---
title: "Generating Sentences from Disentangled Syntactic and Semantic"
description: "The authors present DSS-VAE, which divides a GRU encoder's sentence representation into two… 38 references, cited by 61 papers here."
authors: ["Yu Bao", "Hao Zhou", "Shujian Huang", "Lei Li", "Lili Mou", "Olga Vechtomova", "Xin-yu Dai", "Jiajun Chen"]
year: 2019
venue: "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics"
source: "https://aclanthology.org/P19-1602/"
doi: "10.18653/v1/p19-1602"
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/bao-2019-generating-sentences-disentangled-syntactic-semantic/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/bao-2019-generating-sentences-disentangled-syntactic-semantic/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2019](https://md.research.elamur.ai/free/en/papers/2019/page/4/) / Generating Sentences from Disentangled Syntactic and Semantic Spaces

# Generating Sentences from Disentangled Syntactic and Semantic Spaces

**Authors:** [Yu Bao](https://md.research.elamur.ai/free/en/authors/yu-bao/), [Hao Zhou](https://md.research.elamur.ai/free/en/authors/hao-zhou/), [Shujian Huang](https://md.research.elamur.ai/free/en/authors/shujian-huang/), [Lei Li](https://md.research.elamur.ai/free/en/authors/lei-li/), [Lili Mou](https://md.research.elamur.ai/free/en/authors/lili-mou/), [Olga Vechtomova](https://md.research.elamur.ai/free/en/authors/olga-vechtomova/), [Xin-yu Dai](https://md.research.elamur.ai/free/en/authors/xin-yu-dai/) and [Jiajun Chen](https://md.research.elamur.ai/free/en/authors/jiajun-chen/) · **Year:** 2019 · **Venue:** [Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2019](https://md.research.elamur.ai/free/en/venues/acl/2019/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/P19-1602/) · [PDF](https://aclanthology.org/P19-1602.pdf) · [DOI 10.18653/v1/p19-1602](https://doi.org/10.18653/v1/p19-1602) · [OpenAlex](https://openalex.org/W2963506530)

**Citations:** 93 citations (OpenAlex, 2026-10-14) · [61](https://md.research.elamur.ai/free/en/papers/bao-2019-generating-sentences-disentangled-syntactic-semantic/cited-by/) in our library, of the 141,840 papers whose bibliographies we read

## Summary
Standard variational autoencoders for text store all sentence information in one continuous latent vector. Syntax is therefore never represented explicitly and cannot be sampled or edited on its own. The authors present DSS-VAE, which divides a GRU encoder's sentence representation into two Gaussian latent variables: one for meaning and one for structure. The structural variable learns to predict a linearized constituency tree. ZPar supplies these parses during training only. The semantic variable learns to predict a bag of words. Adversarial objectives and an adversarial reconstruction loss keep each space from absorbing the other's content. Against a plain VAE, the model produces more fluent samples (lower perplexity) and higher reconstruction BLEU. It is also compared with the PRPN syntactic language model. Fixing the semantic vector through MAP inference while resampling the syntactic one gives unsupervised paraphrasing that beats both the VAE and the CGMH sampler. Pairing one sentence's meaning vector with another's syntax vector enables syntax transfer. The work matters because sentence structure becomes a controllable dimension of generation without any parallel corpus.

## Key points
- **Architecture:** two independent latent variables, z_sem and z_syn, each with a N(0, I) prior, are concatenated to initialize the decoder.
  - **Syntax signal:** a separate RNN predicts the linearized parse sequence, where opening and closing nodes such as NP and /NP have distinct embeddings.
  - **Semantics signal:** a bag-of-words prediction.
- **Paraphrase generation:** DSS-VAE outperforms both the plain VAE and CGMH (Miao et al., 2019) on BLEU-ori and BLEU-ref at once.
- **Syntax-transfer benchmark:** the authors built a test set of 1000 non-paraphrase sentence pairs from SNLI.
  - Semantics are scored with word-BLEU differences.
  - Syntax is scored with Tree Edit Distance (zss package).
- **Syntax-transfer results:** the plain VAE essentially fails, with a geometric-mean score of 0.29.
  - Multi-task plus adversarial losses raise the score to 12.09.
  - The full model with both adversarial reconstruction losses reaches 15.30 (ΔTED 30.85, Δword-BLEU 7.59).
  - Transfer works better between structurally compatible sentences, for example ones of similar length.
- **Code and models:** released at github.com/baoy-nlp/DSS-VAE.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [University of Waterloo](https://md.research.elamur.ai/free/en/universities/university-of-waterloo/) — University, Waterloo, Canada · 44 works · 12,783 citations
- [ByteDance](https://md.research.elamur.ai/free/en/companies/bytedance/) — Company, Beijing, China · 18 works · 3,890 citations
- [Nanjing University](https://md.research.elamur.ai/free/en/universities/nanjing-university/) — University, Nanjing, China · 28 works · 7,072 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 9,086 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 8,889 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 9,296 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 9,206 works

## Cite

Cite as: Yu Bao, Hao Zhou, Shujian Huang, Lei Li, Lili Mou, Olga Vechtomova, Xin-yu Dai and Jiajun Chen. 2019. Generating Sentences from Disentangled Syntactic and Semantic Spaces. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics.

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

```bibtex
@inproceedings{bao2019generating,
  title = {{Generating Sentences from Disentangled Syntactic and Semantic Spaces}},
  author = {Yu Bao, Hao Zhou, Shujian Huang, Lei Li, Lili Mou, Olga Vechtomova, Xin-yu Dai and Jiajun Chen},
  booktitle = {Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics},
  year = {2019},
  doi = {10.18653/v1/p19-1602},
  url = {https://doi.org/10.18653/v1/p19-1602}
}
```

- [← previous Evaluating Style Transfer for Text](https://md.research.elamur.ai/free/en/papers/mir-2019-evaluating-style-transfer-text/)
- [next → Cross-Lingual BERT Transformation for Zero-Shot Dependency Parsing](https://md.research.elamur.ai/free/en/papers/wang-2019-cross-lingual-bert-transformation-zero/)
- [↑ back to papers of 2019](https://md.research.elamur.ai/free/en/papers/2019/page/4/)

## References

38 references, 9 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Samuel R. Bowman, Luke Vilnis, Oriol Vinyals, Andrew Dai, Rafal Jozefowicz, and Samy Bengio. [find](https://scholar.google.com/scholar?q=Samuel+R%2E+Bowman%2C+Luke+Vilnis%2C+Oriol+Vinyals%2C+Andrew+Dai%2C+Rafal+Jozefowicz%2C+and+Samy+Bengio%2E)
2. Ciprian Chelba. 1997. A structured language model. In ACL, pages 498–500. [find](https://scholar.google.com/scholar?q=Ciprian+Chelba%2E+1997%2E+A+structured+language+model%2E+In+ACL%2C+pages+498%E2%80%93500%2E)
3. Huadong Chen, Shujian Huang, David Chiang, and Jiajun Chen. 2017. [Improved neural machine translation with a syntax-aware encoder and decoder](https://md.research.elamur.ai/free/en/papers/chen-2017-improved-neural-machine-translation-syntax/). In ACL, pages 1936–1945.
4. 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 EMNLP, 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)
5. Alexander Clark. 2001. Unsupervised induction of stochastic context-free grammars using distributional clustering. In Proceedings of the ACL 2001 Workshop on Computational Natural Language Learning. [find](https://scholar.google.com/scholar?q=Alexander+Clark%2E+2001%2E+Unsupervised+induction+of+stochastic+context%2Dfree+grammars+using+distributional+clustering%2E+In+Proceedings+of+the+ACL+2001+Workshop+on+Computational+Natural+Language+Learning%2E)
6. Hanjun Dai, Yingtao Tian, Bo Dai, Steven Skiena, and Le Song. 2018. Syntax-directed variational autoencoder for structured data. In ICLR. [find](https://scholar.google.com/scholar?q=Hanjun+Dai%2C+Yingtao+Tian%2C+Bo+Dai%2C+Steven+Skiena%2C+and+Le+Song%2E+2018%2E+Syntax%2Ddirected+variational+autoencoder+for+structured+data%2E+In+ICLR%2E)
7. Jan Milan Deriu and Mark Cieliebak. 2018. Syntactic manipulation for generating more diverse and interesting texts. In Proceedings of the 11th International Conference on Natural Language Generation, pages 22–34. [find](https://scholar.google.com/scholar?q=Jan+Milan+Deriu+and+Mark+Cieliebak%2E+2018%2E+Syntactic+manipulation+for+generating+more+diverse+and+interesting+texts%2E+In+Proceedings+of+the+11th+International+Conference+on+Natural+Language+Generation%2C+)
8. Chris Dyer, Adhiguna Kuncoro, Miguel Ballesteros, and Noah A Smith. 2016. Recurrent neural network grammars. In NAACL, pages 199–209. [find](https://scholar.google.com/scholar?q=Chris+Dyer%2C+Adhiguna+Kuncoro%2C+Miguel+Ballesteros%2C+and+Noah+A+Smith%2E+2016%2E+Recurrent+neural+network+grammars%2E+In+NAACL%2C+pages+199%E2%80%93209%2E)
9. Akiko Eriguchi, Kazuma Hashimoto, and Yoshimasa Tsuruoka. 2016. Tree-to-sequence attentional neural machine translation. In ACL, pages 823–833. [find](https://scholar.google.com/scholar?q=Akiko+Eriguchi%2C+Kazuma+Hashimoto%2C+and+Yoshimasa+Tsuruoka%2E+2016%2E+Tree%2Dto%2Dsequence+attentional+neural+machine+translation%2E+In+ACL%2C+pages+823%E2%80%93833%2E)
10. Zhenxin Fu, Xiaoye Tan, Nanyun Peng, Dongyan Zhao, and Rui Yan. 2018. [Style transfer in text: Exploration and evaluation](https://md.research.elamur.ai/free/en/papers/fu-2017-style-transfer-text-exploration-evaluation/). In AAAI, pages 663–670.
11. Rafael Gómez-Bombarelli, Jennifer N Wei, David Duvenaud, José Miguel Hernández-Lobato, Ben-jamı́n Sánchez-Lengeling, Dennis Sheberla, Jorge Aguilera-Iparraguirre, Timothy D Hirzel, Ryan P Adams, and Alán Aspuru-Guzik. 2018. Automatic chemical design using a data-driven continuous representation… [find](https://scholar.google.com/scholar?q=Rafael+Go%CC%81mez%2DBombarelli%2C+Jennifer+N+Wei%2C+David+Duvenaud%2C+Jose%CC%81+Miguel+Herna%CC%81ndez%2DLobato%2C+Ben%2Djam%C4%B1%CC%81n+Sa%CC%81nchez%2DLengeling%2C+Dennis+Sheberla%2C+Jorge+Aguilera%2DIparraguirre%2C+Timothy+D+Hirzel%2C+Ryan+P+Adams%2C+a)
12. Ning Miao, Hao Zhou, Lili Mou, Rui Yan, and Lei Li. 2019. CGMH: Constrained sentence generation by Metropolis-Hastings sampling. In AAAI. [find](https://scholar.google.com/scholar?q=Ning+Miao%2C+Hao+Zhou%2C+Lili+Mou%2C+Rui+Yan%2C+and+Lei+Li%2E+2019%2E+CGMH%3A+Constrained+sentence+generation+by+Metropolis%2DHastings+sampling%2E+In+AAAI%2E)
13. Ankush Gupta, Arvind Agarwal, Prawaan Singh, and Piyush Rai. 2018. [A deep generative framework for paraphrase generation](https://md.research.elamur.ai/free/en/papers/gupta-2017-deep-generative-framework-paraphrase-generation/). In AAAI, pages 5149–5156.
14. Vinod Nair and Geoffrey E Hinton. 2010. Rectified linear units improve restricted boltzmann machines. In ICML, pages 807–814. [find](https://scholar.google.com/scholar?q=Vinod+Nair+and+Geoffrey+E+Hinton%2E+2010%2E+Rectified+linear+units+improve+restricted+boltzmann+machines%2E+In+ICML%2C+pages+807%E2%80%93814%2E)
15. Zhiting Hu, Zichao Yang, Xiaodan Liang, Ruslan Salakhutdinov, and Eric P. Xing. 2017. [Toward controlled generation of text](https://md.research.elamur.ai/free/en/papers/hu-2017-toward-controlled-generation-text/). In ICML, pages 1587– 1596.
16. Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. [BLEU: A method for automatic evaluation of machine translation](https://md.research.elamur.ai/free/en/papers/papineni-2002-bleu-method-automatic-evaluation-machine/). In ACL, pages 311–318.
17. Vineet John, Lili Mou, Hareesh Bahuleyan, and Olga Vechtomova. 2018. Disentangled representation learning for text style transfer. arXiv preprint arXiv:1808.04339. — [arXiv:1808.04339](https://arxiv.org/abs/1808.04339) [find](https://scholar.google.com/scholar?q=Vineet+John%2C+Lili+Mou%2C+Hareesh+Bahuleyan%2C+and+Olga+Vechtomova%2E+2018%2E+Disentangled+representation+learning+for+text+style+transfer%2E+arXiv+preprint+arXiv%3A1808%2E04339%2E+%E2%80%94+%5BarXiv%3A1808%2E04339%5D%28https%3A%2F%2Farxiv%2Eo)
18. Stanislau Semeniuta, Aliaksei Severyn, and Erhardt Barth. 2017. A hybrid convolutional variational autoencoder for text generation. In EMNLP, pages 627–637. [find](https://scholar.google.com/scholar?q=Stanislau+Semeniuta%2C+Aliaksei+Severyn%2C+and+Erhardt+Barth%2E+2017%2E+A+hybrid+convolutional+variational+autoencoder+for+text+generation%2E+In+EMNLP%2C+pages+627%E2%80%93637%2E)
19. Diederik P. Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In ICLR. [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+ICLR%2E)
20. Iulian Vlad Serban, Alessandro Sordoni, Ryan Lowe, Laurent Charlin, Joelle Pineau, Aaron C Courville, and Yoshua Bengio. 2017. [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/). In AAAI, pages 3295–3301.
21. Diederik P Kingma and Max Welling. 2014. Autoencoding variational Bayes. In ICLR. [find](https://scholar.google.com/scholar?q=Diederik+P+Kingma+and+Max+Welling%2E+2014%2E+Autoencoding+variational+Bayes%2E+In+ICLR%2E)
22. Adhiguna Kuncoro, Miguel Ballesteros, Lingpeng Kong, Chris Dyer, Graham Neubig, and Noah A Smith. 2017. What do recurrent neural network grammars learn about syntax? In EACL, pages 1249–1258. [find](https://scholar.google.com/scholar?q=Adhiguna+Kuncoro%2C+Miguel+Ballesteros%2C+Lingpeng+Kong%2C+Chris+Dyer%2C+Graham+Neubig%2C+and+Noah+A+Smith%2E+2017%2E+What+do+recurrent+neural+network+grammars+learn+about+syntax%3F+In+EACL%2C+pages+1249%E2%80%931258%2E)
23. Matt J. Kusner, Brooks Paige, and José Miguel Hernández-Lobato. 2017. Grammar variational autoencoder. In ICML, pages 1945–1954. [find](https://scholar.google.com/scholar?q=Matt+J%2E+Kusner%2C+Brooks+Paige%2C+and+Jose%CC%81+Miguel+Herna%CC%81ndez%2DLobato%2E+2017%2E+Grammar+variational+autoencoder%2E+In+ICML%2C+pages+1945%E2%80%931954%2E)
24. Juncen Li, Robin Jia, He He, and Percy Liang. 2018a. [Delete, Retrieve, Generate: a simple approach to sentiment and style transfer](https://md.research.elamur.ai/free/en/papers/li-2018-delete-retrieve-generate-simple-approach/). In ACL, pages 1865– 1874.
25. Junhui Li, Deyi Xiong, Zhaopeng Tu, Muhua Zhu, Min Zhang, and Guodong Zhou. 2017. Modeling source syntax for neural machine translation. In ACL, pages 688–697. [find](https://scholar.google.com/scholar?q=Junhui+Li%2C+Deyi+Xiong%2C+Zhaopeng+Tu%2C+Muhua+Zhu%2C+Min+Zhang%2C+and+Guodong+Zhou%2E+2017%2E+Modeling+source+syntax+for+neural+machine+translation%2E+In+ACL%2C+pages+688%E2%80%93697%2E)
26. Juntao Li, Yan Song, Haisong Zhang, Dongmin Chen, Shuming Shi, Dongyan Zhao, and Rui Yan. 2018b. Generating classical chinese poems via conditional variational autoencoder and adversarial training. In EMNLP, pages 3890–3900. [find](https://scholar.google.com/scholar?q=Juntao+Li%2C+Yan+Song%2C+Haisong+Zhang%2C+Dongmin+Chen%2C+Shuming+Shi%2C+Dongyan+Zhao%2C+and+Rui+Yan%2E+2018b%2E+Generating+classical+chinese+poems+via+conditional+variational+autoencoder+and+adversarial+training%2E+In)
27. Lemao Liu, Muhua Zhu, and Shuming Shi. 2018. Improving sequence-to-sequence constituency parsing. In AAAI, pages 4873–4880. [find](https://scholar.google.com/scholar?q=Lemao+Liu%2C+Muhua+Zhu%2C+and+Shuming+Shi%2E+2018%2E+Improving+sequence%2Dto%2Dsequence+constituency+parsing%2E+In+AAAI%2C+pages+4873%E2%80%934880%2E)
28. Tomáš Mikolov, Martin Karafiát, Lukáš Burget, Jan Černockỳ, and Sanjeev Khudanpur. 2010. Recurrent neural network based language model. In IN-TERSPEECH. [find](https://scholar.google.com/scholar?q=Toma%CC%81s%CC%8C+Mikolov%2C+Martin+Karafia%CC%81t%2C+Luka%CC%81s%CC%8C+Burget%2C+Jan+C%CC%8Cernocky%CC%80%2C+and+Sanjeev+Khudanpur%2E+2010%2E+Recurrent+neural+network+based+language+model%2E+In+IN%2DTERSPEECH%2E)
29. Yikang Shen, Zhouhan Lin, Chin-Wei Huang, and Aaron Courville. 2017. Neural language modeling by jointly learning syntax and lexicon. In ICLR. [find](https://scholar.google.com/scholar?q=Yikang+Shen%2C+Zhouhan+Lin%2C+Chin%2DWei+Huang%2C+and+Aaron+Courville%2E+2017%2E+Neural+language+modeling+by+jointly+learning+syntax+and+lexicon%2E+In+ICLR%2E)
30. Eric Tzeng, Judy Hoffman, Kate Saenko, and Trevor Darrell. 2017. Adversarial discriminative domain adaptation. In CVPR, pages 7167–7176. [find](https://scholar.google.com/scholar?q=Eric+Tzeng%2C+Judy+Hoffman%2C+Kate+Saenko%2C+and+Trevor+Darrell%2E+2017%2E+Adversarial+discriminative+domain+adaptation%2E+In+CVPR%2C+pages+7167%E2%80%937176%2E)
31. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. [Attention is all you need](https://md.research.elamur.ai/free/en/papers/vaswani-2017-attention-all-need/). In NIPS, pages 5998–6008.
32. Oriol Vinyals, Łukasz Kaiser, Terry Koo, Slav Petrov, Ilya Sutskever, and Geoffrey Hinton. 2015. Grammar as a foreign language. In NIPS, pages 2773– 2781. [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+2015%2E+Grammar+as+a+foreign+language%2E+In+NIPS%2C+pages+2773%E2%80%93+2781%2E)
33. Rongxiang Weng, Shujian Huang, Zaixiang Zheng, XIN-YU DAI, and CHEN Jiajun. 2017. Neural machine translation with word predictions. In EMNLP, pages 136–145. [find](https://scholar.google.com/scholar?q=Rongxiang+Weng%2C+Shujian+Huang%2C+Zaixiang+Zheng%2C+XIN%2DYU+DAI%2C+and+CHEN+Jiajun%2E+2017%2E+Neural+machine+translation+with+word+predictions%2E+In+EMNLP%2C+pages+136%E2%80%93145%2E)
34. Kaizhong Zhang and Dennis Shasha. 1989. Simple fast algorithms for the editing distance between trees and related problems. SIAM journal on computing, 18(6):1245–1262. [find](https://scholar.google.com/scholar?q=Kaizhong+Zhang+and+Dennis+Shasha%2E+1989%2E+Simple+fast+algorithms+for+the+editing+distance+between+trees+and+related+problems%2E+SIAM+journal+on+computing%2C+18%286%29%3A1245%E2%80%931262%2E)
35. Shuming Ma, Xu Sun, Yizhong Wang, and Junyang Lin. 2018. Bag-of-words as target for neural machine translation. In ACL, pages 332–338. [find](https://scholar.google.com/scholar?q=Shuming+Ma%2C+Xu+Sun%2C+Yizhong+Wang%2C+and+Junyang+Lin%2E+2018%2E+Bag%2Dof%2Dwords+as+target+for+neural+machine+translation%2E+In+ACL%2C+pages+332%E2%80%93338%2E)
36. Junbo Jake Zhao, Yoon Kim, Kelly Zhang, Alexander M. Rush, and Yann LeCun. 2018. Adversarially regularized autoencoders. In ICML, pages 5897– 5906. [find](https://scholar.google.com/scholar?q=Junbo+Jake+Zhao%2C+Yoon+Kim%2C+Kelly+Zhang%2C+Alexander+M%2E+Rush%2C+and+Yann+LeCun%2E+2018%2E+Adversarially+regularized+autoencoders%2E+In+ICML%2C+pages+5897%E2%80%93+5906%2E)
37. Mitchell P Marcus, Mary Ann Marcinkiewicz, and Beatrice Santorini. 1993. [Building a large annotated corpus of english: The Penn Treebank](https://md.research.elamur.ai/free/en/papers/marcus-1993-building-large-annotated-corpus-english/). Computational linguistics, 19(2):313–330.
38. Hao Zhou, Zhaopeng Tu, Shujian Huang, Xiaohua Liu, Hang Li, and Jiajun Chen. 2017. Chunk-based bi-scale decoder for neural machine translation. In ACL, pages 580–586. [find](https://scholar.google.com/scholar?q=Hao+Zhou%2C+Zhaopeng+Tu%2C+Shujian+Huang%2C+Xiaohua+Liu%2C+Hang+Li%2C+and+Jiajun+Chen%2E+2017%2E+Chunk%2Dbased+bi%2Dscale+decoder+for+neural+machine+translation%2E+In+ACL%2C+pages+580%E2%80%93586%2E)

*Updated 24 October 2026*