Lemma Dilemma: On Lemma Generation Without Domain- or Language-Specific Training Data
This addresses the challenge of lemmatization for low-resource languages or domains where supervised data is unavailable, offering a practical solution with broad NLP applications.
The paper tackles the problem of lemmatization without domain- or language-specific training data by evaluating large language models (LLMs) for in-context lemma generation, finding that LLMs achieve state-of-the-art results for most of 12 languages without fine-tuning, using only a few examples.
Lemmatization is the task of transforming all words in a given text to their dictionary forms. While large language models (LLMs) have demonstrated their ability to achieve competitive results across a wide range of NLP tasks, there is no prior evidence of how effective they are in the contextual lemmatization task. In this paper, we empirically investigate the capacity of the latest generation of LLMs to perform in-context lemmatization, comparing it to the traditional fully supervised approach. In particular, we consider the setting in which supervised training data is not available for a target domain or language, comparing (i) encoder-only supervised approaches, fine-tuned out-of-domain, and (ii) cross-lingual methods, against direct in-context lemma generation with LLMs. Our experimental investigation across 12 languages of different morphological complexity finds that, while encoders remain competitive in out-of-domain settings when fine-tuned on gold data, current LLMs reach state-of-the-art results for most languages by directly generating lemmas in-context without prior fine-tuning, provided just with a few examples. Data and code available upon publication: https://github.com/oltoporkov/lemma-dilemma