# Pushing the Limits of Low-Resource Morphological Inflection

arXiv: https://arxiv.org/abs/1908.05838 · HTML: https://mlsanity.com/paper/1908.05838/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Aug 2019.

## Built on by (most cited first, 29 of 29)

- [Expanding Pretrained Models to Thousands More Languages via Lexicon-based Adaptation](https://mlsanity.com/paper/2203.09435/) (2022)
- [A Large-Scale Study of Machine Translation in the Turkic Languages](https://mlsanity.com/paper/2109.04593/) (2021)
- [An Audit on the Perspectives and Challenges of Hallucinations in NLP](https://mlsanity.com/paper/2404.07461/) (2024)
- [Does Transliteration Help Multilingual Language Modeling?](https://mlsanity.com/paper/2201.12501/) (2022)
- [Breaking the Script Barrier in Multilingual Pre-Trained Language Models with Transliteration-Based Post-Training Alignment](https://mlsanity.com/paper/2406.19759/) (2024)
- [Can a Transformer Pass the Wug Test? Tuning Copying Bias in Neural Morphological Inflection Models](https://mlsanity.com/paper/2104.06483/) (2021)
- [Smoothing and Shrinking the Sparse Seq2Seq Search Space](https://mlsanity.com/paper/2103.10291/) (2021)
- [Evaluating the Morphosyntactic Well-formedness of Generated Texts](https://mlsanity.com/paper/2103.16590/) (2021)
- [Empowering Cross-lingual Behavioral Testing of NLP Models with Typological Features](https://mlsanity.com/paper/2307.05454/) (2023)
- [The interplay between language similarity and script on a novel multi-layer Algerian dialect corpus](https://mlsanity.com/paper/2105.07400/) (2021)
- [Morphological Processing of Low-Resource Languages: Where We Are and What's Next](https://mlsanity.com/paper/2203.08909/) (2022)
- [Understanding Compositional Data Augmentation in Typologically Diverse Morphological Inflection](https://mlsanity.com/paper/2305.13658/) (2023)
- [Measuring the Effect of Disfluency in Multilingual Knowledge Probing Benchmarks](https://mlsanity.com/paper/2510.15115/) (2025)
- [Computational Morphology with Neural Network Approaches](https://mlsanity.com/paper/2105.09404/) (2021)
- [Dim Wihl Gat Tun: The Case for Linguistic Expertise in NLP for Underdocumented Languages](https://mlsanity.com/paper/2203.09632/) (2022)
- [Character-aware Transformers Learn an Irregular Morphological Pattern Yet None Generalize Like Humans](https://mlsanity.com/paper/2602.14100/) (2026)
- [Minimal Supervision for Morphological Inflection](https://mlsanity.com/paper/2104.08512/) (2021)
- [Generalising Multilingual Concept-to-Text NLG with Language Agnostic Delexicalisation](https://mlsanity.com/paper/2105.03432/) (2021)
- [A Three Step Training Approach with Data Augmentation for Morphological Inflection](https://mlsanity.com/paper/2109.07006/) (2021)
- [Word Segmentation and Morphological Parsing for Sanskrit](https://mlsanity.com/paper/2201.12833/) (2022)
- [Transformers on Multilingual Clause-Level Morphology](https://mlsanity.com/paper/2211.01736/) (2022)
- [Is linguistically-motivated data augmentation worth it?](https://mlsanity.com/paper/2506.03593/) (2025)
- [Enhancing Cross-Lingual Transfer through Reversible Transliteration: A Huffman-Based Approach for Low-Resource Languages](https://mlsanity.com/paper/2509.17493/) (2025)
- [Modeling the Graphotactics of Low-Resource Languages Using Sequential GANs](https://mlsanity.com/paper/2210.14409/) (2022)
- [A Framework for Bidirectional Decoding: Case Study in Morphological Inflection](https://mlsanity.com/paper/2305.12580/) (2023)
- [Morphological Inflection with Phonological Features](https://mlsanity.com/paper/2306.12581/) (2023)
- [Script-Agnostic Language Identification](https://mlsanity.com/paper/2406.17901/) (2024)
- [Probing Subphonemes in Morphology Models](https://mlsanity.com/paper/2505.11297/) (2025)
- [Responsible AI for General-Purpose Systems: Overview, Challenges, and A Path Forward](https://mlsanity.com/paper/2601.13122/) (2026)

## Abstract (arXiv)

Recent years have seen exceptional strides in the task of automatic morphological inflection generation. However, for a long tail of languages the necessary resources are hard to come by, and state-of-the-art neural methods that work well under higher resource settings perform poorly in the face of a paucity of data. In response, we propose a battery of improvements that greatly improve performance under such low-resource conditions. First, we present a novel two-step attention architecture for the inflection decoder. In addition, we investigate the effects of cross-lingual transfer from single and multiple languages, as well as monolingual data hallucination. The macro-averaged accuracy of our models outperforms the state-of-the-art by 15 percentage points. Also, we identify the crucial factors for success with cross-lingual transfer for morphological inflection: typological similarity and a common representation across languages.