---
title: "Controlling Linguistic Style Aspects in Neural — Ficler 2017"
description: "Neural text generators are usually steered toward content rather than style, and earlier style-control work typically handled one attribute at a time."
authors: ["Jessica Ficler", "Yoav Goldberg"]
year: 2017
venue: "Proceedings of the Workshop on Stylistic Variation"
source: "https://aclanthology.org/W17-4912/"
doi: "10.18653/v1/w17-4912"
arxiv: "1707.02633"
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/ficler-2017-controlling-linguistic-style-aspects-neural/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/ficler-2017-controlling-linguistic-style-aspects-neural/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2017](https://md.research.elamur.ai/free/en/papers/2017/page/2/) / Controlling Linguistic Style Aspects in Neural Language Generation

# Controlling Linguistic Style Aspects in Neural Language Generation

**Authors:** [Jessica Ficler](https://md.research.elamur.ai/free/en/authors/jessica-ficler/), [Yoav Goldberg](https://md.research.elamur.ai/free/en/authors/yoav-goldberg/) · **Year:** 2017 · **Venue:** Proceedings of the Workshop on Stylistic Variation · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/W17-4912/) · [PDF](https://aclanthology.org/W17-4912.pdf) · [DOI 10.18653/v1/w17-4912](https://doi.org/10.18653/v1/w17-4912) · [arXiv 1707.02633](https://arxiv.org/abs/1707.02633) · [OpenAlex](https://openalex.org/W2735574368)

**Citations:** 265 citations (OpenAlex, 2026-10-14) · [159](https://md.research.elamur.ai/free/en/papers/ficler-2017-controlling-linguistic-style-aspects-neural/cited-by/) in our library, of the 140884 papers whose bibliographies we read

## Summary
Neural text generators are usually steered toward content rather than style, and earlier style-control work typically handled one attribute at a time. Ficler and Goldberg ask whether several stylistic dimensions can be controlled jointly alongside content. They train an LSTM language model with a BPE subword vocabulary. The model is conditioned on a vector built by concatenating learned embeddings of the desired attribute values, and this vector is appended to the input at every time step. The data are Rotten Tomatoes movie reviews split into sentences. Labels come either from site meta-data, such as reviewer scores and critic versus audience origin, or from simple heuristics over word lists, function words and part-of-speech distributions. Six attributes are used: two content ones (theme, sentiment) and four stylistic ones (length, descriptiveness, personal voice, professional style). The conditioned model reaches lower perplexity than unconditioned baselines, mostly produces sentences matching the requested settings, and copes with attribute combinations absent from training. The work shows that a plain conditioned LM trained on noisy, automatically derived labels can control multiple attributes on naturally long sentences.

## Key points
- **Corpus:** 1,002,625 Rotten Tomatoes reviews covering 7,500 movies, segmented into sentences.
- **Sentiment labels:** derived from scores normalized to a 0–5 scale. Grades 0–2 count as negative, 3 as neutral and 4–5 as positive, with "none" used when no score is available.
- **Attributes and values:**
  - Theme: Plot, Acting, Production, Effects or Other.
  - Length: ≤10, 11–20, 21–40 or >40 words.
  - Professional, Personal and Descriptive: true or false.
- **Generalization test:** the authors removed the 75,421 training sentences labeled both theme:plot and personal:true and retrained the model.
  - All generated sentences for this unseen combination contained personal pronouns.
  - 82.4% matched the plot theme, compared with 97.8% for a model trained on the full data.
- **Comparison with Hu et al. (2017):** that VAE-plus-discriminator approach was limited to sentences of up to 16 words and two aspects (sentiment, tense). This model needs no discriminator and handles six aspects on full-length sentences.

*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/)

Topics: [Text generation](https://md.research.elamur.ai/free/en/topics/text-generation/)

## Cite

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

```bibtex
@inproceedings{ficler2017controlling,
  title = {{Controlling Linguistic Style Aspects in Neural Language Generation}},
  author = {Ficler, Jessica and Goldberg, Yoav},
  booktitle = {Proceedings of the Workshop on Stylistic Variation},
  year = {2017},
  doi = {10.18653/v1/w17-4912},
  eprint = {1707.02633},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.18653/v1/w17-4912}
}
```

- [← previous Neural AMR: Sequence-to-Sequence Models for Parsing and Generation](https://md.research.elamur.ai/free/en/papers/konstas-2017-neural-amr-sequence-sequence-models/)
- [next → Data Augmentation for Low-Resource Neural Machine Translation](https://md.research.elamur.ai/free/en/papers/fadaee-2017-data-augmentation-low-resource-neural/)
- [↑ back to papers of 2017](https://md.research.elamur.ai/free/en/papers/2017/page/2/)

## References

29 references, 11 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Fadi Abu Sheikha and Diana Inkpen. 2011. Generation of formal and informal sentences. In Proceedings of the 13th European Workshop on Natural Language Generation. Association for Computational Linguistics, Nancy, France, pages 187–193. [http://www.aclweb.org/anthology/W11-2826](http://www.aclweb.org/anthology/W11-2826). [↗](http://www.aclweb.org/anthology/W11-2826)
2. John A Bateman and Cecile Paris. 1989. Phrasing a text in terms the user can understand. In IJCAI. pages 1511–1517. [find](https://scholar.google.com/scholar?q=John+A+Bateman+and+Cecile+Paris%2E+1989%2E+Phrasing+a+text+in+terms+the+user+can+understand%2E+In+IJCAI%2E+pages+1511%E2%80%931517%2E)
3. Douglas Biber and Susan Conrad. 2009. Register, genre, and style. Cambridge University Press. [find](https://scholar.google.com/scholar?q=Douglas+Biber+and+Susan+Conrad%2E+2009%2E+Register%2C+genre%2C+and+style%2E+Cambridge+University+Press%2E)
4. Ondřej Dušek and Filip Jurcicek. 2016a. A context-aware natural language generator for dialogue systems. In Proceedings of the 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue. Association for Computational Linguistics, Los Angeles, pages 185–190. [http://www.aclweb.org/a…](http://www.aclweb.org/a…) [↗](http://www.aclweb.org/a…)
5. Ondřej Dušek and Filip Jurcicek. 2016b. Sequence-to-sequence generation for spoken dialogue via deep syntax trees and strings. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume David D McDonald and James D Pustejovsky. 1985. A computational theory o… [find](https://scholar.google.com/scholar?q=Ondr%CC%8Cej+Dus%CC%8Cek+and+Filip+Jurcicek%2E+2016b%2E+Sequence%2Dto%2Dsequence+generation+for+spoken+dialogue+via+deep+syntax+trees+and+strings%2E+In+Proceedings+of+the+54th+Annual+Meeting+of+the+Association+for+Comput)
6. Cong Duy Vu Hoang, Gholamreza Haffari, and Trevor Cohn. 2016. Incorporating side information into recurrent neural network language models. In Proceedings of NAACL-HLT. pages 1250–1255. [find](https://scholar.google.com/scholar?q=Cong+Duy+Vu+Hoang%2C+Gholamreza+Haffari%2C+and+Trevor+Cohn%2E+2016%2E+Incorporating+side+information+into+recurrent+neural+network+language+models%2E+In+Proceedings+of+NAACL%2DHLT%2E+pages+1250%E2%80%931255%2E)
7. Hongyuan Mei, Mohit Bansal, and Matthew R. Walter. 2016. What to talk about and how? selective generation using lstms with coarse-to-fine alignment. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Asso… [find](https://scholar.google.com/scholar?q=Hongyuan+Mei%2C+Mohit+Bansal%2C+and+Matthew+R%2E+Walter%2E+2016%2E+What+to+talk+about+and+how%3F+selective+generation+using+lstms+with+coarse%2Dto%2Dfine+alignment%2E+In+Proceedings+of+the+2016+Conference+of+the+North+) [our card](https://md.research.elamur.ai/free/en/papers/mei-2016-what-talk-about-how-selective/)
8. Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. MIT Press, volume 9, pages 1735–1780. [find](https://scholar.google.com/scholar?q=Sepp+Hochreiter+and+Ju%CC%88rgen+Schmidhuber%2E+1997%2E+Long+short%2Dterm+memory%2E+MIT+Press%2C+volume+9%2C+pages+1735%E2%80%931780%2E)
9. Eduard Hovy. 1987. Generating natural language under pragmatic constraints. Journal of Pragmatics, volume 11, pages 689–719. [find](https://scholar.google.com/scholar?q=Eduard+Hovy%2E+1987%2E+Generating+natural+language+under+pragmatic+constraints%2E+Journal+of+Pragmatics%2C+volume+11%2C+pages+689%E2%80%93719%2E)
10. Zhiting Hu, Zichao Yang, Xiaodan Liang, Ruslan Salakhutdinov, and Eric P Xing. 2017. Controllable text generation. In Proc. of ICML. [find](https://scholar.google.com/scholar?q=Zhiting+Hu%2C+Zichao+Yang%2C+Xiaodan+Liang%2C+Ruslan+Salakhutdinov%2C+and+Eric+P+Xing%2E+2017%2E+Controllable+text+generation%2E+In+Proc%2E+of+ICML%2E)
11. Tomas Mikolov, Martin Karafiát, Lukas Burget, Jan Cernockỳ, and Sanjeev Khudanpur. 2010. Recurrent neural network based language model. In Interspeech. volume 2, page 3. [find](https://scholar.google.com/scholar?q=Tomas+Mikolov%2C+Martin+Karafia%CC%81t%2C+Lukas+Burget%2C+Jan+Cernocky%CC%80%2C+and+Sanjeev+Khudanpur%2E+2010%2E+Recurrent+neural+network+based+language+model%2E+In+Interspeech%2E+volume+2%2C+page+3%2E)
12. Chloé Kiddon, Luke Zettlemoyer, and Yejin Choi. 2016. Globally coherent text generation with neural checklist models. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Austin, Texas, pages 329–339. [https://aclweb.or…](https://aclweb.or…) [↗](https://aclweb.or…) [our card](https://md.research.elamur.ai/free/en/papers/kiddon-2016-globally-coherent-text-generation-neural/)
13. Kate G Niederhoffer and James W Pennebaker. 2002. Linguistic style matching in social interaction. Journal of Language and Social Psychology, volume 21, pages 337–360. [find](https://scholar.google.com/scholar?q=Kate+G+Niederhoffer+and+James+W+Pennebaker%2E+2002%2E+Linguistic+style+matching+in+social+interaction%2E+Journal+of+Language+and+Social+Psychology%2C+volume+21%2C+pages+337%E2%80%93360%2E)
14. Ellie Pavlick and Ani Nenkova. 2015. Inducing lexical style properties for paraphrase and genre differentiation. In Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistic… [find](https://scholar.google.com/scholar?q=Ellie+Pavlick+and+Ani+Nenkova%2E+2015%2E+Inducing+lexical+style+properties+for+paraphrase+and+genre+differentiation%2E+In+Proceedings+of+the+2015+Conference+of+the+North+American+Chapter+of+the+Association+)
15. Yuta Kikuchi, Graham Neubig, Ryohei Sasano, Hiroya Takamura, and Manabu Okumura. 2016. Controlling output length in neural encoder-decoders. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Austin, Texas, pages 1328… [find](https://scholar.google.com/scholar?q=Yuta+Kikuchi%2C+Graham+Neubig%2C+Ryohei+Sasano%2C+Hiroya+Takamura%2C+and+Manabu+Okumura%2E+2016%2E+Controlling+output+length+in+neural+encoder%2Ddecoders%2E+In+Proceedings+of+the+2016+Conference+on+Empirical+Methods+) [our card](https://md.research.elamur.ai/free/en/papers/kikuchi-2016-controlling-output-length-neural-encoder/)
16. Ellie Pavlick and Joel Tetreault. 2016. An empirical analysis of formality in online communication. Transactions of the Association for Computational Linguistics, volume 4, pages 61–74. [find](https://scholar.google.com/scholar?q=Ellie+Pavlick+and+Joel+Tetreault%2E+2016%2E+An+empirical+analysis+of+formality+in+online+communication%2E+Transactions+of+the+Association+for+Computational+Linguistics%2C+volume+4%2C+pages+61%E2%80%9374%2E) [our card](https://md.research.elamur.ai/free/en/papers/pavlick-2016-empirical-analysis-formality-online-communication/)
17. Rémi Lebret, David Grangier, and Michael Auli. 2016. Neural text generation from structured data with application to the biography domain. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Austin, Texas, pages 1203–… [find](https://scholar.google.com/scholar?q=Re%CC%81mi+Lebret%2C+David+Grangier%2C+and+Michael+Auli%2E+2016%2E+Neural+text+generation+from+structured+data+with+application+to+the+biography+domain%2E+In+Proceedings+of+the+2016+Conference+on+Empirical+Methods+i) [our card](https://md.research.elamur.ai/free/en/papers/lebret-2016-neural-text-generation-structured-data/)
18. Richard Power, Donia Scott, and Nadjet Bouayad-Agha. 2003. Generating texts with style. In Proc. of CiCLING. Springer, pages 444–452. [find](https://scholar.google.com/scholar?q=Richard+Power%2C+Donia+Scott%2C+and+Nadjet+Bouayad%2DAgha%2E+2003%2E+Generating+texts+with+style%2E+In+Proc%2E+of+CiCLING%2E+Springer%2C+pages+444%E2%80%93452%2E)
19. Alec Radford, Rafal Jozefowicz, and Ilya Sutskever. 2017. Learning to generate reviews and discovering sentiment. arXiv preprint arXiv:1704.01444. [find](https://scholar.google.com/scholar?q=Alec+Radford%2C+Rafal+Jozefowicz%2C+and+Ilya+Sutskever%2E+2017%2E+Learning+to+generate+reviews+and+discovering+sentiment%2E+arXiv+preprint+arXiv%3A1704%2E01444%2E) [our card](https://md.research.elamur.ai/free/en/papers/radford-2017-learning-generate-reviews-discovering-sentiment/)
20. Jiwei Li, Michel Galley, Chris Brockett, Georgios Spithourakis, Jianfeng Gao, and Bill Dolan. 2016. A persona-based neural conversation model. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics… [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+2016%2E+A+persona%2Dbased+neural+conversation+model%2E+In+Proceedings+of+the+54th+Annual+Meeting+of+the+Associat) [our card](https://md.research.elamur.ai/free/en/papers/li-2016-persona-based-neural-conversation-model/)
21. Ehud Reiter and Sandra Williams. 2010. Generating texts in different styles. In The Structure of Style, Springer, pages 59–75. [find](https://scholar.google.com/scholar?q=Ehud+Reiter+and+Sandra+Williams%2E+2010%2E+Generating+texts+in+different+styles%2E+In+The+Structure+of+Style%2C+Springer%2C+pages+59%E2%80%9375%2E)
22. Rico Sennrich, Barry Haddow, and Alexandra Birch. 2016. Controlling politeness in neural machine translation via side constraints. In Proceedings of NAACL-HLT. 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%2DHLT%2E+pages+35%E2%80%9340%2E) [our card](https://md.research.elamur.ai/free/en/papers/sennrich-2016-controlling-politeness-neural-machine-translation/)
23. Zachary C Lipton, Sharad Vikram, and Julian McAuley. 2015. Capturing meaning in product reviews with character-level generative text models. arXiv preprint arXiv:1511.03683. — [arXiv:1511.03683](https://arxiv.org/abs/1511.03683) [find](https://scholar.google.com/scholar?q=Zachary+C+Lipton%2C+Sharad+Vikram%2C+and+Julian+McAuley%2E+2015%2E+Capturing+meaning+in+product+reviews+with+character%2Dlevel+generative+text+models%2E+arXiv+preprint+arXiv%3A1511%2E03683%2E+%E2%80%94+%5BarXiv%3A1511%2E03683%5D%28https)
24. Jian Tang, Yifan Yang, Sam Carton, Ming Zhang, and Qiaozhu Mei. 2016. Context-aware natural language generation with recurrent neural networks. arXiv preprint arXiv:1611.09900. — [arXiv:1611.09900](https://arxiv.org/abs/1611.09900) [find](https://scholar.google.com/scholar?q=Jian+Tang%2C+Yifan+Yang%2C+Sam+Carton%2C+Ming+Zhang%2C+and+Qiaozhu+Mei%2E+2016%2E+Context%2Daware+natural+language+generation+with+recurrent+neural+networks%2E+arXiv+preprint+arXiv%3A1611%2E09900%2E+%E2%80%94+%5BarXiv%3A1611%2E09900%5D%28ht)
25. François Mairesse and Marilyn A Walker. 2011. Controlling user perceptions of linguistic style: Trainable generation of personality traits. MIT Press, volume 37, pages 455–488. [find](https://scholar.google.com/scholar?q=Franc%CC%A7ois+Mairesse+and+Marilyn+A+Walker%2E+2011%2E+Controlling+user+perceptions+of+linguistic+style%3A+Trainable+generation+of+personality+traits%2E+MIT+Press%2C+volume+37%2C+pages+455%E2%80%93488%2E)
26. Tsung-Hsien Wen, Milica Gasic, Nikola Mrkšić, Pei-Hao Su, David Vandyke, and Steve Young. 2015. Semantically conditioned lstm-based natural language generation for spoken dialogue systems. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. Association for Co… [find](https://scholar.google.com/scholar?q=Tsung%2DHsien+Wen%2C+Milica+Gasic%2C+Nikola+Mrks%CC%8Cic%CC%81%2C+Pei%2DHao+Su%2C+David+Vandyke%2C+and+Steve+Young%2E+2015%2E+Semantically+conditioned+lstm%2Dbased+natural+language+generation+for+spoken+dialogue+systems%2E+In+Procee) [our card](https://md.research.elamur.ai/free/en/papers/wen-2015-semantically-conditioned-lstm-based-natural/)
27. Wei Xu, Alan Ritter, Bill Dolan, Ralph Grishman, and Colin Cherry. 2012. Paraphrasing for style. In Proceedings of COLING 2012. [find](https://scholar.google.com/scholar?q=Wei+Xu%2C+Alan+Ritter%2C+Bill+Dolan%2C+Ralph+Grishman%2C+and+Colin+Cherry%2E+2012%2E+Paraphrasing+for+style%2E+In+Proceedings+of+COLING+2012%2E) [our card](https://md.research.elamur.ai/free/en/papers/xu-2012-paraphrasing-style/)
28. The COLING 2012 Organizing Committee, Mumbai, India, pages 2899– 2914. [http://www.aclweb.org/anthology/C12-1177](http://www.aclweb.org/anthology/C12-1177). [↗](http://www.aclweb.org/anthology/C12-1177) [our card](https://md.research.elamur.ai/free/en/papers/xu-2012-paraphrasing-style/)
29. Yinfei Yang and Ani Nenkova. 2014. Detecting information-dense texts in multiple news domains. In AAAI. pages 1650–1656. [find](https://scholar.google.com/scholar?q=Yinfei+Yang+and+Ani+Nenkova%2E+2014%2E+Detecting+information%2Ddense+texts+in+multiple+news+domains%2E+In+AAAI%2E+pages+1650%E2%80%931656%2E)