Word Sense Disambiguation for 158 Languages using Word Embeddings Only
This addresses the challenge of WSD for under-resourced languages that lack training data or linguistic knowledge, providing a scalable solution.
The paper tackles word sense disambiguation (WSD) by developing an unsupervised, knowledge-free method that uses pre-trained word embeddings to induce sense inventories, enabling WSD for 158 languages without requiring supervised or knowledge-based resources.
Disambiguation of word senses in context is easy for humans, but is a major challenge for automatic approaches. Sophisticated supervised and knowledge-based models were developed to solve this task. However, (i) the inherent Zipfian distribution of supervised training instances for a given word and/or (ii) the quality of linguistic knowledge representations motivate the development of completely unsupervised and knowledge-free approaches to word sense disambiguation (WSD). They are particularly useful for under-resourced languages which do not have any resources for building either supervised and/or knowledge-based models. In this paper, we present a method that takes as input a standard pre-trained word embedding model and induces a fully-fledged word sense inventory, which can be used for disambiguation in context. We use this method to induce a collection of sense inventories for 158 languages on the basis of the original pre-trained fastText word embeddings by Grave et al. (2018), enabling WSD in these languages. Models and system are available online.