An Experimental Study of Graph Connectivity for Unsupervised Word Sense Disambiguation

By Roberto Navigli, Mirella Lapata. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010

316 citations recorded by the source corpus.

Word sense disambiguation (WSD), the task of identifying the intended meanings (senses) of words in context, has been a long-standing research objective for natural language processing. In this paper, we are concerned with graph-based algorithms for large-scale WSD. Under this framework, finding the right sense for a given word amounts to identifying the most ¿important¿ node among the set of graph nodes representing its senses. We introduce a graph-based WSD algorithm which has few parameters and does not require sense-annotated data for training. Using this algorithm, we investigate several measures of graph connectivity with the aim of identifying those best suited for WSD. We also examine how the chosen lexicon and its connectivity influences WSD performance. We report results on standard data sets and show that our graph-based approach performs comparably to the state of the art.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/e6066a0e23f2fde6908b6fffcbd5e598cb443f7d

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

A Unified Model for Word Sense Representation and Disambiguation (2014, result): “We also compare our results with four systems 7 : Static PageRank (A-girre et al., 2009), the k nearest neighbor algorith-m ( k -NN), Degree (Navigli and Lapata, 2010) and Personalized PageRank (Agirre et al., 2009 (Koeling et al., 2005). similar to the test example.”
Entity Linking meets Word Sense Disambiguation: a Unified Approach (2014, background): “Other approaches, instead, leverage the structural properties of the knowledge base by exploiting centrality and connectivity measures (Sinha and Mihalcea, 2007; Tsatsaronis et al., 2007; Agirre and Soroa, 2009; Navigli and Lapata, 2010).”
BabelNet: Building a Very Large Multilingual Semantic Network (2010, background): “Recent studies in the difficult task of Word Sense Disambiguation (Navigli, 2009b, WSD) have shown the impact of the amount and quality of lexical knowledge (Cuadros and Rigau, 2006): richer knowledge sources can be of great benefit to both knowledge-lean systems (Navigli and Lapata, 2010) and super”
Structured Lexical Similarity via Convolution Kernels on Dependency Trees (2011, methodology): “graphs, are enough similar, as explored in (Mihalcea, 2005; Zhao et al., 2009; Fürstenau and Lapata, 2009; Navigli and Lapata, 2010).”