---
title: "A Simple Joint Model for Improved Contextual Neural Lemmatization — Malaviya 2019"
description: "The paper proposes a joint neural model that predicts the morphological tag of each word and then generates the… 34 references, cited by 17 papers here."
authors: ["Chaitanya Malaviya", "Shijie Wu", "Ryan Cotterell"]
year: 2019
venue: "Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)"
source: "https://aclanthology.org/N19-1155/"
doi: "10.18653/v1/n19-1155"
arxiv: "1904.02306"
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/malaviya-2019-simple-joint-model-improved-contextual/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/malaviya-2019-simple-joint-model-improved-contextual/)

[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/) / A Simple Joint Model for Improved Contextual Neural Lemmatization

# A Simple Joint Model for Improved Contextual Neural Lemmatization

**Authors:** [Chaitanya Malaviya](https://md.research.elamur.ai/free/en/authors/chaitanya-malaviya/), [Shijie Wu](https://md.research.elamur.ai/free/en/authors/shijie-wu/) and [Ryan Cotterell](https://md.research.elamur.ai/free/en/authors/ryan-cotterell/) · **Year:** 2019 · **Venue:** Proceedings of the 2019 Conference of the North American Chapter of the ACL: Human Language Technologies, Volume 1 (Long and Short Papers) **Link:** [aclanthology.org/N19-1155](https://aclanthology.org/N19-1155/) · **Licence:** [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/)

[**22** citations](https://openalex.org/works?filter=cites:W2927851123) OpenAlex, 2026-10-14 · [**17** citations in our library](https://md.research.elamur.ai/free/en/papers/malaviya-2019-simple-joint-model-improved-contextual/cited-by/) of the 140,884 papers whose bibliographies we read · [Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)](https://aclanthology.org/volumes/N19-1/) · [licence](https://creativecommons.org/licenses/by/4.0/)

- [Publisher's page](https://aclanthology.org/N19-1155/)
- [PDF](https://aclanthology.org/N19-1155.pdf)
- [DOI 10.18653/v1/n19-1155](https://doi.org/10.18653/v1/n19-1155)
- [arXiv 1904.02306](https://arxiv.org/abs/1904.02306)
- [OpenAlex](https://openalex.org/W2927851123)

**Authors (3)**

1. [Chaitanya Malaviya](https://openalex.org/A5037500486) [Semantic Scholar](https://www.semanticscholar.org/author/8805254) · h 13 · 1,786 citations · 43 works
2. [Shijie Wu](https://openalex.org/A5015766325) [ORCID](https://orcid.org/0000-0002-1206-6926) · [Semantic Scholar](https://www.semanticscholar.org/author/50425845) · h 18 · 1,619 citations · 26 works
3. [Ryan Cotterell](https://openalex.org/A5061951606) [ORCID](https://orcid.org/0000-0003-4080-1833) · [Semantic Scholar](https://www.semanticscholar.org/author/1750769) · h 44 · 6,252 citations · 425 works

Citations and author metrics: OpenAlex, 2026-10-14; authors with the same name are not always told apart.

## What it is about

Lemmatization maps an inflected form to its citation form, and the right lemma often depends on context, as "running" is a verb in one sentence and a noun in another. The paper proposes a joint neural model that predicts the morphological tag of each word and then generates the lemma conditioned on the tag and on the sentence, decoded either greedily or by crunching over the k best tag sequences. On 20 UD languages it reaches 95.42 average lemma accuracy against 95.05 for the strongest baseline (Bergmanis and Goldwater), a difference the authors report as significant. The gains grow as the treebank gets smaller, with a correlation of -0.845 between training tokens and the improvement, and feeding gold tags to the model shows that better tagging would raise lemma accuracy further.

## Ideas

- I3. Low-resource slope: train the lemma choice on 10, 25, 50 and 100 percent of the English training data and plot accuracy, as the paper's learning curve does; the claim to test is that tag-conditioned lemmas gain most with little data (cv on train, EWT test once per release).

## For Mova

- I1. Tag-conditioned lemma rules in `en/src/morph.rs`: when the dictionary has several candidates or a suffix rule is ambiguous, choose the rule with the UPOS and FEATS predicted by `en/src/ud.rs`; measure lemma accuracy on EWT dev, reporting ambiguous tokens (more than one lemma) separately from the rest.
- I2. Crunching in `en`: keep the k best UPOS and FEATS per token and pick the lemma with the best joint score; measure lemma accuracy on EWT dev against the greedy choice, bank by bank, since the paper's gain is significant only for some languages.

The lemmatizer is `en/src/morph.rs` (dictionary from AGID and UD plus suffix rules, lemma accuracy 99.3 to 99.5 percent), and the tags come from `en/src/ud.rs`. The chapter is [languages/en/10-word-classes.md](https://mova.elamur.ai/free/en/docs/languages/en/10-word-classes/), with [languages/en/13-verbs.md](https://mova.elamur.ai/free/en/docs/languages/en/13-verbs/) for the verb forms. Measure first the lemma accuracy on ambiguous tokens of EWT dev, where the paper's effect would show.

## Institutions

[🎓**University of Cambridge** Cambridge · United Kingdom 119 works · 110,950 citations](https://md.research.elamur.ai/free/en/universities/university-of-cambridge/) · [🎓**Johns Hopkins University** Baltimore · United States 151 works · 84,111 citations](https://md.research.elamur.ai/free/en/universities/johns-hopkins-university/)

Topics[Universal Dependencies](https://md.research.elamur.ai/free/en/topics/universal-dependencies/) · [Morphology](https://md.research.elamur.ai/free/en/topics/morphology/)

## Cite

Cite as Chaitanya Malaviya, Shijie Wu and Ryan Cotterell. 2019. A Simple Joint Model for Improved Contextual Neural Lemmatization. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers).

The paper itself, not this card. BibTeX from the library's record of the work. [DOI 10.18653/v1/n19-1155](https://doi.org/10.18653/v1/n19-1155) · [arXiv 1904.02306](https://arxiv.org/abs/1904.02306)

```bibtex
@inproceedings{malaviya2019simple,
  title = {{A Simple Joint Model for Improved Contextual Neural Lemmatization}},
  author = {Chaitanya Malaviya, Shijie Wu and Ryan Cotterell},
  booktitle = {Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)},
  year = {2019},
  doi = {10.18653/v1/n19-1155},
  eprint = {1904.02306},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.18653/v1/n19-1155}
}
```

- [← previous WikiCREM: A Large Unsupervised Corpus for Coreference Resolution](https://md.research.elamur.ai/free/en/papers/kocijan-2019-wikicrem-large-unsupervised-corpus-coreference/)
- [next → Crowdsourcing Discourse Relation Annotations by a Two-Step Connective Insertion Task](https://md.research.elamur.ai/free/en/papers/yung-2019-crowdsourcing-discourse-relation-annotations-two/)
- [↑ back to papers of 2019](https://md.research.elamur.ai/free/en/papers/2019/page/4/)

## References

34 references, 4 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Željko Agić and Natalie Schluter. 2017. How (not) to train a dependency parser: The curious case of jackknifing part-of-speech taggers. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 679–684. Association for Computational L… [find](https://scholar.google.com/scholar?q=%C5%BDeljko+Agic%CC%81+and+Natalie+Schluter%2E+2017%2E+How+%28not%29+to+train+a+dependency+parser%3A+The+curious+case+of+jackknifing+part%2Dof%2Dspeech+taggers%2E+In+Proceedings+of+the+55th+Annual+Meeting+of+the+Association+fo)
2. Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2015. Neural machine translation by jointly learning to align and translate. In Proceedings of the International Conference on Learning Representations. [our card](https://md.research.elamur.ai/free/en/papers/bahdanau-2014-neural-machine-translation-jointly-learning/)
3. Toms Bergmanis and Sharon Goldwater. 2018. Context sensitive neural lemmatization with Lematus. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 1391–1400. Association for… [find](https://scholar.google.com/scholar?q=Toms+Bergmanis+and+Sharon+Goldwater%2E+2018%2E+Context+sensitive+neural+lemmatization+with+Lematus%2E+In+Proceedings+of+the+2018+Conference+of+the+North+American+Chapter+of+the+Association+for+Computational)
4. Toms Bergmanis and Sharon Goldwater. 2019. Data Augmentation for Context-Sensitive Neural Lemmatization Using Inflection Tables and Raw Text. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (S… [find](https://scholar.google.com/scholar?q=Toms+Bergmanis+and+Sharon+Goldwater%2E+2019%2E+Data+Augmentation+for+Context%2DSensitive+Neural+Lemmatization+Using+Inflection+Tables+and+Raw+Text%2E+In+Proceedings+of+the+2019+Conference+of+the+North+America)
5. Anders Björkelund, Bernd Bohnet, Love Hafdell, and Pierre Nugues. 2010. A high-performance syntactic and semantic dependency parser. In Proceedings of the 23rd International Conference on Computational Linguistics: Demonstrations, pages 33– 36. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Anders+Bj%C3%B6rkelund%2C+Bernd+Bohnet%2C+Love+Hafdell%2C+and+Pierre+Nugues%2E+2010%2E+A+high%2Dperformance+syntactic+and+semantic+dependency+parser%2E+In+Proceedings+of+the+23rd+International+Conference+on+Computationa)
6. Victor Chahuneau, Eva Schlinger, Noah A. Smith, and Chris Dyer. 2013. Translating into morphologically rich languages with synthetic phrases. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pages 1677–1687. [find](https://scholar.google.com/scholar?q=Victor+Chahuneau%2C+Eva+Schlinger%2C+Noah+A%2E+Smith%2C+and+Chris+Dyer%2E+2013%2E+Translating+into+morphologically+rich+languages+with+synthetic+phrases%2E+In+Proceedings+of+the+2013+Conference+on+Empirical+Methods)
7. Grzegorz Chrupała. 2008. Towards a machine-learning architecture for lexical functional grammar parsing. Ph.D. thesis, Dublin City University. [find](https://scholar.google.com/scholar?q=Grzegorz+Chrupa%C5%82a%2E+2008%2E+Towards+a+machine%2Dlearning+architecture+for+lexical+functional+grammar+parsing%2E+Ph%2ED%2E+thesis%2C+Dublin+City+University%2E)
8. Grzegorz Chrupała, Georgiana Dinu, and Josef van Genabith. 2008. Learning morphology with Morfette. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08), Marrakech, Morocco. European Language Resources Association (ELRA). Http://www.lrec-conf.org/procee… [our card](https://md.research.elamur.ai/free/en/papers/chrupala-2008-learning-morphology-morfette/)
9. Ryan Cotterell and Georg Heigold. 2017. Cross-lingual character-level neural morphological tagging. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 748–759. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Ryan+Cotterell+and+Georg+Heigold%2E+2017%2E+Cross%2Dlingual+character%2Dlevel+neural+morphological+tagging%2E+In+Proceedings+of+the+2017+Conference+on+Empirical+Methods+in+Natural+Language+Processing%2C+pages+748)
10. Ryan Cotterell, Christo Kirov, John Sylak-Glassman, Gėraldine Walther, Ekaterina Vylomova, Arya D. McCarthy, Katharina Kann, Sebastian Mielke, Garrett Nicolai, Miikka Silfverberg, David Yarowsky, Jason Eisner, and Mans Hulden. 2018. The CoNLL– SIGMORPHON 2018 shared task: Universal morphological re… [find](https://scholar.google.com/scholar?q=Ryan+Cotterell%2C+Christo+Kirov%2C+John+Sylak%2DGlassman%2C+Ge%CC%87raldine+Walther%2C+Ekaterina+Vylomova%2C+Arya+D%2E+McCarthy%2C+Katharina+Kann%2C+Sebastian+Mielke%2C+Garrett+Nicolai%2C+Miikka+Silfverberg%2C+David+Yarowsky%2C+Jas)
11. Ryan Cotterell, Christo Kirov, John Sylak-Glassman, Gėraldine Walther, Ekaterina Vylomova, Patrick Xia, Manaal Faruqui, Sandra Kübler, David Yarowsky, Jason Eisner, and Mans Hulden. 2017. [find](https://scholar.google.com/scholar?q=Ryan+Cotterell%2C+Christo+Kirov%2C+John+Sylak%2DGlassman%2C+Ge%CC%87raldine+Walther%2C+Ekaterina+Vylomova%2C+Patrick+Xia%2C+Manaal+Faruqui%2C+Sandra+K%C3%BCbler%2C+David+Yarowsky%2C+Jason+Eisner%2C+and+Mans+Hulden%2E+2017%2E)
12. CoNLL-SIGMORPHON 2017 shared task: Universal morphological reinflection in 52 languages. In Proceedings of the CoNLL SIGMORPHON 2017 Shared Task: Universal Morphological Reinflection, pages 1–30. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=CoNLL%2DSIGMORPHON+2017+shared+task%3A+Universal+morphological+reinflection+in+52+languages%2E+In+Proceedings+of+the+CoNLL+SIGMORPHON+2017+Shared+Task%3A+Universal+Morphological+Reinflection%2C+pages+1%E2%80%9330%2E+Asso)
13. Ryan Cotterell, Christo Kirov, John Sylak-Glassman, David Yarowsky, Jason Eisner, and Mans Hulden. 2016. [find](https://scholar.google.com/scholar?q=Ryan+Cotterell%2C+Christo+Kirov%2C+John+Sylak%2DGlassman%2C+David+Yarowsky%2C+Jason+Eisner%2C+and+Mans+Hulden%2E+2016%2E)
14. The SIGMORPHON 2016 shared task— morphological reinflection. In Proceedings of the 14th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology, pages 10–22. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=The+SIGMORPHON+2016+shared+task%E2%80%94+morphological+reinflection%2E+In+Proceedings+of+the+14th+SIGMORPHON+Workshop+on+Computational+Research+in+Phonetics%2C+Phonology%2C+and+Morphology%2C+pages+10%E2%80%9322%2E+Association+)
15. Matthew S. Dryer and Martin Haspelmath, editors. 2013. WALS Online. Max Planck Institute for Evolutionary Anthropology, Leipzig. [find](https://scholar.google.com/scholar?q=Matthew+S%2E+Dryer+and+Martin+Haspelmath%2C+editors%2E+2013%2E+WALS+Online%2E+Max+Planck+Institute+for+Evolutionary+Anthropology%2C+Leipzig%2E)
16. Alexander Fraser, Marion Weller, Aoife Cahill, and Fabienne Cap. 2012. Modeling inflection and word-formation in smt. In Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics, pages 664–674. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Alexander+Fraser%2C+Marion+Weller%2C+Aoife+Cahill%2C+and+Fabienne+Cap%2E+2012%2E+Modeling+inflection+and+word%2Dformation+in+smt%2E+In+Proceedings+of+the+13th+Conference+of+the+European+Chapter+of+the+Association+f)
17. Alex Graves, Abdel-rahman Mohamed, and Geoffrey Hinton. 2013. Speech recognition with deep recurrent neural networks. In Acoustics, speech and signal processing (icassp), 2013 ieee international conference on, pages 6645–6649. IEEE. [find](https://scholar.google.com/scholar?q=Alex+Graves%2C+Abdel%2Drahman+Mohamed%2C+and+Geoffrey+Hinton%2E+2013%2E+Speech+recognition+with+deep+recurrent+neural+networks%2E+In+Acoustics%2C+speech+and+signal+processing+%28icassp%29%2C+2013+ieee+international+confe)
18. Martin Haspelmath and Andrea Sims. 2013. Understanding morphology. Routledge. [find](https://scholar.google.com/scholar?q=Martin+Haspelmath+and+Andrea+Sims%2E+2013%2E+Understanding+morphology%2E+Routledge%2E)
19. Georg Heigold, Guenter Neumann, and Josef van Genabith. 2017. An extensive empirical evaluation of character-based morphological tagging for 14 languages. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, pages 505–… [find](https://scholar.google.com/scholar?q=Georg+Heigold%2C+Guenter+Neumann%2C+and+Josef+van+Genabith%2E+2017%2E+An+extensive+empirical+evaluation+of+character%2Dbased+morphological+tagging+for+14+languages%2E+In+Proceedings+of+the+15th+Conference+of+the+)
20. Jakub Kanis and Lucie Skorkovská. 2010. Comparison of different lemmatization approaches through the means of information retrieval performance. In International Conference on Text, Speech and Dialogue, pages 93–100. Springer. [find](https://scholar.google.com/scholar?q=Jakub+Kanis+and+Lucie+Skorkovsk%C3%A1%2E+2010%2E+Comparison+of+different+lemmatization+approaches+through+the+means+of+information+retrieval+performance%2E+In+International+Conference+on+Text%2C+Speech+and+Dialogu)
21. John D. Lafferty, Andrew McCallum, and Fernando C. N. Pereira. 2001. Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In Proceedings of the Eighteenth International Conference on Machine Learning, pages 282–289, San Francisco, CA, USA. [find](https://scholar.google.com/scholar?q=John+D%2E+Lafferty%2C+Andrew+McCallum%2C+and+Fernando+C%2E+N%2E+Pereira%2E+2001%2E+Conditional+random+fields%3A+Probabilistic+models+for+segmenting+and+labeling+sequence+data%2E+In+Proceedings+of+the+Eighteenth+Interna)
22. Peter Makarov and Simon Clematide. 2018. UZH at CoNLL-SIGMORPHON 2018 shared task on universal morphological reinflection. In Proceedings of the CoNLL SIGMORPHON 2018 Shared Task: Universal Morphological Reinflection, pages 69–75. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Peter+Makarov+and+Simon+Clematide%2E+2018%2E+UZH+at+CoNLL%2DSIGMORPHON+2018+shared+task+on+universal+morphological+reinflection%2E+In+Proceedings+of+the+CoNLL+SIGMORPHON+2018+Shared+Task%3A+Universal+Morphologi)
23. Chaitanya Malaviya, Matthew R. Gormley, and Graham Neubig. 2018. Neural factor graph models for cross-lingual morphological tagging. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2653–2663. Association for Computational Ling… [find](https://scholar.google.com/scholar?q=Chaitanya+Malaviya%2C+Matthew+R%2E+Gormley%2C+and+Graham+Neubig%2E+2018%2E+Neural+factor+graph+models+for+cross%2Dlingual+morphological+tagging%2E+In+Proceedings+of+the+56th+Annual+Meeting+of+the+Association+for+Co)
24. Jonathan May and Kevin Knight. 2006. A better n-best list: Practical determinization of weighted finite tree automata. In Proceedings of the Human Language Technology Conference of the NAACL, Main Conference. [find](https://scholar.google.com/scholar?q=Jonathan+May+and+Kevin+Knight%2E+2006%2E+A+better+n%2Dbest+list%3A+Practical+determinization+of+weighted+finite+tree+automata%2E+In+Proceedings+of+the+Human+Language+Technology+Conference+of+the+NAACL%2C+Main+Con)
25. Arya D McCarthy, Miikka Silfverberg, Ryan Cotterell, Mans Hulden, and David Yarowsky. 2018. Marrying universal dependencies and universal morphology. In Proceedings of the Second Workshop on Universal Dependencies (UDW 2018), pages 91–101. [our card](https://md.research.elamur.ai/free/en/papers/mccarthy-2018-marrying-universal-dependencies-universal-morphology/)
26. Christof Monz and Maarten De Rijke. 2001. Shallow morphological analysis in monolingual information retrieval for Dutch, German, and Italian. In Workshop of the Cross-Language Evaluation Forum for European Languages, pages 262–277. Springer. [find](https://scholar.google.com/scholar?q=Christof+Monz+and+Maarten+De+Rijke%2E+2001%2E+Shallow+morphological+analysis+in+monolingual+information+retrieval+for+Dutch%2C+German%2C+and+Italian%2E+In+Workshop+of+the+Cross%2DLanguage+Evaluation+Forum+for+Eur)
27. Thomas Müller, Ryan Cotterell, Alexander Fraser, and Hinrich Schütze. 2015. Joint lemmatization and morphological tagging with Lemming. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 2268–2274. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Thomas+M%C3%BCller%2C+Ryan+Cotterell%2C+Alexander+Fraser%2C+and+Hinrich+Sch%C3%BCtze%2E+2015%2E+Joint+lemmatization+and+morphological+tagging+with+Lemming%2E+In+Proceedings+of+the+2015+Conference+on+Empirical+Methods+in+Na)
28. Joakim Nivre et al. 2017. Universal dependencies 2.0. LINDAT/CLARIN digital library at the Institute of Formal and Applied Linguistics (ÚFAL), Faculty of Mathematics and Physics, Charles University. [find](https://scholar.google.com/scholar?q=Joakim+Nivre+et+al%2E+2017%2E+Universal+dependencies+2%2E0%2E+LINDAT%2FCLARIN+digital+library+at+the+Institute+of+Formal+and+Applied+Linguistics+%28%C3%9AFAL%29%2C+Faculty+of+Mathematics+and+Physics%2C+Charles+University%2E)
29. Lawrence R. Rabiner. 1989. A tutorial on hidden Markov models and selected applications in speech recognition. Proceedings of the IEEE, 77(2):257– 286. [find](https://scholar.google.com/scholar?q=Lawrence+R%2E+Rabiner%2E+1989%2E+A+tutorial+on+hidden+Markov+models+and+selected+applications+in+speech+recognition%2E+Proceedings+of+the+IEEE%2C+77%282%29%3A257%E2%80%93+286%2E)
30. Diederik P. Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980. [find](https://scholar.google.com/scholar?q=Diederik+P%2E+Kingma+and+Jimmy+Ba%2E+2014%2E+Adam%3A+A+method+for+stochastic+optimization%2E+arXiv+preprint+arXiv%3A1412%2E6980%2E)
31. Marc’Aurelio Ranzato, Sumit Chopra, Michael Auli, and Wojciech Zaremba. 2015. Sequence level training with recurrent neural networks. arXiv preprint arXiv:1511.06732. [our card](https://md.research.elamur.ai/free/en/papers/ranzato-2015-sequence-level-training-recurrent-neural/)
32. Daphne Koller and Nir Friedman. 2009. Probabilistic graphical models: Principles and techniques. MIT Press. [find](https://scholar.google.com/scholar?q=Daphne+Koller+and+Nir+Friedman%2E+2009%2E+Probabilistic+graphical+models%3A+Principles+and+techniques%2E+MIT+Press%2E)
33. Pushpendre Rastogi, Ryan Cotterell, and Jason Eisner. 2016. Weighting finite-state transductions with neural context. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 623–633. Association for Comp… [find](https://scholar.google.com/scholar?q=Pushpendre+Rastogi%2C+Ryan+Cotterell%2C+and+Jason+Eisner%2E+2016%2E+Weighting+finite%2Dstate+transductions+with+neural+context%2E+In+Proceedings+of+the+2016+Conference+of+the+North+American+Chapter+of+the+Associa)
34. Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever, and Ruslan Salakhutdinov. 2014. Dropout: a simple way to prevent neural networks from overfitting. The Journal of Machine Learning Research, 15(1):1929–1958. [find](https://scholar.google.com/scholar?q=Nitish+Srivastava%2C+Geoffrey+Hinton%2C+Alex+Krizhevsky%2C+Ilya+Sutskever%2C+and+Ruslan+Salakhutdinov%2E+2014%2E+Dropout%3A+a+simple+way+to+prevent+neural+networks+from+overfitting%2E+The+Journal+of+Machine+Learning+)