Language models in word sense disambiguation for Polish

TL;DR

This paper explores two neural language model-based unsupervised approaches for Polish word sense disambiguation, achieving results comparable to supervised methods and offering a solution for languages lacking annotated data.

Contribution

Introduces two novel unsupervised neural language model methods for Polish WSD, outperforming previous unsupervised approaches and matching supervised results.

Findings

F1 score of 0.68 on Polish WSD

Significant improvement over previous unsupervised methods

Potential applicability to other low-resource languages

Abstract

In the paper, we test two different approaches to the {unsupervised} word sense disambiguation task for Polish. In both methods, we use neural language models to predict words similar to those being disambiguated and, on the basis of these words, we predict the partition of word senses in different ways. In the first method, we cluster selected similar words, while in the second, we cluster vectors representing their subsets. The evaluation was carried out on texts annotated with plWordNet senses and provided a relatively good result (F1=0.68 for all ambiguous words). The results are significantly better than those obtained for the neural model-based unsupervised method proposed in \cite{waw:myk:17:Sense} and are at the level of the supervised method presented there. The proposed method may be a way of solving word sense disambiguation problem for languages that lack sense annotated data.