---
title: "Generating Sentences by Editing Prototypes — Guu 2017"
description: "Standard neural language models build each sentence from nothing, usually word by word."
authors: ["Kelvin Guu", "Tatsunori B. Hashimoto", "Yonatan Oren", "Percy Liang"]
year: 2017
venue: "arXiv:1709.08878"
source: "https://arxiv.org/abs/1709.08878"
doi: "10.48550/arxiv.1709.08878"
arxiv: "1709.08878"
licence: "arXiv — non-exclusive license 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/guu-2017-generating-sentences-editing-prototypes/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/guu-2017-generating-sentences-editing-prototypes/)

[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/) / Generating Sentences by Editing Prototypes

# Generating Sentences by Editing Prototypes

**Authors:** [Kelvin Guu](https://md.research.elamur.ai/free/en/authors/kelvin-guu/), [Tatsunori B. Hashimoto](https://md.research.elamur.ai/free/en/authors/tatsunori-b-hashimoto/), [Yonatan Oren](https://md.research.elamur.ai/free/en/authors/yonatan-oren/), [Percy Liang](https://md.research.elamur.ai/free/en/authors/percy-liang/) · **Year:** 2017 · **Venue:** arXiv:1709.08878 · **Licence:** [arXiv — non-exclusive license to distribute](http://arxiv.org/licenses/nonexclusive-distrib/1.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/1709.08878) · [PDF](https://arxiv.org/pdf/1709.08878) · [DOI 10.48550/arxiv.1709.08878](https://doi.org/10.48550/arxiv.1709.08878) · [arXiv 1709.08878](https://arxiv.org/abs/1709.08878) · [OpenAlex](https://openalex.org/W2963018920)

**Citations:** 289 citations (openalex-snapshot · 2026-10-14) · [115](#cited-by) in our library, of the 140673 papers whose bibliographies we read

## Summary
Standard neural language models build each sentence from nothing, usually word by word. They often drift toward bland, generic output, and simple tricks to add variety tend to damage grammaticality. Guu, Hashimoto, Oren and Liang propose a different generative story inspired by how people draft and revise. The model first picks a real sentence from the training corpus as a prototype. It then samples a latent edit vector, and an attention-based neural editor rewrites the prototype according to that vector. Training maximizes a lower bound on likelihood with two approximations. Only lexically close prototypes are considered, found efficiently with locality sensitive hashing. An inverse editor acts as a variational encoder, giving an ELBO in VAE style. On the Yelp corpus and the One Billion Word Benchmark, the approach lowers perplexity, and human judges rate its outputs higher. The learned edit vectors also beat a sentence VAE on similarity, controlled generation and analogy tasks. The work shows that retrieving and editing corpus examples is a strong inductive bias for unconditional text generation.

## Key points
- Compared with from-scratch neural LMs, perplexity is 13 points lower on Yelp, and the One Billion Word Benchmark shows a 7-point reduction.
- On Yelp, 70% of test sentences lie within word-token Jaccard distance 0.5 of some training sentence, although exact repeats are almost absent.
- Prototype neighborhoods are restricted to Jaccard distance below 0.5 and precomputed with LSH plus minhashing.
- Human review of 250 neighbor pairs from Yelp found:
  - 35.2% were full paraphrases.
  - 84% were at least roughly equivalent.
  - Only 7.2% involved negation or a topic shift.
- Architecture:
  - The editor uses a 3-layer bidirectional LSTM encoder with GloVe inputs and a 3-layer attentive LSTM decoder, with the edit vector fed in at every decoding step.
  - Light interpolation with a plain NLM covers test sentences that have no close prototype.
  - Code and data are released on CodaLab.

*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

115 papers of our library cite it (of the 140673 whose bibliographies we read); 16 of them have a page here, 99 not yet.

- [Controllable Paraphrase Generation with a Syntactic Exemplar](https://md.research.elamur.ai/free/en/papers/chen-2019-controllable-paraphrase-generation-syntactic-exemplar/)
- [An Empirical Survey of Data Augmentation for Limited Data Learning in NLP](https://md.research.elamur.ai/free/en/papers/chen-2023-empirical-survey-data-augmentation-limited/)
- [Adversarial Example Generation with Syntactically Controlled Paraphrase Networks](https://md.research.elamur.ai/free/en/papers/iyyer-2018-adversarial-example-generation-syntactically-controlled/)
- [Reformulating Unsupervised Style Transfer as Paraphrase Generation](https://md.research.elamur.ai/free/en/papers/krishna-2020-reformulating-unsupervised-style-transfer-as/)
- [Pre-training via Paraphrasing](https://md.research.elamur.ai/free/en/papers/lewis-2020-pre-training-paraphrasing/)
- [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/)
- [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/)
- [What Makes Good In-Context Examples for GPT-3?](https://md.research.elamur.ai/free/en/papers/liu-2022-what-makes-good-context-examples/)
- [An efficient framework for learning sentence representations](https://md.research.elamur.ai/free/en/papers/logeswaran-2018-efficient-framework-learning-sentence-representations/)
- [Diff4TST: Masked Diffusion Language Model for Text Style Transfer](https://md.research.elamur.ai/free/en/papers/ma-2026-diff4tst-masked-diffusion-language-model/)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://md.research.elamur.ai/free/en/papers/min-2023-factscore-fine-grained-atomic-evaluation/)
- [ToTTo: A Controlled Table-To-Text Generation Dataset](https://md.research.elamur.ai/free/en/papers/parikh-2020-totto-controlled-table-text-generation/)
- [Unsupervised Question Decomposition for Question Answering](https://md.research.elamur.ai/free/en/papers/perez-2020-unsupervised-question-decomposition-question-answering/)
- [Retrieve and Refine: Improved Sequence Generation Models For Dialogue](https://md.research.elamur.ai/free/en/papers/weston-2018-retrieve-refine-improved-sequence-generation/)
- [Exploring Pre-trained Language Models for Event Extraction and Generation](https://md.research.elamur.ai/free/en/papers/yang-2019-exploring-pre-trained-language-models/)
- [PAWS: Paraphrase Adversaries from Word Scrambling](https://md.research.elamur.ai/free/en/papers/zhang-2019-paws-paraphrase-adversaries-word-scrambling/)

## Cite

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

```bibtex
@misc{guu2017generating,
  title = {{Generating Sentences by Editing Prototypes}},
  author = {Guu, Kelvin and Hashimoto, Tatsunori B. and Oren, Yonatan and Liang, Percy},
  year = {2017},
  doi = {10.48550/arxiv.1709.08878},
  eprint = {1709.08878},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.1709.08878}
}
```

- [← previous Generating and Exploiting Large-scale Pseudo Training Data for Zero Pronoun Resolution](https://md.research.elamur.ai/free/en/papers/liu-2017-generating-exploiting-large-scale-pseudo/)
- [next → Get that into your head: Tigre vowel harmonies as templatic](https://md.research.elamur.ai/free/en/papers/lingbulk-2017-faust-get-that-into-your-head/)
- [↑ back to papers of 2017](https://md.research.elamur.ai/free/en/papers/2017/page/2/)

## References

32 references, 10 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. E. Agirre, C. Banea, C. Cardie, D. M. Cer, M. T. Diab, A. Gonzalez-Agirre, W. Guo, R. Mihalcea, G. Rigau, and J. Wiebe. 2014. SemEval-2014 Task 10: Multilingual semantic textual similarity. In International Conference on Computational Linguistics (COLING), pages 81–91. [find](https://scholar.google.com/scholar?q=E%2E+Agirre%2C+C%2E+Banea%2C+C%2E+Cardie%2C+D%2E+M%2E+Cer%2C+M%2E+T%2E+Diab%2C+A%2E+Gonzalez%2DAgirre%2C+W%2E+Guo%2C+R%2E+Mihalcea%2C+G%2E+Rigau%2C+and+J%2E+Wiebe%2E+2014%2E+SemEval%2D2014+Task+10%3A+Multilingual+semantic+textual+similarity%2E+In+Interna) [our card](https://md.research.elamur.ai/free/en/papers/agirre-2014-semeval-2014-task-10-multilingual/)
2. D. Bahdanau, K. Cho, and Y. Bengio. 2015. Neural machine translation by jointly learning to align and translate. In International Conference on Learning Representations (ICLR). [find](https://scholar.google.com/scholar?q=D%2E+Bahdanau%2C+K%2E+Cho%2C+and+Y%2E+Bengio%2E+2015%2E+Neural+machine+translation+by+jointly+learning+to+align+and+translate%2E+In+International+Conference+on+Learning+Representations+%28ICLR%29%2E) [our card](https://md.research.elamur.ai/free/en/papers/bahdanau-2014-neural-machine-translation-jointly-learning/)
3. Y. Bengio, R. Ducharme, P. Vincent, and C. Jauvin. 2003. A neural probabilistic language model. Journal of machine learning research, 3(0):1137–1155. [find](https://scholar.google.com/scholar?q=Y%2E+Bengio%2C+R%2E+Ducharme%2C+P%2E+Vincent%2C+and+C%2E+Jauvin%2E+2003%2E+A+neural+probabilistic+language+model%2E+Journal+of+machine+learning+research%2C+3%280%29%3A1137%E2%80%931155%2E)
4. S. R. Bowman, L. Vilnis, O. Vinyals, A. M. Dai, R. Jozefowicz, and S. Bengio. 2016. Generating sentences from a continuous space. In Computational Natural Language Learning (CoNLL), pages 10–21. [find](https://scholar.google.com/scholar?q=S%2E+R%2E+Bowman%2C+L%2E+Vilnis%2C+O%2E+Vinyals%2C+A%2E+M%2E+Dai%2C+R%2E+Jozefowicz%2C+and+S%2E+Bengio%2E+2016%2E+Generating+sentences+from+a+continuous+space%2E+In+Computational+Natural+Language+Learning+%28CoNLL%29%2C+pages+10%E2%80%9321%2E) [our card](https://md.research.elamur.ai/free/en/papers/bowman-2016-generating-sentences-continuous-space/)
5. C. Chelba, T. Mikolov, M. Schuster, Q. Ge, T. Brants, P. Koehn, and T. Robinson. 2013. One billion word benchmark for measuring progress in statistical language modeling. arXiv preprint arXiv:1312.3005. [find](https://scholar.google.com/scholar?q=C%2E+Chelba%2C+T%2E+Mikolov%2C+M%2E+Schuster%2C+Q%2E+Ge%2C+T%2E+Brants%2C+P%2E+Koehn%2C+and+T%2E+Robinson%2E+2013%2E+One+billion+word+benchmark+for+measuring+progress+in+statistical+language+modeling%2E+arXiv+preprint+arXiv%3A1312%2E300) [our card](https://md.research.elamur.ai/free/en/papers/chelba-2013-one-billion-word-benchmark-measuring/)
6. C. Doersch. 2016. Tutorial on variational autoencoders. arXiv preprint arXiv:1606.05908. — [arXiv:1606.05908](https://arxiv.org/abs/1606.05908) [find](https://scholar.google.com/scholar?q=C%2E+Doersch%2E+2016%2E+Tutorial+on+variational+autoencoders%2E+arXiv+preprint+arXiv%3A1606%2E05908%2E+%E2%80%94+%5BarXiv%3A1606%2E05908%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F1606%2E05908%29)
7. J. Gu, Y. Wang, K. Cho, and V. O. Li. 2017. Search engine guided non-parametric neural machine translation. arXiv preprint arXiv:1705.07267. — [arXiv:1705.07267](https://arxiv.org/abs/1705.07267) [find](https://scholar.google.com/scholar?q=J%2E+Gu%2C+Y%2E+Wang%2C+K%2E+Cho%2C+and+V%2E+O%2E+Li%2E+2017%2E+Search+engine+guided+non%2Dparametric+neural+machine+translation%2E+arXiv+preprint+arXiv%3A1705%2E07267%2E+%E2%80%94+%5BarXiv%3A1705%2E07267%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F1705%2E07267%29)
8. U. Hahn and I. Mani. 2000. The challenges of automatic summarization. Computer, 33. [find](https://scholar.google.com/scholar?q=U%2E+Hahn+and+I%2E+Mani%2E+2000%2E+The+challenges+of+automatic+summarization%2E+Computer%2C+33%2E)
9. T. B. Hashimoto, D. Alvarez-Melis, and T. S. Jaakkola. 2016. Word embeddings as metric recovery in semantic spaces. Transactions of the Association for Computational Linguistics (TACL), 4:273–286. [find](https://scholar.google.com/scholar?q=T%2E+B%2E+Hashimoto%2C+D%2E+Alvarez%2DMelis%2C+and+T%2E+S%2E+Jaakkola%2E+2016%2E+Word+embeddings+as+metric+recovery+in+semantic+spaces%2E+Transactions+of+the+Association+for+Computational+Linguistics+%28TACL%29%2C+4%3A273%E2%80%93286%2E)
10. J. R. Hayes and L. S. Flower. 1986. Writing research and the writer. American psychologist, 41(10):1106–1113. [find](https://scholar.google.com/scholar?q=J%2E+R%2E+Hayes+and+L%2E+S%2E+Flower%2E+1986%2E+Writing+research+and+the+writer%2E+American+psychologist%2C+41%2810%29%3A1106%E2%80%931113%2E)
11. H. He, A. G. II, J. Boyd-Graber, and H. D. III. 2015. Syntax-based rewriting for simultaneous machine translation. In Empirical Methods in Natural Language Processing (EMNLP), pages 55–64. [find](https://scholar.google.com/scholar?q=H%2E+He%2C+A%2E+G%2E+II%2C+J%2E+Boyd%2DGraber%2C+and+H%2E+D%2E+III%2E+2015%2E+Syntax%2Dbased+rewriting+for+simultaneous+machine+translation%2E+In+Empirical+Methods+in+Natural+Language+Processing+%28EMNLP%29%2C+pages+55%E2%80%9364%2E)
12. K. Heafield, I. Pouzyrevsky, J. H. Clark, and P. Koehn. 2013. Scalable modified Kneser-Ney language model estimation. In Association for Computational Linguistics (ACL), pages 690–696. [find](https://scholar.google.com/scholar?q=K%2E+Heafield%2C+I%2E+Pouzyrevsky%2C+J%2E+H%2E+Clark%2C+and+P%2E+Koehn%2E+2013%2E+Scalable+modified+Kneser%2DNey+language+model+estimation%2E+In+Association+for+Computational+Linguistics+%28ACL%29%2C+pages+690%E2%80%93696%2E) [our card](https://md.research.elamur.ai/free/en/papers/heafield-2013-scalable-modified-kneser-ney-language/)
13. M. Hodosh, P. Young, and J. Hockenmaier. 2013. Framing image description as a ranking task: Data, models and evaluation metrics. Journal of Artificial Intelligence Research (JAIR), 47:853–899. [find](https://scholar.google.com/scholar?q=M%2E+Hodosh%2C+P%2E+Young%2C+and+J%2E+Hockenmaier%2E+2013%2E+Framing+image+description+as+a+ranking+task%3A+Data%2C+models+and+evaluation+metrics%2E+Journal+of+Artificial+Intelligence+Research+%28JAIR%29%2C+47%3A853%E2%80%93899%2E)
14. M. I. Jordan, Z. Ghahramani, T. S. Jaakkola, and L. K. Saul. 1999. An introduction to variational methods for graphical models. Machine Learning, 37:183–233. [find](https://scholar.google.com/scholar?q=M%2E+I%2E+Jordan%2C+Z%2E+Ghahramani%2C+T%2E+S%2E+Jaakkola%2C+and+L%2E+K%2E+Saul%2E+1999%2E+An+introduction+to+variational+methods+for+graphical+models%2E+Machine+Learning%2C+37%3A183%E2%80%93233%2E)
15. N. Kalchbrenner and P. Blunsom. 2013. Recurrent continuous translation models. In Empirical Methods in Natural Language Processing (EMNLP), pages 1700– 1709. [find](https://scholar.google.com/scholar?q=N%2E+Kalchbrenner+and+P%2E+Blunsom%2E+2013%2E+Recurrent+continuous+translation+models%2E+In+Empirical+Methods+in+Natural+Language+Processing+%28EMNLP%29%2C+pages+1700%E2%80%93+1709%2E) [our card](https://md.research.elamur.ai/free/en/papers/kalchbrenner-2013-recurrent-continuous-translation-models/)
16. D. P. Kingma and M. Welling. 2014. Auto-encoding variational Bayes. arXiv preprint arXiv:1312.6114. [find](https://scholar.google.com/scholar?q=D%2E+P%2E+Kingma+and+M%2E+Welling%2E+2014%2E+Auto%2Dencoding+variational+Bayes%2E+arXiv+preprint+arXiv%3A1312%2E6114%2E) [our card](https://md.research.elamur.ai/free/en/papers/kingma-2013-auto-encoding-variational-bayes/)
17. P. Kuznetsova, V. Ordonez, A. C. Berg, T. L. Berg, and Y. Choi. 2013. Generalizing image captions for image-text parallel corpus. In Association for Computational Linguistics (ACL), pages 790–796. [find](https://scholar.google.com/scholar?q=P%2E+Kuznetsova%2C+V%2E+Ordonez%2C+A%2E+C%2E+Berg%2C+T%2E+L%2E+Berg%2C+and+Y%2E+Choi%2E+2013%2E+Generalizing+image+captions+for+image%2Dtext+parallel+corpus%2E+In+Association+for+Computational+Linguistics+%28ACL%29%2C+pages+790%E2%80%93796%2E)
18. J. Li, M. Galley, C. Brockett, J. Gao, and W. B. Dolan. 2016. A diversity-promoting objective function for neural conversation models. In Human Language Technology and North American Association for Computational Linguistics (HLT/NAACL), pages 110–119. [find](https://scholar.google.com/scholar?q=J%2E+Li%2C+M%2E+Galley%2C+C%2E+Brockett%2C+J%2E+Gao%2C+and+W%2E+B%2E+Dolan%2E+2016%2E+A+diversity%2Dpromoting+objective+function+for+neural+conversation+models%2E+In+Human+Language+Technology+and+North+American+Association+for+C) [our card](https://md.research.elamur.ai/free/en/papers/li-2016-diversity-promoting-objective-function-neural/)
19. R. Mason and E. Charniak. 2014. Domain-specific image captioning. In Computational Natural Language Learning (CoNLL), pages 2–10. [find](https://scholar.google.com/scholar?q=R%2E+Mason+and+E%2E+Charniak%2E+2014%2E+Domain%2Dspecific+image+captioning%2E+In+Computational+Natural+Language+Learning+%28CoNLL%29%2C+pages+2%E2%80%9310%2E)
20. T. Mikolov, K. Chen, G. Corrado, and Jeffrey. 2013a. Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781. [find](https://scholar.google.com/scholar?q=T%2E+Mikolov%2C+K%2E+Chen%2C+G%2E+Corrado%2C+and+Jeffrey%2E+2013a%2E+Efficient+estimation+of+word+representations+in+vector+space%2E+arXiv+preprint+arXiv%3A1301%2E3781%2E)
21. T. Mikolov, W. Yih, and G. Zweig. 2013b. Linguistic regularities in continuous space word representations. In Human Language Technology and North American Association for Computational Linguistics (HLT/NAACL), volume 13, pages 746–751. [find](https://scholar.google.com/scholar?q=T%2E+Mikolov%2C+W%2E+Yih%2C+and+G%2E+Zweig%2E+2013b%2E+Linguistic+regularities+in+continuous+space+word+representations%2E+In+Human+Language+Technology+and+North+American+Association+for+Computational+Linguistics+%28HL) [our card](https://md.research.elamur.ai/free/en/papers/mikolov-2013-linguistic-regularities-continuous-space-word/)
22. E. Parzen. 1962. On estimation of a probability density function and mode. Annals of Mathematical Statistics, 33:1065–1076. [find](https://scholar.google.com/scholar?q=E%2E+Parzen%2E+1962%2E+On+estimation+of+a+probability+density+function+and+mode%2E+Annals+of+Mathematical+Statistics%2C+33%3A1065%E2%80%931076%2E)
23. J. Pennington, R. Socher, and C. D. Manning. 2014. GloVe: Global vectors for word representation. In Empirical Methods in Natural Language Processing (EMNLP), pages 1532–1543. [find](https://scholar.google.com/scholar?q=J%2E+Pennington%2C+R%2E+Socher%2C+and+C%2E+D%2E+Manning%2E+2014%2E+GloVe%3A+Global+vectors+for+word+representation%2E+In+Empirical+Methods+in+Natural+Language+Processing+%28EMNLP%29%2C+pages+1532%E2%80%931543%2E)
24. A. Ritter, C. Cherry, and W. B. Dolan. 2011. Data-driven response generation in social media. In Empirical Methods in Natural Language Processing (EMNLP), pages 583–593. [find](https://scholar.google.com/scholar?q=A%2E+Ritter%2C+C%2E+Cherry%2C+and+W%2E+B%2E+Dolan%2E+2011%2E+Data%2Ddriven+response+generation+in+social+media%2E+In+Empirical+Methods+in+Natural+Language+Processing+%28EMNLP%29%2C+pages+583%E2%80%93593%2E) [our card](https://md.research.elamur.ai/free/en/papers/ritter-2011-data-driven-response-generation-social/)
25. L. Shao, S. Gouws, D. Britz, A. Goldie, B. Strope, and R. Kurzweil. 2017. Generating high-quality and informative conversation responses with sequence-to-sequence models. In Empirical Methods in Natural Language Processing (EMNLP), pages 2210–2219. [find](https://scholar.google.com/scholar?q=L%2E+Shao%2C+S%2E+Gouws%2C+D%2E+Britz%2C+A%2E+Goldie%2C+B%2E+Strope%2C+and+R%2E+Kurzweil%2E+2017%2E+Generating+high%2Dquality+and+informative+conversation+responses+with+sequence%2Dto%2Dsequence+models%2E+In+Empirical+Methods+in+Natur)
26. Y. Song, R. Yan, X. Li, D. Zhao, and M. Zhang. 2016. Two are better than one: An ensemble of retrieval-and generation-based dialog systems. arXiv preprint arXiv:1610.07149. — [arXiv:1610.07149](https://arxiv.org/abs/1610.07149) [find](https://scholar.google.com/scholar?q=Y%2E+Song%2C+R%2E+Yan%2C+X%2E+Li%2C+D%2E+Zhao%2C+and+M%2E+Zhang%2E+2016%2E+Two+are+better+than+one%3A+An+ensemble+of+retrieval%2Dand+generation%2Dbased+dialog+systems%2E+arXiv+preprint+arXiv%3A1610%2E07149%2E+%E2%80%94+%5BarXiv%3A1610%2E07149%5D%28https%3A)
27. I. Sutskever, O. Vinyals, and Q. V. Le. 2014. Sequence to sequence learning with neural networks. In Advances in Neural Information Processing Systems (NIPS), pages 3104–3112. [find](https://scholar.google.com/scholar?q=I%2E+Sutskever%2C+O%2E+Vinyals%2C+and+Q%2E+V%2E+Le%2E+2014%2E+Sequence+to+sequence+learning+with+neural+networks%2E+In+Advances+in+Neural+Information+Processing+Systems+%28NIPS%29%2C+pages+3104%E2%80%933112%2E)
28. J. B. Tenenbaum, V. D. Silva, and J. C. Langford. 2000. A global geometric framework for nonlinear dimensionality reduction. Science, pages 2319–2323. [find](https://scholar.google.com/scholar?q=J%2E+B%2E+Tenenbaum%2C+V%2E+D%2E+Silva%2C+and+J%2E+C%2E+Langford%2E+2000%2E+A+global+geometric+framework+for+nonlinear+dimensionality+reduction%2E+Science%2C+pages+2319%E2%80%932323%2E)
29. A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin. 2017. Attention is all you need. arXiv preprint arXiv:1706.03762. [find](https://scholar.google.com/scholar?q=A%2E+Vaswani%2C+N%2E+Shazeer%2C+N%2E+Parmar%2C+J%2E+Uszkoreit%2C+L%2E+Jones%2C+A%2E+N%2E+Gomez%2C+L%2E+Kaiser%2C+and+I%2E+Polosukhin%2E+2017%2E+Attention+is+all+you+need%2E+arXiv+preprint+arXiv%3A1706%2E03762%2E)
30. A. T. Wood. 1994. Simulation of the von mises fisher distribution. Communications in statistics-simulation and computation, pages 157–164. [find](https://scholar.google.com/scholar?q=A%2E+T%2E+Wood%2E+1994%2E+Simulation+of+the+von+mises+fisher+distribution%2E+Communications+in+statistics%2Dsimulation+and+computation%2C+pages+157%E2%80%93164%2E)
31. Y. Wu, M. Schuster, Z. Chen, Q. V. Le, M. Norouzi, W. Macherey, M. Krikun, Y. Cao, Q. Gao, K. Macherey, et al. 2016. Google’s neural machine translation system: Bridging the gap between human and machine translation. arXiv preprint arXiv:1609.08144. [find](https://scholar.google.com/scholar?q=Y%2E+Wu%2C+M%2E+Schuster%2C+Z%2E+Chen%2C+Q%2E+V%2E+Le%2C+M%2E+Norouzi%2C+W%2E+Macherey%2C+M%2E+Krikun%2C+Y%2E+Cao%2C+Q%2E+Gao%2C+K%2E+Macherey%2C+et+al%2E+2016%2E+Google%E2%80%99s+neural+machine+translation+system%3A+Bridging+the+gap+between+human+and+mach)
32. Yelp. 2017. Yelp Dataset Challenge, Round 8. [https://www.yelp.com/dataset_challenge](https://www.yelp.com/dataset_challenge). [↗](https://www.yelp.com/dataset_challenge)