Semi-supervised Learning with Induced Word Senses for State of the Art Word Sense Disambiguation

Abstract

Word Sense Disambiguation (WSD) aims to determine the meaning of a word in context, and successful approaches are known to benefit many applications in Natural Language Processing. Although supervised learning has been shown to provide superior WSD performance, current sense-annotated corpora do not contain a sufficient number of instances per word type to train supervised systems for all words. While unsupervised techniques have been proposed to overcome this data sparsity problem, such techniques have not outperformed supervised methods. In this paper, we propose a new approach to building semi-supervised WSD systems that combines a small amount of sense-annotated data with information from Word Sense Induction, a fully-unsupervised technique that automatically learns the different senses of a word based on how it is used. In three experiments, we show how sense induction models may be effectively combined to ultimately produce high-performance semi-supervised WSD systems that exceed the performance of state-of-the-art supervised WSD techniques trained on the same sense-annotated data. We anticipate that our results and released software will also benefit evaluation practices for sense induction systems and those working in low-resource languages by demonstrating how to quickly produce accurate WSD systems with minimal annotation effort.

Word Sense Disambiguation: A Unified Evaluation Framework and Empirical Comparison

“…In this work we compare supervised systems and study the role of their underlying senseannotated training corpus. Since semi-supervised models have been shown to outperform fully supervised systems in some settings (Taghipour and Ng, 2015b;Başkaya and Jurgens, 2016;Iacobacci et al, 2016;Yuan et al, 2016), we evaluate and compare models using both manually-curated and automatically-constructed sense-annotated corpora for training.…”

Neural Sequence Learning Models for Word Sense Disambiguation

“…Supervised models have been shown to consistently outperform knowledge-based ones in all standard benchmarks (Raganato et al, 2017), at the expense, however, of harder training and limited flexibility. First of all, obtaining reliable sense-annotated corpora is highly expensive and especially difficult when non-expert annotators are involved (de Lacalle and Agirre, 2015), and as a consequence approaches based on unlabeled data and semisupervised learning are emerging (Taghipour and Ng, 2015b;Başkaya and Jurgens, 2016;Yuan et al, 2016;Pasini and Navigli, 2017).…”

Graph Convolutional Network for Word Sense Disambiguation

“…Mahmoodv and Hourali [29] used the machine learning algorithm with minimal supervision to disambiguate word senses based on features of target word and collaborative learning method. Başkaya and Jurgens [30] gave a semisupervised WSD method that combines a small amount of annotated data with information from word sense induction. Navigli and Velardi [31] created structural specifications of possible senses for each word in context and selected the best hypothesis with G grammar.…”