--- title: "Controlling Output Length in Neural — Kikuchi 2016" description: "The paper addresses a gap in neural encoder-decoder summarization: standard models cannot be told how long their output should be." authors: ["Yuta Kikuchi", "Graham Neubig", "Ryohei Sasano", "Hiroya Takamura", "Manabu Okumura"] year: 2016 venue: "Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing" source: "https://aclanthology.org/D16-1140/" doi: "10.18653/v1/d16-1140" 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/kikuchi-2016-controlling-output-length-neural-encoder/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/kikuchi-2016-controlling-output-length-neural-encoder/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2016](https://md.research.elamur.ai/free/en/papers/2016/) / Controlling Output Length in Neural Encoder-Decoders # Controlling Output Length in Neural Encoder-Decoders **Authors:** [Yuta Kikuchi](https://md.research.elamur.ai/free/en/authors/yuta-kikuchi/), [Graham Neubig](https://md.research.elamur.ai/free/en/authors/graham-neubig/), [Ryohei Sasano](https://md.research.elamur.ai/free/en/authors/ryohei-sasano/), Hiroya Takamura, [Manabu Okumura](https://md.research.elamur.ai/free/en/authors/manabu-okumura/) · **Year:** 2016 · **Venue:** Proceedings of the 2016 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/D16-1140/) · [PDF](https://aclanthology.org/D16-1140.pdf) · [DOI 10.18653/v1/d16-1140](https://doi.org/10.18653/v1/d16-1140) · [OpenAlex](https://openalex.org/W2963104691) **Citations:** 216 citations (openalex-snapshot · 2026-10-14) · [107](#cited-by) in our library, of the 140884 papers whose bibliographies we read ## Summary The paper addresses a gap in neural encoder-decoder summarization: standard models cannot be told how long their output should be. Summary length usually depends on the training data. On the Annotated English Gigaword sentence-headline pairs, a baseline produces outputs averaging about 38 bytes, while reference headlines average about 51. Earlier work handled length limits crudely, by blocking the end-of-sentence tag and truncating the result. The authors build an attentional encoder-decoder with a BiLSTM encoder and Luong-style attention. On top of it they compare four length-control strategies. Two act only at decoding time. fixLen suppresses EOS until a target length is reached. fixRng prunes beam hypotheses that end outside a minimum-maximum window. The other two learn length during training. LenEmb feeds the decoder an embedding of the remaining length. LenInit sets the decoder's initial memory cell from the desired length. The learning-based variants produce output lengths that cluster tightly around the requested value. They beat the decoding-based ones for longer targets such as 50 and 75 bytes. On DUC2004 they stay competitive with existing systems in ROUGE. This shows that length control need not hurt summary quality. ## Key points - Training data comes from Annotated English Gigaword, with pairs built as in Rush et al. (2015). Average source first sentence length is 181.87 bytes, average headline length is 51.38 bytes, and their ratio is about 0.30. - Four methods are compared: fixLen, fixRng, LenEmb and LenInit. Length is measured in bytes to match the DUC2004 evaluation, which has a 75-byte limit. - On DUC2004 task-1, LenEmb scores R-1 26.73, R-2 8.40 and R-L 23.88. ABS (Rush et al., 2015) scores 26.55, 7.06 and 22.05. - Length histograms and final beam states show that LenEmb and LenInit keep candidates near the target length. In one 30-byte example, every beam candidate fell between 28 and 32 bytes, while the standard model's beam ranged from 32 to 57 bytes. - The code is released at https://github.com/kiyukuta/lencon. *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 107 papers of our library cite it (of the 140884 whose bibliographies we read); 9 of them have a page here, 98 not yet. - [Plug and Play Language Models: A Simple Approach to Controlled Text Generation](https://md.research.elamur.ai/free/en/papers/dathathri-2019-plug-play-language-models-simple/) - [Queens are Powerful too: Mitigating Gender Bias in Dialogue Generation](https://md.research.elamur.ai/free/en/papers/dinan-2020-queens-are-powerful-too-mitigating/) - [GSum: A General Framework for Guided Neural Abstractive Summarization](https://md.research.elamur.ai/free/en/papers/dou-2021-gsum-general-framework-guided-neural/) - [Controllable Abstractive Summarization](https://md.research.elamur.ai/free/en/papers/fan-2018-controllable-abstractive-summarization/) - [Controlling Linguistic Style Aspects in Neural Language Generation](https://md.research.elamur.ai/free/en/papers/ficler-2017-controlling-linguistic-style-aspects-neural/) - [Abstract Meaning Representation for Multi-Document Summarization](https://md.research.elamur.ai/free/en/papers/liao-2018-abstract-meaning-representation-multi-document/) - [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://md.research.elamur.ai/free/en/papers/liu-2021-pre-train-prompt-predict-systematic/) - [InstructSum: A Benchmark to Evaluate Instruction-Following Capability of Large Language Models in Summarization](https://md.research.elamur.ai/free/en/papers/nishida-2026-instructsum-benchmark-evaluate-instruction-following/) - [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/) ## Cite The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{kikuchi2016controlling, title = {{Controlling Output Length in Neural Encoder-Decoders}}, author = {Kikuchi, Yuta and Neubig, Graham and Sasano, Ryohei and Takamura, Hiroya and Okumura, Manabu}, booktitle = {Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing}, year = {2016}, doi = {10.18653/v1/d16-1140}, url = {https://doi.org/10.18653/v1/d16-1140} } ``` - [← previous context2vec: Learning Generic Context Embedding with Bidirectional LSTM](https://md.research.elamur.ai/free/en/papers/melamud-2016-context2vec-learning-generic-context-embedding/) - [next → Controlling Politeness in Neural Machine Translation via Side Constraints](https://md.research.elamur.ai/free/en/papers/sennrich-2016-controlling-politeness-neural-machine-translation/) - [↑ back to papers of 2016](https://md.research.elamur.ai/free/en/papers/2016/) ## References 40 references, 16 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Ayana, S. Shen, Z. Liu, and M. Sun. 2016. Neural Headline Generation with Minimum Risk Training. CoRR, abs/1604.01904. — [arXiv:1604.01904](https://arxiv.org/abs/1604.01904) [find](https://scholar.google.com/scholar?q=Ayana%2C+S%2E+Shen%2C+Z%2E+Liu%2C+and+M%2E+Sun%2E+2016%2E+Neural+Headline+Generation+with+Minimum+Risk+Training%2E+CoRR%2C+abs%2F1604%2E01904%2E+%E2%80%94+%5BarXiv%3A1604%2E01904%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F1604%2E01904%29) 2. Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2015. Neural machine translation by jointly learning to align and translate. In Proceedings of ICLR15. [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+In+Proceedings+of+ICLR15%2E) [our card](https://md.research.elamur.ai/free/en/papers/bahdanau-2014-neural-machine-translation-jointly-learning/) 3. Michele Banko, Vibhu O. Mittal, and Michael J. Witbrock. 2000. Headline generation based on statistical translation. In Proceedings of ACL00, pages 318–325. [find](https://scholar.google.com/scholar?q=Michele+Banko%2C+Vibhu+O%2E+Mittal%2C+and+Michael+J%2E+Witbrock%2E+2000%2E+Headline+generation+based+on+statistical+translation%2E+In+Proceedings+of+ACL00%2C+pages+318%E2%80%93325%2E) 4. Nancy Chinchor. 1992. The statistical significance of the muc-4 results. In Proceedings MUC4 ’92, pages 30–50. [find](https://scholar.google.com/scholar?q=Nancy+Chinchor%2E+1992%2E+The+statistical+significance+of+the+muc%2D4+results%2E+In+Proceedings+MUC4+%E2%80%9992%2C+pages+30%E2%80%9350%2E) 5. Kyunghyun Cho, Bart van Merrienboer, Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. 2014. Learning phrase representations using rnn encoder–decoder for statistical machine translation. In Proceedings of the EMNLP14, pages 1724–1734. [find](https://scholar.google.com/scholar?q=Kyunghyun+Cho%2C+Bart+van+Merrienboer%2C+Caglar+Gulcehre%2C+Dzmitry+Bahdanau%2C+Fethi+Bougares%2C+Holger+Schwenk%2C+and+Yoshua+Bengio%2E+2014%2E+Learning+phrase+representations+using+rnn+encoder%E2%80%93decoder+for+statistic) 6. Sumit Chopra, Michael Auli, and Alexander M. Rush. 2016. Abstractive sentence summarization with attentive recurrent neural networks. In Proceedings of NAACL-HLT16, pages 93–98. [find](https://scholar.google.com/scholar?q=Sumit+Chopra%2C+Michael+Auli%2C+and+Alexander+M%2E+Rush%2E+2016%2E+Abstractive+sentence+summarization+with+attentive+recurrent+neural+networks%2E+In+Proceedings+of+NAACL%2DHLT16%2C+pages+93%E2%80%9398%2E) [our card](https://md.research.elamur.ai/free/en/papers/chopra-2016-abstractive-sentence-summarization-attentive-recurrent/) 7. Trevor Cohn and Mirella Lapata. 2008. Sentence compression beyond word deletion. In Proceedings of COLING08, pages 137–144. [find](https://scholar.google.com/scholar?q=Trevor+Cohn+and+Mirella+Lapata%2E+2008%2E+Sentence+compression+beyond+word+deletion%2E+In+Proceedings+of+COLING08%2C+pages+137%E2%80%93144%2E) 8. Trevor Cohn and Mirella Lapata. 2013. An abstractive approach to sentence compression. ACM TIST13, 4(3):41:1–41:35, July. [find](https://scholar.google.com/scholar?q=Trevor+Cohn+and+Mirella+Lapata%2E+2013%2E+An+abstractive+approach+to+sentence+compression%2E+ACM+TIST13%2C+4%283%29%3A41%3A1%E2%80%9341%3A35%2C+July%2E) 9. Bonnie Dorr, David Zajic, and Richard Schwartz. 2003. Hedge trimmer: A parse-and-trim approach to headline generation. In Proceedings of the HLT-NAACL 03 Text Summarization Workshop, pages 1–8. [find](https://scholar.google.com/scholar?q=Bonnie+Dorr%2C+David+Zajic%2C+and+Richard+Schwartz%2E+2003%2E+Hedge+trimmer%3A+A+parse%2Dand%2Dtrim+approach+to+headline+generation%2E+In+Proceedings+of+the+HLT%2DNAACL+03+Text+Summarization+Workshop%2C+pages+1%E2%80%938%2E) [our card](https://md.research.elamur.ai/free/en/papers/dorr-2003-hedge-trimmer-parse-trim-approach/) 10. Katja Filippova and Yasemin Altun. 2013. Overcoming the lack of parallel data in sentence compression. In Proceedings of EMNLP13, pages 1481–1491. [find](https://scholar.google.com/scholar?q=Katja+Filippova+and+Yasemin+Altun%2E+2013%2E+Overcoming+the+lack+of+parallel+data+in+sentence+compression%2E+In+Proceedings+of+EMNLP13%2C+pages+1481%E2%80%931491%2E) 11. Katja Filippova and Michael Strube. 2008. Dependency tree based sentence compression. In Proceedings of INLG08, pages 25–32. [find](https://scholar.google.com/scholar?q=Katja+Filippova+and+Michael+Strube%2E+2008%2E+Dependency+tree+based+sentence+compression%2E+In+Proceedings+of+INLG08%2C+pages+25%E2%80%9332%2E) 12. Katja Filippova, Enrique Alfonseca, Carlos A. Col-menares, Lukasz Kaiser, and Oriol Vinyals. 2015. Sentence compression by deletion with lstms. In Proceedings of EMNLP15, pages 360–368. [find](https://scholar.google.com/scholar?q=Katja+Filippova%2C+Enrique+Alfonseca%2C+Carlos+A%2E+Col%2Dmenares%2C+Lukasz+Kaiser%2C+and+Oriol+Vinyals%2E+2015%2E+Sentence+compression+by+deletion+with+lstms%2E+In+Proceedings+of+EMNLP15%2C+pages+360%E2%80%93368%2E) [our card](https://md.research.elamur.ai/free/en/papers/filippova-2015-sentence-compression-deletion-lstms/) 13. Dimitrios Galanis and Ion Androutsopoulos. 2010. An extractive supervised two-stage method for sentence compression. In Proceedings of NAACL-HLT10, pages 885–893. A. Graves, N. Jaitly, and A. r. Mohamed. 2013. Hybrid speech recognition with deep bidirectional lstm. In Proceedings of IEEE Workshop on… [find](https://scholar.google.com/scholar?q=Dimitrios+Galanis+and+Ion+Androutsopoulos%2E+2010%2E+An+extractive+supervised+two%2Dstage+method+for+sentence+compression%2E+In+Proceedings+of+NAACL%2DHLT10%2C+pages+885%E2%80%93893%2E+A%2E+Graves%2C+N%2E+Jaitly%2C+and+A%2E+r%2E+Moham) 14. Jiatao Gu, Zhengdong Lu, Hang Li, and Victor O.K. Li. 2016. Incorporating copying mechanism in sequence-to-sequence learning. In Proceedings of ACL16, pages 1631–1640. [find](https://scholar.google.com/scholar?q=Jiatao+Gu%2C+Zhengdong+Lu%2C+Hang+Li%2C+and+Victor+O%2EK%2E+Li%2E+2016%2E+Incorporating+copying+mechanism+in+sequence%2Dto%2Dsequence+learning%2E+In+Proceedings+of+ACL16%2C+pages+1631%E2%80%931640%2E) [our card](https://md.research.elamur.ai/free/en/papers/gu-2016-incorporating-copying-mechanism-sequence-sequence/) 15. Caglar Gulcehre, Sungjin Ahn, Ramesh Nallapati, Bowen Zhou, and Yoshua Bengio. 2016. Pointing the unknown words. In Proceedings of ACL16, pages 140–149. Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural Computation, 9(8):1735– 1780. Rafal Józefowicz, Wojciech Zaremba, an… [find](https://scholar.google.com/scholar?q=Caglar+Gulcehre%2C+Sungjin+Ahn%2C+Ramesh+Nallapati%2C+Bowen+Zhou%2C+and+Yoshua+Bengio%2E+2016%2E+Pointing+the+unknown+words%2E+In+Proceedings+of+ACL16%2C+pages+140%E2%80%93149%2E+Sepp+Hochreiter+and+Ju%CC%88rgen+Schmidhuber%2E+1997%2E+) [our card](https://md.research.elamur.ai/free/en/papers/gulcehre-2016-pointing-unknown-words/) 16. Nal Kalchbrenner and Phil Blunsom. 2013. Recurrent continuous translation models. In Proceedings of EMNLP13, pages 1700–1709, Seattle, Washington, USA, October. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Nal+Kalchbrenner+and+Phil+Blunsom%2E+2013%2E+Recurrent+continuous+translation+models%2E+In+Proceedings+of+EMNLP13%2C+pages+1700%E2%80%931709%2C+Seattle%2C+Washington%2C+USA%2C+October%2E+Association+for+Computational+Linguisti) [our card](https://md.research.elamur.ai/free/en/papers/kalchbrenner-2013-recurrent-continuous-translation-models/) 17. Diederik P. Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In Proceedings of ICLR15. [find](https://scholar.google.com/scholar?q=Diederik+P%2E+Kingma+and+Jimmy+Ba%2E+2015%2E+Adam%3A+A+method+for+stochastic+optimization%2E+In+Proceedings+of+ICLR15%2E) 18. Jiwei Li, Michel Galley, Chris Brockett, Jianfeng Gao, and Bill Dolan. 2016a. A diversity-promoting objective function for neural conversation models. In Proceedings of NAACL-HLT16, pages 110–119. [find](https://scholar.google.com/scholar?q=Jiwei+Li%2C+Michel+Galley%2C+Chris+Brockett%2C+Jianfeng+Gao%2C+and+Bill+Dolan%2E+2016a%2E+A+diversity%2Dpromoting+objective+function+for+neural+conversation+models%2E+In+Proceedings+of+NAACL%2DHLT16%2C+pages+110%E2%80%93119%2E) [our card](https://md.research.elamur.ai/free/en/papers/li-2016-diversity-promoting-objective-function-neural/) 19. Jiwei Li, Michel Galley, Chris Brockett, Georgios Spithourakis, Jianfeng Gao, and Bill Dolan. 2016b. A persona-based neural conversation model. In Proceedings of ACL16, pages 994–1003. [find](https://scholar.google.com/scholar?q=Jiwei+Li%2C+Michel+Galley%2C+Chris+Brockett%2C+Georgios+Spithourakis%2C+Jianfeng+Gao%2C+and+Bill+Dolan%2E+2016b%2E+A+persona%2Dbased+neural+conversation+model%2E+In+Proceedings+of+ACL16%2C+pages+994%E2%80%931003%2E) [our card](https://md.research.elamur.ai/free/en/papers/li-2016-persona-based-neural-conversation-model/) 20. Chin-Yew Lin. 2004. Rouge: A package for automatic evaluation of summaries. In Proceedings of the ACL04 Workshop, pages 74–81. [find](https://scholar.google.com/scholar?q=Chin%2DYew+Lin%2E+2004%2E+Rouge%3A+A+package+for+automatic+evaluation+of+summaries%2E+In+Proceedings+of+the+ACL04+Workshop%2C+pages+74%E2%80%9381%2E) 21. Konstantin Lopyrev. 2015. Generating news headlines with recurrent neural networks. CoRR, abs/1512.01712. — [arXiv:1512.01712](https://arxiv.org/abs/1512.01712) [find](https://scholar.google.com/scholar?q=Konstantin+Lopyrev%2E+2015%2E+Generating+news+headlines+with+recurrent+neural+networks%2E+CoRR%2C+abs%2F1512%2E01712%2E+%E2%80%94+%5BarXiv%3A1512%2E01712%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F1512%2E01712%29) 22. Thang Luong, Hieu Pham, and Christopher D. Manning. 2015. Effective approaches to attention-based neural machine translation. In Proceedings of EMNLP15, pages 1412–1421. [find](https://scholar.google.com/scholar?q=Thang+Luong%2C+Hieu+Pham%2C+and+Christopher+D%2E+Manning%2E+2015%2E+Effective+approaches+to+attention%2Dbased+neural+machine+translation%2E+In+Proceedings+of+EMNLP15%2C+pages+1412%E2%80%931421%2E) 23. Ramesh Nallapati, Bing Xiang, and Bowen Zhou. 2016. Sequence-to-sequence rnns for text summarization. CoRR, abs/1602.06023. [find](https://scholar.google.com/scholar?q=Ramesh+Nallapati%2C+Bing+Xiang%2C+and+Bowen+Zhou%2E+2016%2E+Sequence%2Dto%2Dsequence+rnns+for+text+summarization%2E+CoRR%2C+abs%2F1602%2E06023%2E) 24. Courtney Napoles, Chris Callison-Burch, Juri Ganitkevitch, and Benjamin Van Durme. 2011. Paraphrastic sentence compression with a character-based metric: Tightening without deletion. In Proceedings of the Workshop on Monolingual Text-To-Text Generation, pages 84–90. [find](https://scholar.google.com/scholar?q=Courtney+Napoles%2C+Chris+Callison%2DBurch%2C+Juri+Ganitkevitch%2C+and+Benjamin+Van+Durme%2E+2011%2E+Paraphrastic+sentence+compression+with+a+character%2Dbased+metric%3A+Tightening+without+deletion%2E+In+Proceedings+of) 25. Courtney Napoles, Matthew Gormley, and Benjamin Van Durme. 2012. Annotated gigaword. In Proceedings of the Joint Workshop on Automatic Knowledge Base Construction and Web-scale Knowledge Extraction, pages 95–100. [find](https://scholar.google.com/scholar?q=Courtney+Napoles%2C+Matthew+Gormley%2C+and+Benjamin+Van+Durme%2E+2012%2E+Annotated+gigaword%2E+In+Proceedings+of+the+Joint+Workshop+on+Automatic+Knowledge+Base+Construction+and+Web%2Dscale+Knowledge+Extraction%2C+p) [our card](https://md.research.elamur.ai/free/en/papers/napoles-2012-annotated-gigaword/) 26. Ani Nenkova and Kathleen McKeown. 2011. Automatic R in Infor-summarization. In Foundations and Trends ⃝ mation Retrieval, volume 2-3, pages 103–233. [find](https://scholar.google.com/scholar?q=Ani+Nenkova+and+Kathleen+McKeown%2E+2011%2E+Automatic+R+in+Infor%2Dsummarization%2E+In+Foundations+and+Trends+%E2%83%9D+mation+Retrieval%2C+volume+2%2D3%2C+pages+103%E2%80%93233%2E) 27. Marc’Aurelio Ranzato, Sumit Chopra, Michael Auli, and Wojciech Zaremba. 2015. Sequence level training with recurrent neural networks. CoRR, abs/1511.06732. [find](https://scholar.google.com/scholar?q=Marc%E2%80%99Aurelio+Ranzato%2C+Sumit+Chopra%2C+Michael+Auli%2C+and+Wojciech+Zaremba%2E+2015%2E+Sequence+level+training+with+recurrent+neural+networks%2E+CoRR%2C+abs%2F1511%2E06732%2E) [our card](https://md.research.elamur.ai/free/en/papers/ranzato-2015-sequence-level-training-recurrent-neural/) 28. Ronald Rosenfeld, Stanley F. Chen, and Xiaojin Zhu. 2001. Whole-sentence exponential language models: a vehicle for linguistic-statistical integration. Computer Speech & Language, 15(1):55–73. [find](https://scholar.google.com/scholar?q=Ronald+Rosenfeld%2C+Stanley+F%2E+Chen%2C+and+Xiaojin+Zhu%2E+2001%2E+Whole%2Dsentence+exponential+language+models%3A+a+vehicle+for+linguistic%2Dstatistical+integration%2E+Computer+Speech+%26+Language%2C+15%281%29%3A55%E2%80%9373%2E) 29. Alexander M. Rush, Sumit Chopra, and Jason Weston. 2015. A neural attention model for abstractive sentence summarization. In Proceedings of EMNLP15, pages 379–389. [find](https://scholar.google.com/scholar?q=Alexander+M%2E+Rush%2C+Sumit+Chopra%2C+and+Jason+Weston%2E+2015%2E+A+neural+attention+model+for+abstractive+sentence+summarization%2E+In+Proceedings+of+EMNLP15%2C+pages+379%E2%80%93389%2E) 30. M. Schuster and K.K. Paliwal. 1997. Bidirectional recurrent neural networks. IEEE Transactions on Signal Processing, 45(11):2673–2681. [find](https://scholar.google.com/scholar?q=M%2E+Schuster+and+K%2EK%2E+Paliwal%2E+1997%2E+Bidirectional+recurrent+neural+networks%2E+IEEE+Transactions+on+Signal+Processing%2C+45%2811%29%3A2673%E2%80%932681%2E) 31. Rico Sennrich, Barry Haddow, and Alexandra Birch. 2016. Controlling politeness in neural machine translation via side constraints. In Proceedings of NAACL-HLT16, pages 35–40. [find](https://scholar.google.com/scholar?q=Rico+Sennrich%2C+Barry+Haddow%2C+and+Alexandra+Birch%2E+2016%2E+Controlling+politeness+in+neural+machine+translation+via+side+constraints%2E+In+Proceedings+of+NAACL%2DHLT16%2C+pages+35%E2%80%9340%2E) [our card](https://md.research.elamur.ai/free/en/papers/sennrich-2016-controlling-politeness-neural-machine-translation/) 32. Iulian Vlad Serban, Alessandro Sordoni, Yoshua Bengio, Aaron C. Courville, and Joelle Pineau. 2016. Building end-to-end dialogue systems using generative hierarchical neural network models. In Proceedings of AAAI16, pages 3776–3784. [find](https://scholar.google.com/scholar?q=Iulian+Vlad+Serban%2C+Alessandro+Sordoni%2C+Yoshua+Bengio%2C+Aaron+C%2E+Courville%2C+and+Joelle+Pineau%2E+2016%2E+Building+end%2Dto%2Dend+dialogue+systems+using+generative+hierarchical+neural+network+models%2E+In+Proceed) [our card](https://md.research.elamur.ai/free/en/papers/serban-2015-building-end-end-dialogue-systems/) 33. Ilya Sutskever, Oriol Vinyals, and Quoc V Le. 2014. Sequence to sequence learning with neural networks. In Proceedings of NIPS14, pages 3104–3112. [find](https://scholar.google.com/scholar?q=Ilya+Sutskever%2C+Oriol+Vinyals%2C+and+Quoc+V+Le%2E+2014%2E+Sequence+to+sequence+learning+with+neural+networks%2E+In+Proceedings+of+NIPS14%2C+pages+3104%E2%80%933112%2E) 34. Seiya Tokui, Kenta Oono, Shohei Hido, and Justin Clayton. 2015. Chainer: a next-generation open source framework for deep learning. In Proceedings of NIPS15 Workshop on LearningSys. [find](https://scholar.google.com/scholar?q=Seiya+Tokui%2C+Kenta+Oono%2C+Shohei+Hido%2C+and+Justin+Clayton%2E+2015%2E+Chainer%3A+a+next%2Dgeneration+open+source+framework+for+deep+learning%2E+In+Proceedings+of+NIPS15+Workshop+on+LearningSys%2E) 35. Oriol Vinyals, Lukasz Kaiser, Terry Koo, Slav Petrov, Ilya Sutskever, and Geoffrey E. Hinton. 2015a. Grammar as a foreign language. In Proceedings of NIPS15, pages 2773–2781. [find](https://scholar.google.com/scholar?q=Oriol+Vinyals%2C+Lukasz+Kaiser%2C+Terry+Koo%2C+Slav+Petrov%2C+Ilya+Sutskever%2C+and+Geoffrey+E%2E+Hinton%2E+2015a%2E+Grammar+as+a+foreign+language%2E+In+Proceedings+of+NIPS15%2C+pages+2773%E2%80%932781%2E) 36. Oriol Vinyals, Alexander Toshev, Samy Bengio, and Dumitru Erhan. 2015b. Show and tell: A neural image caption generator. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 3156–3164. Tsung-Hsien Wen, Milica Gasic, Nikola Mrkšić, Pei-Hao Su, David Vandyke, and S… [find](https://scholar.google.com/scholar?q=Oriol+Vinyals%2C+Alexander+Toshev%2C+Samy+Bengio%2C+and+Dumitru+Erhan%2E+2015b%2E+Show+and+tell%3A+A+neural+image+caption+generator%2E+In+Proceedings+of+the+IEEE+Conference+on+Computer+Vision+and+Pattern+Recognitio) [our card](https://md.research.elamur.ai/free/en/papers/vinyals-2014-show-tell-neural-image-caption/) 37. Kristian Woodsend, Yansong Feng, and Mirella Lapata. 2010. Title generation with quasi-synchronous grammar. In Proceedings of the EMNLP10, pages 513–523. [find](https://scholar.google.com/scholar?q=Kristian+Woodsend%2C+Yansong+Feng%2C+and+Mirella+Lapata%2E+2010%2E+Title+generation+with+quasi%2Dsynchronous+grammar%2E+In+Proceedings+of+the+EMNLP10%2C+pages+513%E2%80%93523%2E) 38. Sander Wubben, Antal van den Bosch, and Emiel Krahmer. 2012. Sentence simplification by monolingual machine translation. In Proceedings of ACL12, pages 1015–1024. [find](https://scholar.google.com/scholar?q=Sander+Wubben%2C+Antal+van+den+Bosch%2C+and+Emiel+Krahmer%2E+2012%2E+Sentence+simplification+by+monolingual+machine+translation%2E+In+Proceedings+of+ACL12%2C+pages+1015%E2%80%931024%2E) [our card](https://md.research.elamur.ai/free/en/papers/wubben-2012-sentence-simplification-monolingual-machine-translation/) 39. 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 David Blei and Francis Bach, editors, Proceedings of ICML15, 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/) 40. JMLR Workshop and Conference Proceedings. David Zajic, Bonnie J Dorr, and R. Schwartz. 2004. Bbn/umd at duc-2004: Topiary. In Proceedings of NAACL-HLT04 Document Understanding Workshop, pages 112 – 119. [find](https://scholar.google.com/scholar?q=JMLR+Workshop+and+Conference+Proceedings%2E+David+Zajic%2C+Bonnie+J+Dorr%2C+and+R%2E+Schwartz%2E+2004%2E+Bbn%2Fumd+at+duc%2D2004%3A+Topiary%2E+In+Proceedings+of+NAACL%2DHLT04+Document+Understanding+Workshop%2C+pages+112+%E2%80%93+11)