mlsanityData to 14 Oct 2026

Morphological Processing of Low-Resource Languages: Where We Are and What's Next

arXiv 2203.08909 ↗First posted 16 Mar 2022cs.CLcited by 4

Not on the map. Why?

Abstract (arXiv)

Automatic morphological processing can aid downstream natural language processing applications, especially for low-resource languages, and assist language documentation efforts for endangered languages. Having long been multilingual, the field of computational morphology is increasingly moving towards approaches suitable for languages with minimal or no annotated resources. First, we survey recent developments in computational morphology with a focus on low-resource languages. Second, we argue that the field is ready to tackle the logical next challenge: understanding a language's morphology from raw text alone. We perform an empirical study on a truly unsupervised version of the paradigm completion task and show that, while existing state-of-the-art models bridged by two newly proposed models we devise perform reasonably, there is still much room for improvement. The stakes are high: solving this task will increase the language coverage of morphological resources by a number of magnitudes.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 53 of its 158 references that are in the map. First posted on arXiv 16 Mar 2022.

Builds on

53 of 158 references.

References · 53

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  4. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  5. 2016Enriching Word Vectors with Subword Informationcited by 1,583
  6. 2019fairseq: A Fast, Extensible Toolkit for Sequence Modelingcited by 1,488
  7. 2015Pointer Networkscited by 895
  8. 2020Stanza: A Python Natural Language Processing Toolkit for Many Human Languagescited by 723
  9. 2021Word Alignment by Fine-tuning Embeddings on Parallel Corporacited by 186
  10. 2021Trankit: A Light-Weight Transformer-based Toolkit for Multilingual Natural Language Processingcited by 68
  11. 2021Superbizarre Is Not Superb: Derivational Morphology Improves BERT's Interpretation of Complex Wordscited by 63
  12. 2018MTNT: A Testbed for Machine Translation of Noisy Textcited by 54
38 more
  1. 2019The SIGMORPHON 2019 Shared Task: Morphological Analysis in Context and Cross-Lingual Transfer for Inflectioncited by 43
  2. 2020Applying the Transformer to Character-level Transductioncited by 43
  3. 2018UniMorph 2.0: Universal Morphologycited by 42
  4. 2018The CoNLL--SIGMORPHON 2018 Shared Task: Universal Morphological Reinflectioncited by 41
  5. 2017CoNLL-SIGMORPHON 2017 Shared Task: Universal Morphological Reinflection in 52 Languagescited by 40
  6. 2020Morphology Matters: A Multilingual Language Modeling Analysiscited by 37
  7. 2019Pushing the Limits of Low-Resource Morphological Inflectioncited by 29
  8. 2015Segmental Recurrent Neural Networkscited by 17
  9. 2017Cross-lingual, Character-Level Neural Morphological Taggingcited by 17
  10. 2018Unsupervised Cross-lingual Transfer of Word Embedding Spacescited by 16
  11. 2019Meaning to Form: Measuring Systematicity as Informationcited by 16
  12. 2019UDPipe at SIGMORPHON 2019: Contextualized Embeddings, Regularization with Morphological Categories, Corpora Mergingcited by 15
  13. 2015Morphological Inflection Generation Using Character Sequence to Sequence Learningcited by 14
  14. 2018Fortification of Neural Morphological Segmentation Models for Polysynthetic Minimal-Resource Languagescited by 13
  15. 2019Morphological Irregularity Correlates with Frequencycited by 13
  16. 2016Single-Model Encoder-Decoder with Explicit Morphological Representation for Reinflectioncited by 12
  17. 2018Marrying Universal Dependencies and Universal Morphologycited by 11
  18. 2018Imitation Learning for Neural Morphological String Transductioncited by 10
  19. 2020Tackling the Low-resource Challenge for Canonical Segmentationcited by 10
  20. 2021Canonical and Surface Morphological Segmentation for Nguni Languagescited by 10
  21. 2016Cross-Lingual Morphological Tagging for Low-Resource Languagescited by 9
  22. 2017Modeling Target-Side Inflection in Neural Machine Translationcited by 9
  23. 2019Better Character Language Modeling Through Morphologycited by 9
  24. 2015An Unsupervised Method for Uncovering Morphological Chainscited by 8
  25. 2016Cross-Lingual Syntactic Transfer with Limited Resourcescited by 8
  26. 2018Neural Factor Graph Models for Cross-lingual Morphological Taggingcited by 8
  27. 2020Unsupervised Morphological Paradigm Completioncited by 8
  28. 2016Neural Multi-Source Morphological Reinflectioncited by 7
  29. 2019A Simple Joint Model for Improved Contextual Neural Lemmatizationcited by 7
  30. 2020The Paradigm Discovery Problemcited by 6
  31. 2017Unlabeled Data for Morphological Generation With Character-Based Sequence-to-Sequence Modelscited by 5
  32. 2017Align and Copy: UZH at SIGMORPHON 2017 Shared Task for Morphological Reinflectioncited by 5
  33. 2018Neural Transductive Learning and Beyond: Morphological Generation in the Minimal-Resource Settingcited by 5
  34. 2016Neural Morphological Tagging from Characters for Morphologically Rich Languagescited by 4
  35. 2017One-Shot Neural Cross-Lingual Transfer for Paradigm Completioncited by 4
  36. 2020The SIGMORPHON 2020 Shared Task on Unsupervised Morphological Paradigm Completioncited by 4
  37. 2018Copenhagen at CoNLL--SIGMORPHON 2018: Multilingual Inflection in Context with Explicit Morphosyntactic Decodingcited by 3
  38. 2020LowResourceEval-2019: a shared task on morphological analysis for low-resource languagescited by 2

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 1; 2025: 1.

4 papers.

  1. 2024Can we teach language models to gloss endangered languages?cited by 14
  2. 2025Rethinking Tokenization for Rich Morphology: The Dominance of Unigram over BPE and Morphological Alignmentcited by 9
  3. 2023On the Automatic Generation and Simplification of Children's Storiescited by 4
  4. 2023An Investigation of Noise in Morphological Inflectioncited by 3