---
title: "Pushing the Limits of Low-Resource Morphological Inflection (2019)"
description: "Many of the world's languages have rich morphology but only tiny annotated datasets. 43 references, cited by 70 papers here."
authors: ["Antonios Anastasopoulos", "Graham Neubig"]
year: 2019
venue: "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)"
source: "https://aclanthology.org/D19-1091/"
doi: "10.18653/v1/d19-1091"
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/anastasopoulos-2019-pushing-limits-low-resource-morphological/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/anastasopoulos-2019-pushing-limits-low-resource-morphological/)

[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/) / Pushing the Limits of Low-Resource Morphological Inflection

# Pushing the Limits of Low-Resource Morphological Inflection

**Authors:** [Antonios Anastasopoulos](https://md.research.elamur.ai/free/en/authors/antonios-anastasopoulos/) and [Graham Neubig](https://md.research.elamur.ai/free/en/authors/graham-neubig/) · **Year:** 2019 · **Venue:** [Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/) ([EMNLP 2019](https://md.research.elamur.ai/free/en/venues/emnlp/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/D19-1091/) · [PDF](https://aclanthology.org/D19-1091.pdf) · [DOI 10.18653/v1/d19-1091](https://doi.org/10.18653/v1/d19-1091) · [OpenAlex](https://openalex.org/W2968525655)

**Citations:** 67 citations (OpenAlex, 2026-10-14) · 70 in our library, of the 141,840 papers whose bibliographies we read

## Summary
Many of the world's languages have rich morphology but only tiny annotated datasets. Neural inflection models that excel with plenty of data break down when they get only a few dozen lemma–tag–form examples. The authors address this setting within the cross-lingual track of SIGMORPHON 2019. Their sequence-to-sequence model has separate encoders for the lemma (bidirectional RNN) and the tag set (self-attention). Its decoder attends in two steps: first over the tags, then over lemma characters using that tag-aware state. They add data hallucination, which aligns lemmas with inflected forms, treats long matching stretches as stems and replaces their interior with random letters. They also train jointly with related high-resource languages, using a schedule that avoids costly monotonic-attention constraints. Together these changes raise macro-averaged accuracy by 15 percentage points over the previous state of the art. The system ranked first on accuracy in SIGMORPHON 2019. The analysis shows transfer works best when source languages are genetically close and share a script, which is practical guidance for under-resourced languages.

## Key points
- The two-step attention decoder conditions lemma attention on the morphological tags. Its attention maps are easy to interpret, for example showing which tags produce Kazakh plural/accusative suffixes or the Greek subjunctive particle.
- Hallucination produces 10,000 synthetic examples per low-resource language, whose original training sets can be as small as about 50 examples. Stems are defined as runs of at least 3 aligned characters, and the method also handles stem changes such as apophony.
- A hallucination-only monolingual setup comes within a few points of combining transfer with hallucination. This makes it viable for isolates or for families without a high-resource member.
- Extra components include coverage and Markov attention regularizers (after Cohn et al., 2016) and an adversarial language discriminator with gradient reversal. Transfer from multiple related languages beats transfer from a single one.
- The system was best in SIGMORPHON 2019 by accuracy and third by average Levenshtein distance. It improved on Wu and Cotterell (2019), and the code is published at github.com/antonisa/inflection.

*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

- [Carnegie Mellon University](https://md.research.elamur.ai/free/en/universities/carnegie-mellon-university/) — University, Pittsburgh, United States · 365 works · 158,048 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

🧭 Topics (2): [🧩 Morphology](https://md.research.elamur.ai/free/en/topics/morphology/) · 277 works · [🌱 Low-resource languages](https://md.research.elamur.ai/free/en/topics/low-resource-languages/) · 166 works

## Cite

Cite as: Antonios Anastasopoulos and Graham Neubig. 2019. Pushing the Limits of Low-Resource Morphological Inflection. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP).

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

```bibtex
@inproceedings{anastasopoulos2019pushing,
  title = {{Pushing the Limits of Low-Resource Morphological Inflection}},
  author = {Antonios Anastasopoulos and Graham Neubig},
  booktitle = {Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)},
  year = {2019},
  doi = {10.18653/v1/d19-1091},
  url = {https://doi.org/10.18653/v1/d19-1091}
}
```

- [← previous Lost in Translation: Loss and Decay of Linguistic Richness in Machine Translation](https://md.research.elamur.ai/free/en/papers/vanmassenhove-2019-lost-translation-loss-decay-linguistic/)
- [next → Question Answering by Reasoning Across Documents with Graph Convolutional Networks](https://md.research.elamur.ai/free/en/papers/cao-2019-question-answering-reasoning-across-documents/)
- [↑ back to papers of 2019](https://md.research.elamur.ai/free/en/papers/2019/page/4/)

## References

43 references, 13 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Yarowsky, Jason Eisner, and Mans Hulden. 2017. [find](https://scholar.google.com/scholar?q=Yarowsky%2C+Jason+Eisner%2C+and+Mans+Hulden%2E+2017%2E)
2. CoNLL-SIGMORPHON 2017 shared task: Universal morphological reinflection in 52 languages. In Proc. CoNLL SIGMORPHON. [find](https://scholar.google.com/scholar?q=CoNLL%2DSIGMORPHON+2017+shared+task%3A+Universal+morphological+reinflection+in+52+languages%2E+In+Proc%2E+CoNLL+SIGMORPHON%2E)
3. Judit Ács. 2018. BME-HAS system for CoNLL– SIGMORPHON 2018 shared task: Universal morphological reinflection. In Proc. CoNLL– SIGMORPHON, pages 121–126, Brussels. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Judit+%C3%81cs%2E+2018%2E+BME%2DHAS+system+for+CoNLL%E2%80%93+SIGMORPHON+2018+shared+task%3A+Universal+morphological+reinflection%2E+In+Proc%2E+CoNLL%E2%80%93+SIGMORPHON%2C+pages+121%E2%80%93126%2C+Brussels%2E+Association+for+Computational+Linguis)
4. 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)
5. The SIGMORPHON 2016 shared task— morphological reinflection. In Proc. SIGMOR-PHON. [find](https://scholar.google.com/scholar?q=The+SIGMORPHON+2016+shared+task%E2%80%94+morphological+reinflection%2E+In+Proc%2E+SIGMOR%2DPHON%2E)
6. Roee Aharoni and Yoav Goldberg. 2017. [Morphological inflection generation with hard monotonic attention](https://md.research.elamur.ai/free/en/papers/aharoni-2017-morphological-inflection-generation-hard-monotonic/). In Proc. ACL.
7. Ben Foley, Josh Arnold, Rolando Coto-Solano, Gautier Durantin, T Mark Ellison, Daan van Esch, Scott Heath, František Kratochvíl, Zara Maxwell-Smith, David Nash, et al. 2018. Building speech recognition systems for language documentation: The Co-EDL endangered language pipeline and inference system (… [find](https://scholar.google.com/scholar?q=Ben+Foley%2C+Josh+Arnold%2C+Rolando+Coto%2DSolano%2C+Gautier+Durantin%2C+T+Mark+Ellison%2C+Daan+van+Esch%2C+Scott+Heath%2C+Franti%C5%A1ek+Kratochv%C3%ADl%2C+Zara+Maxwell%2DSmith%2C+David+Nash%2C+et+al%2E+2018%2E+Building+speech+recognitio)
8. Roee Aharoni, Yoav Goldberg, and Yonatan Belinkov. 2016. Improving sequence to sequence learning for morphological inflection generation: The BIU-MIT systems for the SIGMORPHON 2016 shared task for morphological reinflection. In Proc. SIGMOR-PHON. [find](https://scholar.google.com/scholar?q=Roee+Aharoni%2C+Yoav+Goldberg%2C+and+Yonatan+Belinkov%2E+2016%2E+Improving+sequence+to+sequence+learning+for+morphological+inflection+generation%3A+The+BIU%2DMIT+systems+for+the+SIGMORPHON+2016+shared+task+for+mo)
9. Antonios Anastasopoulos and David Chiang. 2018. Leveraging translations for speech transcription in low-resource settings. In Proc. INTERSPEECH. [find](https://scholar.google.com/scholar?q=Antonios+Anastasopoulos+and+David+Chiang%2E+2018%2E+Leveraging+translations+for+speech+transcription+in+low%2Dresource+settings%2E+In+Proc%2E+INTERSPEECH%2E)
10. Yaroslav Ganin, Evgeniya Ustinova, Hana Ajakan, Pascal Germain, Hugo Larochelle, François Laviolette, Mario Marchand, and Victor Lempitsky. 2016. Domain-adversarial training of neural networks. JMLR. [find](https://scholar.google.com/scholar?q=Yaroslav+Ganin%2C+Evgeniya+Ustinova%2C+Hana+Ajakan%2C+Pascal+Germain%2C+Hugo+Larochelle%2C+Fran%C3%A7ois+Laviolette%2C+Mario+Marchand%2C+and+Victor+Lempitsky%2E+2016%2E+Domain%2Dadversarial+training+of+neural+networks%2E+JMLR%2E)
11. Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2015. [Neural machine translation by jointly learning to align and translate](https://md.research.elamur.ai/free/en/papers/bahdanau-2014-neural-machine-translation-jointly-learning/). In Proc. ICLR.
12. Robert D Hoberman and Mark Aronoff. 2003. The verbal morphology of Maltese. Language Acquisition and Language Disorders, 28:61–78. [find](https://scholar.google.com/scholar?q=Robert+D+Hoberman+and+Mark+Aronoff%2E+2003%2E+The+verbal+morphology+of+Maltese%2E+Language+Acquisition+and+Language+Disorders%2C+28%3A61%E2%80%9378%2E)
13. Samy Bengio, Oriol Vinyals, Navdeep Jaitly, and Noam Shazeer. 2015. Scheduled sampling for sequence prediction with recurrent neural networks. In Proc. NIPS. [find](https://scholar.google.com/scholar?q=Samy+Bengio%2C+Oriol+Vinyals%2C+Navdeep+Jaitly%2C+and+Noam+Shazeer%2E+2015%2E+Scheduled+sampling+for+sequence+prediction+with+recurrent+neural+networks%2E+In+Proc%2E+NIPS%2E)
14. Katharina Kann, Ryan Cotterell, and Hinrich Schütze. 2017. One-shot neural cross-lingual transfer for paradigm completion. In Proc. ACL. [find](https://scholar.google.com/scholar?q=Katharina+Kann%2C+Ryan+Cotterell%2C+and+Hinrich+Sch%C3%BCtze%2E+2017%2E+One%2Dshot+neural+cross%2Dlingual+transfer+for+paradigm+completion%2E+In+Proc%2E+ACL%2E)
15. Toms Bergmanis, Katharina Kann, Hinrich Schütze, and Sharon Goldwater. 2017. Training data augmentation for low-resource morphological inflection. Proc. SIGMORPHON. [find](https://scholar.google.com/scholar?q=Toms+Bergmanis%2C+Katharina+Kann%2C+Hinrich+Sch%C3%BCtze%2C+and+Sharon+Goldwater%2E+2017%2E+Training+data+augmentation+for+low%2Dresource+morphological+inflection%2E+Proc%2E+SIGMORPHON%2E)
16. Christo Kirov, Ryan Cotterell, John Sylak-Glassman, Géraldine Walther, Ekaterina Vylomova, Patrick Xia, Manaal Faruqui, Sebastian J. Mielke, Arya Mc-Carthy, Sandra Kübler, David Yarowsky, Jason Eisner, and Mans Hulden. 2018. UniMorph 2.0: Universal Morphology. In Proc. LREC. [find](https://scholar.google.com/scholar?q=Christo+Kirov%2C+Ryan+Cotterell%2C+John+Sylak%2DGlassman%2C+G%C3%A9raldine+Walther%2C+Ekaterina+Vylomova%2C+Patrick+Xia%2C+Manaal+Faruqui%2C+Sebastian+J%2E+Mielke%2C+Arya+Mc%2DCarthy%2C+Sandra+K%C3%BCbler%2C+David+Yarowsky%2C+Jason+Eisner)
17. Theresa Breiner, Chieu Nguyen, Daan van Esch, and Jeremy O’Brien. 2019. Automatic keyboard layout design for low-resource Latin-script languages. arXiv:1901.06039. — [arXiv:1901.06039](https://arxiv.org/abs/1901.06039) [find](https://scholar.google.com/scholar?q=Theresa+Breiner%2C+Chieu+Nguyen%2C+Daan+van+Esch%2C+and+Jeremy+O%E2%80%99Brien%2E+2019%2E+Automatic+keyboard+layout+design+for+low%2Dresource+Latin%2Dscript+languages%2E+arXiv%3A1901%2E06039%2E+%E2%80%94+%5BarXiv%3A1901%2E06039%5D%28https%3A%2F%2Farxiv%2Eo)
18. Xilun Chen, Yu Sun, Ben Athiwaratkun, Claire Cardie, and Kilian Weinberger. 2018. [Adversarial deep averaging networks for cross-lingual sentiment classification](https://md.research.elamur.ai/free/en/papers/chen-2018-adversarial-deep-averaging-networks-cross/). Transactions of the Association for Computational Linguistics, 6:557–570.
19. Guillaume Lample, Alexis Conneau, Ludovic Denoyer, and Marc’Aurelio Ranzato. 2018. [Unsupervised machine translation using monolingual corpora only](https://md.research.elamur.ai/free/en/papers/lample-2017-unsupervised-machine-translation-using-monolingual/). In Proc. ICLR.
20. Patrick Littell, David R. Mortensen, Ke Lin, Katherine Kairis, Carlisle Turner, and Lori Levin. 2017. [Uriel and lang2vec: Representing languages as typological, geographical, and phylogenetic vectors](https://md.research.elamur.ai/free/en/papers/littell-2017-uriel-lang2vec-representing-languages-as/). In Proc. EACL.
21. Trevor Cohn, Cong Duy Vu Hoang, Ekaterina Vy-molova, Kaisheng Yao, Chris Dyer, and Gholamreza Haffari. 2016. [Incorporating structural alignment biases into an attentional neural translation model](https://md.research.elamur.ai/free/en/papers/cohn-2016-incorporating-structural-alignment-biases-into/). In Proc. NAACL-HLT.
22. Minh-Thang Luong and Christopher D Manning. 2015. Stanford neural machine translation systems for spoken language domains. In Proc. IWSLT. [find](https://scholar.google.com/scholar?q=Minh%2DThang+Luong+and+Christopher+D+Manning%2E+2015%2E+Stanford+neural+machine+translation+systems+for+spoken+language+domains%2E+In+Proc%2E+IWSLT%2E)
23. Ryan Cotterell, Christo Kirov, John Sylak-Glassman, Géraldine 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 rein… [find](https://scholar.google.com/scholar?q=Ryan+Cotterell%2C+Christo+Kirov%2C+John+Sylak%2DGlassman%2C+G%C3%A9raldine+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+Jaso)
24. Thang Luong, Hieu Pham, and Christopher D Manning. 2015. [Effective approaches to attention-based neural machine translation](https://md.research.elamur.ai/free/en/papers/luong-2015-effective-approaches-attention-based-neural/). In Proc. EMNLP.
25. Andre Martins and Ramon Astudillo. 2016. From softmax to sparsemax: A sparse model of attention and multi-label classification. In Proc. ICML, pages 1614–1623. [find](https://scholar.google.com/scholar?q=Andre+Martins+and+Ramon+Astudillo%2E+2016%2E+From+softmax+to+sparsemax%3A+A+sparse+model+of+attention+and+multi%2Dlabel+classification%2E+In+Proc%2E+ICML%2C+pages+1614%E2%80%931623%2E)
26. Ryan Cotterell, Christo Kirov, John Sylak-Glassman, Géraldine Walther, Ekaterina Vylomova, Patrick Xia, Manaal Faruqui, Sandra Kübler, David A Arya D. McCarthy, Ekaterina Vylomova, Shijie Wu, Chaitanya Malaviya, Lawrence Wolf-Sonkin, Garrett Nicolai, Christo Kirov, Miikka Silfverberg, Sebastian Miel… [find](https://scholar.google.com/scholar?q=Ryan+Cotterell%2C+Christo+Kirov%2C+John+Sylak%2DGlassman%2C+G%C3%A9raldine+Walther%2C+Ekaterina+Vylomova%2C+Patrick+Xia%2C+Manaal+Faruqui%2C+Sandra+K%C3%BCbler%2C+David+A+Arya+D%2E+McCarthy%2C+Ekaterina+Vylomova%2C+Shijie+Wu%2C+Chaitany)
27. The SIGMORPHON 2019 shared task: Crosslinguality and context in morphology. In Proc. SIGMORPHON. [find](https://scholar.google.com/scholar?q=The+SIGMORPHON+2019+shared+task%3A+Crosslinguality+and+context+in+morphology%2E+In+Proc%2E+SIGMORPHON%2E)
28. Hyperparameters Here we list all the hyperparameters of our models: • Encoder/Decoder number of layers: 1 • Character/Tag Embedding size: 32 • Recurrent State Size: 100 • LSTM Type: CoupledLSTM • Attention Size: 100 • Target and Source Character Embeddings are Tied • Tag Self-Attention size: 100 • T… [find](https://scholar.google.com/scholar?q=Hyperparameters+Here+we+list+all+the+hyperparameters+of+our+models%3A+%E2%80%A2+Encoder%2FDecoder+number+of+layers%3A+1+%E2%80%A2+Character%2FTag+Embedding+size%3A+32+%E2%80%A2+Recurrent+State+Size%3A+100+%E2%80%A2+LSTM+Type%3A+CoupledLSTM+%E2%80%A2+Atte)
29. Arya D. McCarthy, Ekaterina Vylomova, Shijie Wu, Chaitanya Malaviya, Lawrence Wolf-Sonkin, Garrett Nicolai, Miikka Silfverberg, Sebastian J. Mielke, Jeffrey Heinz, Ryan Cotterell, and Mans Hulden. 2019b. [find](https://scholar.google.com/scholar?q=Arya+D%2E+McCarthy%2C+Ekaterina+Vylomova%2C+Shijie+Wu%2C+Chaitanya+Malaviya%2C+Lawrence+Wolf%2DSonkin%2C+Garrett+Nicolai%2C+Miikka+Silfverberg%2C+Sebastian+J%2E+Mielke%2C+Jeffrey+Heinz%2C+Ryan+Cotterell%2C+and+Mans+Hulden%2E+201)
30. The SIGMORPHON 2019 shared task: Morphological analysis in context and cross-lingual transfer for inflection. In Proceedings of the 16th Workshop on Computational Research in Phonetics, Phonology, and Morphology, pages 229–244, Florence, Italy. [find](https://scholar.google.com/scholar?q=The+SIGMORPHON+2019+shared+task%3A+Morphological+analysis+in+context+and+cross%2Dlingual+transfer+for+inflection%2E+In+Proceedings+of+the+16th+Workshop+on+Computational+Research+in+Phonetics%2C+Phonology%2C+and)
31. Here we list the optimizer settings: Graham Neubig, Chris Dyer, Yoav Goldberg, Austin Matthews, Waleed Ammar, Antonios Anastasopoulos, Miguel Ballesteros, David Chiang, Daniel Clothiaux, Trevor Cohn, et al. 2017. [DyNet: The dynamic neural network toolkit](https://md.research.elamur.ai/free/en/papers/neubig-2017-dynet-dynamic-neural-network-toolkit/). arXiv:1701.03980.
32. Optimizer: SimpleSGD • Starting learning rate: 0.1 • Learning Rate Decay: 0.5 • Learning Rate Decay Patience: 6 epochs • Maximum number of epochs: 20, 40, 40 (for each training phase) • Minibatch Size: 10, 10, 2 (for each training phase). [find](https://scholar.google.com/scholar?q=Optimizer%3A+SimpleSGD+%E2%80%A2+Starting+learning+rate%3A+0%2E1+%E2%80%A2+Learning+Rate+Decay%3A+0%2E5+%E2%80%A2+Learning+Rate+Decay+Patience%3A+6+epochs+%E2%80%A2+Maximum+number+of+epochs%3A+20%2C+40%2C+40+%28for+each+training+phase%29+%E2%80%A2+Minibatch+Size)
33. Graham Neubig and Junjie Hu. 2018. [Rapid adaptation of neural machine translation to new languages](https://md.research.elamur.ai/free/en/papers/neubig-2018-rapid-adaptation-neural-machine-translation/). In Proc. EMNLP.
34. Ben Peters and André F. T. Martins. 2019. IT–IST at the SIGMORPHON 2019 shared task: Sparse two-headed models for inflection. In Proc. SIGMOR-PHON, Florence, Italy. [find](https://scholar.google.com/scholar?q=Ben+Peters+and+Andr%C3%A9+F%2E+T%2E+Martins%2E+2019%2E+IT%E2%80%93IST+at+the+SIGMORPHON+2019+shared+task%3A+Sparse+two%2Dheaded+models+for+inflection%2E+In+Proc%2E+SIGMOR%2DPHON%2C+Florence%2C+Italy%2E)
35. Lane Schwartz, Emily Chen, Benjamin Hunt, and Sylvia LR Schreiner. 2019. Bootstrapping a neural morphological analyzer for St. Lawrence Island Yupik from a finite-state transducer. In Proc. Comput-EL3. [find](https://scholar.google.com/scholar?q=Lane+Schwartz%2C+Emily+Chen%2C+Benjamin+Hunt%2C+and+Sylvia+LR+Schreiner%2E+2019%2E+Bootstrapping+a+neural+morphological+analyzer+for+St%2E+Lawrence+Island+Yupik+from+a+finite%2Dstate+transducer%2E+In+Proc%2E+Comput%2DEL3)
36. Miikka Silfverberg, Adam Wiemerslage, Ling Liu, and Lingshuang Jack Mao. 2017. [Data augmentation for morphological reinflection](https://md.research.elamur.ai/free/en/papers/silfverberg-2017-data-augmentation-morphological-reinflection/). Proc. SIGMORPHON.
37. James Neil Sneddon, K Alexander Adelaar, Dwi N Djenar, and Michael Ewing. 2012. Indonesian: A comprehensive grammar. Routledge. [find](https://scholar.google.com/scholar?q=James+Neil+Sneddon%2C+K+Alexander+Adelaar%2C+Dwi+N+Djenar%2C+and+Michael+Ewing%2E+2012%2E+Indonesian%3A+A+comprehensive+grammar%2E+Routledge%2E)
38. 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 Proc. NeurIPS.
39. Shijie Wu and Ryan Cotterell. 2019. [Exact hard monotonic attention for character-level transduction](https://md.research.elamur.ai/free/en/papers/wu-2019-exact-hard-monotonic-attention-character/). arXiv:1905.06319.
40. Qizhe Xie, Zihang Dai, Yulun Du, Eduard Hovy, and Graham Neubig. 2017. Controllable invariance through adversarial feature learning. In Proc. NeurIPS, pages 585–596. [find](https://scholar.google.com/scholar?q=Qizhe+Xie%2C+Zihang+Dai%2C+Yulun+Du%2C+Eduard+Hovy%2C+and+Graham+Neubig%2E+2017%2E+Controllable+invariance+through+adversarial+feature+learning%2E+In+Proc%2E+NeurIPS%2C+pages+585%E2%80%93596%2E)
41. Chunting Zhou and Graham Neubig. 2017. Morphological inflection generation with multi-space variational encoder-decoders. In Proc. SIGMORPHON. [find](https://scholar.google.com/scholar?q=Chunting+Zhou+and+Graham+Neubig%2E+2017%2E+Morphological+inflection+generation+with+multi%2Dspace+variational+encoder%2Ddecoders%2E+In+Proc%2E+SIGMORPHON%2E)
42. Barret Zoph and Kevin Knight. 2016. [Multi-source neural translation](https://md.research.elamur.ai/free/en/papers/zoph-2016-multi-source-neural-translation/). In Proc. NAACL-HLT.
43. Genetic dist. latin bengali sorani italian latvian english italian urdu slovene russian swahili portuguese kurmanji zulu kannada czech greek irish ladin lithuanian murrinhpatha neapolitan old english old saxon portuguese quechua russian sorani swahili telugu 0.86 0.88 1.0 0.30 0.25 N/A 0.10 0.88 0.8… [find](https://scholar.google.com/scholar?q=Genetic+dist%2E+latin+bengali+sorani+italian+latvian+english+italian+urdu+slovene+russian+swahili+portuguese+kurmanji+zulu+kannada+czech+greek+irish+ladin+lithuanian+murrinhpatha+neapolitan+old+english+)

*Updated 24 October 2026*