Abstract | Previous research has conflicting conclusions on whether word sense disambiguation (WSD) systems can improve information retrieval (IR) performance. |
Abstract | Together with the senses predicted for words in documents, we propose a novel approach to incorporate word senses into the language modeling approach to IR and also exploit the integration of synonym relations. |
Abstract | Our experimental results on standard TRE C collections show that using the word senses tagged by a supervised WSD system, we obtain significant improvements over a state-of-the-art IR system. |
Introduction | Word sense disambiguation (WSD) is the task of identifying the correct meaning of a word in context. |
Introduction | Some of the early research showed a drop in retrieval performance by using word senses (Krovetz and Croft, 1992; Voorhees, 1993). |
Introduction | Some other experiments observed improvements by integrating word senses in IR systems (Schutze and Pedersen, 1995; Gonzalo et al., 1998; Stokoe et al., 2003; Kim et al., 2004). |
Related Work | However, it is hard to judge the effect of word senses because of the overall poor performances of their baseline method and their system. |
Word Sense Disambiguation | 4.1 Word sense disambiguation system |
Introduction | Reisinger and Mooney (2010b) introduced a multi-prototype VSM where word sense discrimination is first applied by clustering contexts, and then prototypes are built using the contexts of the sense-labeled words. |
Multi-Prototype Neural Language Model | We present a way to use our learned single-prototype embeddings to represent each context window, which can then be used by clustering to perform word sense discrimination (Schutze, 1998). |
Related Work | The multi-prototype approach has been widely studied in models of categorization in psychology (Rosseel, 2002; Griffiths et al., 2009), while Schutze (1998) used clustering of contexts to perform word sense discrimination. |
Existing algorithms 3.1 Yarowsky | th is similar to that of Yarowsky (1995) but is better specified and omits word sense disambiguation optimizations. |
Graph propagation | The tasks of Eisner and Karakos (2005) are word sense disambiguation on several English words which have two senses corresponding to two different words in French. |
Graph propagation | There is no difference on the word sense data sets. |