A Game-Theoretic Approach to Word Sense Disambiguation

Abstract

This paper presents a new model for word sense disambiguation formulated in terms of evolutionary game theory, where each word to be disambiguated is represented as a node on a graph whose edges represent word relations and senses are represented as classes. The words simultaneously update their class membership preferences according to the senses that neighboring words are likely to choose. We use distributional information to weigh the influence that each word has on the decisions of the others and semantic similarity information to measure the strength of compatibility among the choices. With this information we can formulate the word sense disambiguation problem as a constraint satisfaction problem and solve it using tools derived from game theory, maintaining the textual coherence. The model is based on two ideas: similar words should be assigned to similar classes and the meaning of a word does not depend on all the words in a text but just on some of them. The paper provides an in-depth motivation of the idea of modeling the word sense disambiguation problem in terms of game theory, which is illustrated by an example. The conclusion presents an extensive analysis on the combination of similarity measures to use in the framework and a comparison with state-of-the-art systems. The results show that our model outperforms state-of-the-art algorithms and can be applied to different tasks and in different scenarios.Comment: To be published in Computational Linguistic

From Word To Sense Embeddings: A Survey on Vector Representations of Meaning

“…Methods to perform WSD can be roughly divided into two classes: supervised (Zhong & Ng, 2010;Iacobacci, Pilehvar, & Navigli, 2016;Yuan, Richardson, Doherty, Evans, & Altendorf, 2016;Raganato, Delli Bovi, & Navigli, 2017b;Luo, Liu, Xia, Chang, & Sui, 2018) and knowledge-based (Lesk, 1986;Banerjee & Pedersen, 2002;Agirre, de Lacalle, & Soroa, 2014;Moro, Raganato, & Navigli, 2014;Tripodi & Pelillo, 2017;Chaplot & Salakhutdinov, 2018). While supervised methods make use of sense-annotated corpora, knowledge-based methods exploit the structure and content of the underlying knowledge resource (e.g.…”

Non-invasive study of natural dyes on historical textiles from the collection of Michelangelo Guggenheim

“…It is part of a class of algorithms based on game theoretic principles that in recent years were successfully applied to different pattern recognition and classification tasks [50,51]. This algorithm treats the objects to be clustered as nodes of a weighted graph, G. Graph weights can be calculated by means of similarity functions for each pair of objects in the dataset.…”

SenseDefs: a multilingual corpus of semantically annotated textual definitions

“…3.3). NASARI has proved to be effective in various NLP tasks, including not only semantic similarity and WSD (Shalaby and Zadrozny 2015;Camacho-Collados et al 2016b;Tripodi and Pelillo 2017), but also sense clustering (see Sect. 5.2.2), knowledge-base construction and alignment (Lieto et al 2016;Espinosa-Anke et al 2016a;Camacho-Collados and Navigli 2017;Cocos et al 2017), object recognition (Young et al 2016) and text classification (Pilehvar et al 2017).…”