Unsupervised Morphological Paradigm Completion
This addresses a challenging unsupervised task that could improve tools for low-resource languages or assist linguistic annotators, though it appears incremental as it builds on existing methods.
The paper tackles the problem of unsupervised morphological paradigm completion, which involves generating all inflected forms of lemmas from raw text and a lemma list, and shows that their system outperforms trivial baselines and, for some languages, achieves higher accuracy than minimally supervised systems.
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.