--- title: "Incorporating Copying Mechanism in — Gu 2016" description: "Standard encoder-decoder networks, even with attention, often fail when an output has to repeat parts of the input exactly." authors: ["Jiatao Gu", "Zhengdong Lu", "Hang Li", "Victor O. K. Li"] year: 2016 venue: "arXiv:1603.06393" source: "https://arxiv.org/abs/1603.06393" doi: "10.48550/arxiv.1603.06393" arxiv: "1603.06393" 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/gu-2016-incorporating-copying-mechanism-sequence-sequence/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/gu-2016-incorporating-copying-mechanism-sequence-sequence/) [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/page/2/) / Incorporating Copying Mechanism in Sequence-to-Sequence Learning # Incorporating Copying Mechanism in Sequence-to-Sequence Learning **Authors:** [Jiatao Gu](https://md.research.elamur.ai/free/en/authors/jiatao-gu/), [Zhengdong Lu](https://md.research.elamur.ai/free/en/authors/zhengdong-lu/), [Hang Li](https://md.research.elamur.ai/free/en/authors/hang-li/), [Victor O. K. Li](https://md.research.elamur.ai/free/en/authors/victor-o-k-li/) · **Year:** 2016 · **Venue:** arXiv:1603.06393 · **Licence:** [arXiv — non-exclusive licence to distribute](http://arxiv.org/licenses/nonexclusive-distrib/1.0/) **Links:** [Publisher's page](https://arxiv.org/abs/1603.06393) · [PDF](https://arxiv.org/pdf/1603.06393) · [DOI 10.48550/arxiv.1603.06393](https://doi.org/10.48550/arxiv.1603.06393) · [arXiv 1603.06393](https://arxiv.org/abs/1603.06393) · [OpenAlex](https://openalex.org/W2964165364) **Citations:** 1446 citations (openalex-snapshot · 2026-10-14) · [449](#cited-by) in our library, of the 140673 papers whose bibliographies we read ## Summary Standard encoder-decoder networks, even with attention, often fail when an output has to repeat parts of the input exactly. Names, dates and rare words are typical cases, and they are often out-of-vocabulary (OOV). Gu, Lu, Li and Li propose COPYNET to handle this. It is an attention-based RNN encoder-decoder whose decoder can either generate a word from a fixed vocabulary or copy a token from the source. The two options share one softmax normalization, so they compete directly for each output position. A "selective read" passes the location of the previously copied word back into the decoder state, which helps the model copy several consecutive words. The whole model is differentiable and is trained end to end with gradient descent. The authors test it on synthetic sequence-transformation data, Chinese text summarization (LCSTS) and Chinese single-turn dialogue. COPYNET clearly beats an RNNSearch baseline, especially when the input contains words never seen in training. The work matters because it gives Seq2Seq systems a learned, built-in way to deal with OOV words and verbatim reuse of input. It was an early influence on pointer-generator style models. ## Key points - **Output distribution:** each output word's probability adds a generate-mode score and a copy-mode score. A word can be produced by both modes, by copying only (OOV source tokens) or by neither (UNK). For each input, the effective vocabulary is V ∪ UNK ∪ the source words. - **Copy scores:** these come from a tanh projection that compares the decoder state with the encoder's bidirectional hidden states. Those states carry both what a word means and where it sits in the source. - **Dialogue results:** on the template-based dialogue sets (DS-I and DS-II), top-1 accuracy went from 44.1 to 61.2 on DS-I. On DS-II, where the filled-in entities never appear in training, it went from 13.5 to 50.5, and top-10 accuracy went from 15.9 to 64.8. - **Example behaviour:** in the case studies, the baseline replaces unseen entities with other names (it outputs Hainan instead of Shanghai). COPYNET copies the right entity and generates the rest of the reply normally. - **Related work and limits:** unlike Pointer Networks, COPYNET is not limited to copying from the input. It cannot be used directly for machine translation because it copies source words exactly, and the authors leave that extension for future work. *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 449 papers of our library cite it (of the 140673 whose bibliographies we read); 41 of them have a page here, 408 not yet. - [Story Realization: Expanding Plot Events into Sentences](https://md.research.elamur.ai/free/en/papers/ammanabrolu-2019-story-realization-expanding-plot-events/) - [Incorporating Discrete Translation Lexicons into Neural Machine Translation](https://md.research.elamur.ai/free/en/papers/arthur-2016-incorporating-discrete-translation-lexicons-into/) - [Taskmaster-1: Toward a Realistic and Diverse Dialog Dataset](https://md.research.elamur.ai/free/en/papers/byrne-2019-taskmaster-1-realistic-diverse-dialog/) - [AMR Parsing via Graph-Sequence Iterative Inference](https://md.research.elamur.ai/free/en/papers/cai-2020-amr-parsing-graph-sequence-iterative/) - [Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting](https://md.research.elamur.ai/free/en/papers/chen-2018-fast-abstractive-summarization-reinforce-selected/) - [Logical Natural Language Generation from Open-Domain Tables](https://md.research.elamur.ai/free/en/papers/chen-2020-logical-natural-language-generation-open/) - [Neural Summarization by Extracting Sentences and Words](https://md.research.elamur.ai/free/en/papers/cheng-2016-neural-summarization-extracting-sentences-words/) - [A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents](https://md.research.elamur.ai/free/en/papers/cohan-2018-discourse-aware-attention-model-abstractive/) - [EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing](https://md.research.elamur.ai/free/en/papers/dong-2019-editnts-neural-programmer-interpreter-model/) - [GSum: A General Framework for Guided Neural Abstractive Summarization](https://md.research.elamur.ai/free/en/papers/dou-2021-gsum-general-framework-guided-neural/) - [Bottom-Up Abstractive Summarization](https://md.research.elamur.ai/free/en/papers/gehrmann-2018-bottom-up-abstractive-summarization/) - [Pointing the Unknown Words](https://md.research.elamur.ai/free/en/papers/gulcehre-2016-pointing-unknown-words/) - [Improved Lexically Constrained Decoding for Translation and Monolingual Rewriting](https://md.research.elamur.ai/free/en/papers/hu-2019-improved-lexically-constrained-decoding-translation/) - [BIDER: Bridging Knowledge Inconsistency for Efficient Retrieval-Augmented LLMs via Key Supporting Evidence](https://md.research.elamur.ai/free/en/papers/jin-2024-bider-bridging-knowledge-inconsistency-efficient/) - [Controlling Output Length in Neural Encoder-Decoders](https://md.research.elamur.ai/free/en/papers/kikuchi-2016-controlling-output-length-neural-encoder/) - [Sequicity: Simplifying Task-oriented Dialogue Systems with Single Sequence-to-Sequence Architectures](https://md.research.elamur.ai/free/en/papers/lei-2018-sequicity-simplifying-task-oriented-dialogue/) - [Wiktionary Normalization of Translations and Morphological Information](https://md.research.elamur.ai/free/en/papers/lex-2020-wu-wiktionary-normalization/) - [Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsing](https://md.research.elamur.ai/free/en/papers/lin-2020-bridging-textual-tabular-data-cross/) - [MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems](https://md.research.elamur.ai/free/en/papers/lin-2020-mintl-minimalist-transfer-learning-task/) - [Controllable Text Simplification with Explicit Paraphrasing](https://md.research.elamur.ai/free/en/papers/maddela-2021-controllable-text-simplification-explicit-paraphrasing/) - [Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems](https://md.research.elamur.ai/free/en/papers/madotto-2018-mem2seq-effectively-incorporating-knowledge-bases/) - [Encode, Tag, Realize: High-Precision Text Editing](https://md.research.elamur.ai/free/en/papers/malmi-2019-encode-tag-realize-high-precision/) - [Data-Driven Sentence Simplification: Survey and Benchmark](https://md.research.elamur.ai/free/en/papers/manchego-2020-data-driven-sentence-simplification-survey/) - [The Natural Language Decathlon: Multitask Learning as Question Answering](https://md.research.elamur.ai/free/en/papers/mccann-2018-natural-language-decathlon-multitask-learning/) - [Deep Keyphrase Generation](https://md.research.elamur.ai/free/en/papers/meng-2017-deep-keyphrase-generation/) - [Pointer Sentinel Mixture Models](https://md.research.elamur.ai/free/en/papers/merity-2016-pointer-sentinel-mixture-models/) - [On Extractive and Abstractive Neural Document Summarization with Transformer Language Models](https://md.research.elamur.ai/free/en/papers/pilault-2020-extractive-abstractive-neural-document-summarization/) - [QADiscourse - Discourse Relations as QA Pairs: Representation, Crowdsourcing and Baselines](https://md.research.elamur.ai/free/en/papers/pyatkin-2020-qadiscourse-discourse-relations-as-qa/) - [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/) - [Leveraging Pre-trained Checkpoints for Sequence Generation Tasks](https://md.research.elamur.ai/free/en/papers/rothe-2019-leveraging-pre-trained-checkpoints-sequence/) - [Interpretation of Natural Language Rules in Conversational Machine Reading](https://md.research.elamur.ai/free/en/papers/saeidi-2018-interpretation-natural-language-rules-conversational/) - [A Graph-to-Sequence Model for AMR-to-Text Generation](https://md.research.elamur.ai/free/en/papers/song-2018-graph-sequence-model-amr-text/) - [Machine Comprehension Using Match-LSTM and Answer Pointer](https://md.research.elamur.ai/free/en/papers/wang-2016-machine-comprehension-using-match-lstm/) - [AMR-To-Text Generation with Graph Transformer](https://md.research.elamur.ai/free/en/papers/wang-2020-amr-text-generation-graph-transformer/) - [Challenges in Data-to-Document Generation](https://md.research.elamur.ai/free/en/papers/wiseman-2017-challenges-data-document-generation/) - [Learning Neural Templates for Text Generation](https://md.research.elamur.ai/free/en/papers/wiseman-2018-learning-neural-templates-text-generation/) - [Break It Down: A Question Understanding Benchmark](https://md.research.elamur.ai/free/en/papers/wolfson-2020-break-it-down-question-understanding/) - [Learning to Mine Aligned Code and Natural Language Pairs from Stack Overflow](https://md.research.elamur.ai/free/en/papers/yin-2018-learning-mine-aligned-code-natural/) - [Extracting Relational Facts by an End-to-End Neural Model with Copy Mechanism](https://md.research.elamur.ai/free/en/papers/zeng-2018-extracting-relational-facts-end-end/) - [HIBERT: Document Level Pre-training of Hierarchical Bidirectional Transformers for Document Summarization](https://md.research.elamur.ai/free/en/papers/zhang-2019-hibert-document-level-pre-training/) - [Paragraph-level Neural Question Generation with Maxout Pointer and Gated Self-attention Networks](https://md.research.elamur.ai/free/en/papers/zhao-2018-paragraph-level-neural-question-generation/) ## Cite The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @misc{gu2016incorporating, title = {{Incorporating Copying Mechanism in Sequence-to-Sequence Learning}}, author = {Gu, Jiatao and Lu, Zhengdong and Li, Hang and Li, Victor O. K.}, year = {2016}, doi = {10.48550/arxiv.1603.06393}, eprint = {1603.06393}, archivePrefix = {arXiv}, url = {https://doi.org/10.48550/arxiv.1603.06393} } ``` - [← previous IMS HotCoref DE: A Data-driven Co-reference Resolver for German](https://md.research.elamur.ai/free/en/papers/roesiger-2016-ims-hotcoref-de-data-driven/) - [next → Incorporating Discrete Translation Lexicons into Neural Machine Translation](https://md.research.elamur.ai/free/en/papers/arthur-2016-incorporating-discrete-translation-lexicons-into/) - [↑ back to papers of 2016](https://md.research.elamur.ai/free/en/papers/2016/page/2/) ## References 22 references, 9 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2014. Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473. [find](https://scholar.google.com/scholar?q=Dzmitry+Bahdanau%2C+Kyunghyun+Cho%2C+and+Yoshua+Bengio%2E+2014%2E+Neural+machine+translation+by+jointly+learning+to+align+and+translate%2E+arXiv+preprint+arXiv%3A1409%2E0473%2E) [our card](https://md.research.elamur.ai/free/en/papers/bahdanau-2014-neural-machine-translation-jointly-learning/) 2. Jianpeng Cheng and Mirella Lapata. 2016. Neural summarization by extracting sentences and words. arXiv preprint arXiv:1603.07252. [find](https://scholar.google.com/scholar?q=Jianpeng+Cheng+and+Mirella+Lapata%2E+2016%2E+Neural+summarization+by+extracting+sentences+and+words%2E+arXiv+preprint+arXiv%3A1603%2E07252%2E) [our card](https://md.research.elamur.ai/free/en/papers/cheng-2016-neural-summarization-extracting-sentences-words/) 3. Kyunghyun Cho, Bart Van Merriënboer, Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. 2014. Learning phrase representations using rnn encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078. [find](https://scholar.google.com/scholar?q=Kyunghyun+Cho%2C+Bart+Van+Merrie%CC%88nboer%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%2Ddecoder+for+statisti) 4. Alex Graves, Greg Wayne, and Ivo Danihelka. 2014. Neural turing machines. arXiv preprint arXiv:1410.5401. [find](https://scholar.google.com/scholar?q=Alex+Graves%2C+Greg+Wayne%2C+and+Ivo+Danihelka%2E+2014%2E+Neural+turing+machines%2E+arXiv+preprint+arXiv%3A1410%2E5401%2E) 5. Caglar Gulcehre, Sungjin Ahn, Ramesh Nallapati, Bowen Zhou, and Yoshua Bengio. 2016. Pointing the unknown words. arXiv preprint arXiv:1603.08148. [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+arXiv+preprint+arXiv%3A1603%2E08148%2E) [our card](https://md.research.elamur.ai/free/en/papers/gulcehre-2016-pointing-unknown-words/) 6. Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2015. Deep residual learning for image recognition. arXiv preprint arXiv:1512.03385. [find](https://scholar.google.com/scholar?q=Kaiming+He%2C+Xiangyu+Zhang%2C+Shaoqing+Ren%2C+and+Jian+Sun%2E+2015%2E+Deep+residual+learning+for+image+recognition%2E+arXiv+preprint+arXiv%3A1512%2E03385%2E) 7. Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural computation, 9(8):1735–1780. [find](https://scholar.google.com/scholar?q=Sepp+Hochreiter+and+Ju%CC%88rgen+Schmidhuber%2E+1997%2E+Long+short%2Dterm+memory%2E+Neural+computation%2C+9%288%29%3A1735%E2%80%931780%2E) 8. Baotian Hu, Qingcai Chen, and Fangze Zhu. 2015. Lcsts: a large scale chinese short text summarization dataset. arXiv preprint arXiv:1506.05865. [find](https://scholar.google.com/scholar?q=Baotian+Hu%2C+Qingcai+Chen%2C+and+Fangze+Zhu%2E+2015%2E+Lcsts%3A+a+large+scale+chinese+short+text+summarization+dataset%2E+arXiv+preprint+arXiv%3A1506%2E05865%2E) 9. Karol Kurach, Marcin Andrychowicz, and Ilya Sutskever. 2015. Neural random-access machines. arXiv preprint arXiv:1511.06392. [find](https://scholar.google.com/scholar?q=Karol+Kurach%2C+Marcin+Andrychowicz%2C+and+Ilya+Sutskever%2E+2015%2E+Neural+random%2Daccess+machines%2E+arXiv+preprint+arXiv%3A1511%2E06392%2E) 10. Chin-Yew Lin. 2004. Rouge: A package for automatic evaluation of summaries. In Stan Szpakowicz Marie-Francine Moens, editor, Text Summarization Branches Out: Proceedings of the ACL-04 Workshop, pages 74–81, Barcelona, Spain, July. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Chin%2DYew+Lin%2E+2004%2E+Rouge%3A+A+package+for+automatic+evaluation+of+summaries%2E+In+Stan+Szpakowicz+Marie%2DFrancine+Moens%2C+editor%2C+Text+Summarization+Branches+Out%3A+Proceedings+of+the+ACL%2D04+Workshop%2C+pages+) 11. Thang Luong, Ilya Sutskever, Quoc Le, Oriol Vinyals, and Wojciech Zaremba. 2015. Addressing the rare word problem in neural machine translation. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language P… [find](https://scholar.google.com/scholar?q=Thang+Luong%2C+Ilya+Sutskever%2C+Quoc+Le%2C+Oriol+Vinyals%2C+and+Wojciech+Zaremba%2E+2015%2E+Addressing+the+rare+word+problem+in+neural+machine+translation%2E+In+Proceedings+of+the+53rd+Annual+Meeting+of+the+Associ) [our card](https://md.research.elamur.ai/free/en/papers/luong-2015-addressing-rare-word-problem-neural/) 12. Geoffrey J McLachlan and Kaye E Basford. 1988. Mixture models. inference and applications to clustering. [find](https://scholar.google.com/scholar?q=Geoffrey+J+McLachlan+and+Kaye+E+Basford%2E+1988%2E+Mixture+models%2E+inference+and+applications+to+clustering%2E) 13. Statistics: Textbooks and Monographs, New York: Dekker, 1988, 1. [find](https://scholar.google.com/scholar?q=Statistics%3A+Textbooks+and+Monographs%2C+New+York%3A+Dekker%2C+1988%2C+1%2E) 14. Alexander M Rush, Sumit Chopra, and Jason Weston. 2015. A neural attention model for abstractive sentence summarization. arXiv preprint arXiv:1509.00685. [find](https://scholar.google.com/scholar?q=Alexander+M+Rush%2C+Sumit+Chopra%2C+and+Jason+Weston%2E+2015%2E+A+neural+attention+model+for+abstractive+sentence+summarization%2E+arXiv+preprint+arXiv%3A1509%2E00685%2E) 15. Lifeng Shang, Zhengdong Lu, and Hang Li. 2015. Neural responding machine for short-text conversation. arXiv preprint arXiv:1503.02364. [find](https://scholar.google.com/scholar?q=Lifeng+Shang%2C+Zhengdong+Lu%2C+and+Hang+Li%2E+2015%2E+Neural+responding+machine+for+short%2Dtext+conversation%2E+arXiv+preprint+arXiv%3A1503%2E02364%2E) [our card](https://md.research.elamur.ai/free/en/papers/shang-2015-neural-responding-machine-short-text/) 16. Shiqi Shen, Yong Cheng, Zhongjun He, Wei He, Hua Wu, Maosong Sun, and Yang Liu. 2015. Minimum risk training for neural machine translation. CoRR, abs/1512.02433. [find](https://scholar.google.com/scholar?q=Shiqi+Shen%2C+Yong+Cheng%2C+Zhongjun+He%2C+Wei+He%2C+Hua+Wu%2C+Maosong+Sun%2C+and+Yang+Liu%2E+2015%2E+Minimum+risk+training+for+neural+machine+translation%2E+CoRR%2C+abs%2F1512%2E02433%2E) [our card](https://md.research.elamur.ai/free/en/papers/shen-2015-minimum-risk-training-neural-machine/) 17. Alessandro Sordoni, Michel Galley, Michael Auli, Chris Brockett, Yangfeng Ji, Margaret Mitchell, Jian-Yun Nie, Jianfeng Gao, and Bill Dolan. 2015. A neural network approach to context-sensitive generation of conversational responses. arXiv preprint arXiv:1506.06714. [find](https://scholar.google.com/scholar?q=Alessandro+Sordoni%2C+Michel+Galley%2C+Michael+Auli%2C+Chris+Brockett%2C+Yangfeng+Ji%2C+Margaret+Mitchell%2C+Jian%2DYun+Nie%2C+Jianfeng+Gao%2C+and+Bill+Dolan%2E+2015%2E+A+neural+network+approach+to+context%2Dsensitive+genera) [our card](https://md.research.elamur.ai/free/en/papers/sordoni-2015-neural-network-approach-context-sensitive/) 18. Rupesh Kumar Srivastava, Klaus Greff, and Jürgen Schmidhuber. 2015. Highway networks. arXiv preprint arXiv:1505.00387. [find](https://scholar.google.com/scholar?q=Rupesh+Kumar+Srivastava%2C+Klaus+Greff%2C+and+Ju%CC%88rgen+Schmidhuber%2E+2015%2E+Highway+networks%2E+arXiv+preprint+arXiv%3A1505%2E00387%2E) [our card](https://md.research.elamur.ai/free/en/papers/srivastava-2015-highway-networks/) 19. Ilya Sutskever, Oriol Vinyals, and Quoc VV Le. 2014. Sequence to sequence learning with neural networks. In Advances in neural information processing systems, pages 3104–3112. [find](https://scholar.google.com/scholar?q=Ilya+Sutskever%2C+Oriol+Vinyals%2C+and+Quoc+VV+Le%2E+2014%2E+Sequence+to+sequence+learning+with+neural+networks%2E+In+Advances+in+neural+information+processing+systems%2C+pages+3104%E2%80%933112%2E) 20. Oriol Vinyals and Quoc Le. 2015. A neural conversational model. arXiv preprint arXiv:1506.05869. [find](https://scholar.google.com/scholar?q=Oriol+Vinyals+and+Quoc+Le%2E+2015%2E+A+neural+conversational+model%2E+arXiv+preprint+arXiv%3A1506%2E05869%2E) [our card](https://md.research.elamur.ai/free/en/papers/vinyals-2015-neural-conversational-model/) 21. Oriol Vinyals, Meire Fortunato, and Navdeep Jaitly. 2015a. Pointer networks. In Advances in Neural Information Processing Systems, pages 2674–2682. [find](https://scholar.google.com/scholar?q=Oriol+Vinyals%2C+Meire+Fortunato%2C+and+Navdeep+Jaitly%2E+2015a%2E+Pointer+networks%2E+In+Advances+in+Neural+Information+Processing+Systems%2C+pages+2674%E2%80%932682%2E) 22. Oriol Vinyals, Łukasz Kaiser, Terry Koo, Slav Petrov, Ilya Sutskever, and Geoffrey Hinton. 2015b. Grammar as a foreign language. In Advances in Neural Information Processing Systems, pages 2755–2763. [find](https://scholar.google.com/scholar?q=Oriol+Vinyals%2C+%C5%81ukasz+Kaiser%2C+Terry+Koo%2C+Slav+Petrov%2C+Ilya+Sutskever%2C+and+Geoffrey+Hinton%2E+2015b%2E+Grammar+as+a+foreign+language%2E+In+Advances+in+Neural+Information+Processing+Systems%2C+pages+2755%E2%80%932763%2E)