# Unsupervised Morphological Paradigm Completion

arXiv: https://arxiv.org/abs/2005.00970 · HTML: https://mlsanity.com/paper/2005.00970/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 May 2020.

## Built on by (most cited first, 8 of 8)

- [(Un)solving Morphological Inflection: Lemma Overlap Artificially Inflates Models' Performance](https://mlsanity.com/paper/2108.05682/) (2021)
- [The Zeno's Paradox of `Low-Resource' Languages](https://mlsanity.com/paper/2410.20817/) (2024)
- [Counting the Bugs in ChatGPT's Wugs: A Multilingual Investigation into the Morphological Capabilities of a Large Language Model](https://mlsanity.com/paper/2310.15113/) (2023)
- [Morphological Processing of Low-Resource Languages: Where We Are and What's Next](https://mlsanity.com/paper/2203.08909/) (2022)
- [CaMEL: Case Marker Extraction without Labels](https://mlsanity.com/paper/2203.10010/) (2022)
- [An Investigation of Noise in Morphological Inflection](https://mlsanity.com/paper/2305.16581/) (2023)
- [Minimal Supervision for Morphological Inflection](https://mlsanity.com/paper/2104.08512/) (2021)
- [RUMLEM: A Dictionary-Based Lemmatizer for Romansh](https://mlsanity.com/paper/2604.11233/) (2026)

## Abstract (arXiv)

We propose the task of unsupervised morphological paradigm completion. Given only raw text and a lemma list, the task consists of generating the morphological paradigms, i.e., all inflected forms, of the lemmas. From a natural language processing (NLP) perspective, this is a challenging unsupervised task, and high-performing systems have the potential to improve tools for low-resource languages or to assist linguistic annotators. From a cognitive science perspective, this can shed light on how children acquire morphological knowledge. We further introduce a system for the task, which generates morphological paradigms via the following steps: (i) EDIT TREE retrieval, (ii) additional lemma retrieval, (iii) paradigm size discovery, and (iv) inflection generation. We perform an evaluation on 14 typologically diverse languages. Our system outperforms trivial baselines with ease and, for some languages, even obtains a higher accuracy than minimally supervised systems.