux%2C+D%2E+Ramachandran%2C+and+A%2E+Black%2E+The+dialog+state+tracking+challenge%2E+In+SIGDIAL%2C+pages+404%E2%80%93413%2C+2013%2E) 32. L. Yu, K. M. Hermann, P. Blunsom, and S. Pulman. Deep learning for answer sentence selection. arXiv preprint arXiv:1412.1632, 2014. — [arXiv:1412.1632](https://arxiv.org/abs/1412.1632) [find](https://scholar.google.com/scholar?q=L%2E+Yu%2C+K%2E+M%2E+Hermann%2C+P%2E+Blunsom%2C+and+S%2E+Pulman%2E+Deep+learning+for+answer+sentence+selection%2E+arXiv+preprint+arXiv%3A1412%2E1632%2C+2014%2E+%E2%80%94+%5BarXiv%3A1412%2E1632%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F1412%2E1632%29) 33. M.D. Zeiler. Adadelta: an adaptive learning rate method. arXiv preprint arXiv:1212.5701, 2012. [find](https://scholar.google.com/scholar?q=M%2ED%2E+Zeiler%2E+Adadelta%3A+an+adaptive+learning+rate+method%2E+arXiv+preprint+arXiv%3A1212%2E5701%2C+2012%2E) [our card](https://md.research.elamur.ai/free/en/papers/zeiler-2012-adadelta-adaptive-learning-rate-method/)