Unsupervised, Knowledge-Free, and Interpretable Word Sense Disambiguation

TL;DR

This paper introduces an unsupervised, knowledge-free, and interpretable word sense disambiguation system that combines the interpretability of knowledge-based methods with the flexibility of knowledge-free approaches, accessible via a web interface and API.

Contribution

It presents a novel WSD system that is completely unsupervised and knowledge-free yet interpretable, bridging the gap between traditional knowledge-based and modern data-driven methods.

Findings

Provides human-readable sense predictions with interpretable inventories

Offers a web interface for all-word disambiguation tasks

Includes a public API for integration

Abstract

Interpretability of a predictive model is a powerful feature that gains the trust of users in the correctness of the predictions. In word sense disambiguation (WSD), knowledge-based systems tend to be much more interpretable than knowledge-free counterparts as they rely on the wealth of manually-encoded elements representing word senses, such as hypernyms, usage examples, and images. We present a WSD system that bridges the gap between these two so far disconnected groups of methods. Namely, our system, providing access to several state-of-the-art WSD models, aims to be interpretable as a knowledge-based system while it remains completely unsupervised and knowledge-free. The presented tool features a Web interface for all-word disambiguation of texts that makes the sense predictions human readable by providing interpretable word sense inventories, sense representations, and disambiguation results. We provide a public API, enabling seamless integration.