KDSL: a Knowledge-Driven Supervised Learning Framework for Word Sense Disambiguation

TL;DR

KDSL is a knowledge-driven framework that automatically generates sense-labeled data from unlabeled corpora using WordNet, improving word sense disambiguation performance especially when manual annotations are scarce.

Contribution

It introduces DisDict, a semantic knowledge base from WordNet, and a joint supervised-unsupervised neural framework for WSD that reduces reliance on manual labels.

Findings

Outperforms state-of-the-art WSD methods on major benchmarks.

Effective even without manually labeled data.

Demonstrates the utility of knowledge-based data generation in WSD.

Abstract

We propose KDSL, a new word sense disambiguation (WSD) framework that utilizes knowledge to automatically generate sense-labeled data for supervised learning. First, from WordNet, we automatically construct a semantic knowledge base called DisDict, which provides refined feature words that highlight the differences among word senses, i.e., synsets. Second, we automatically generate new sense-labeled data by DisDict from unlabeled corpora. Third, these generated data, together with manually labeled data and unlabeled data, are fed to a neural framework conducting supervised and unsupervised learning jointly to model the semantic relations among synsets, feature words and their contexts. The experimental results show that KDSL outperforms several representative state-of-the-art methods on various major benchmarks. Interestingly, it performs relatively well even when manually labeled data is unavailable, thus provides a potential solution for similar tasks in a lack of manual annotations.