Discovering Corpus-Specific Word Senses

By Beate Dorow, Dominic Widdows. 2003

134 citations recorded by the source corpus.

This paper presents an unsupervised algorithm which automatically discovers word senses from text. The algorithm is based on a graph model representing words and relationships between them. Sense clusters are iteratively computed by clustering the local graph of similar words around an ambiguous word. Discrimination against previously extracted sense clusters enables us to discover new senses. We use the same data for both recognising and resolving ambiguity.

Subfields: Artificial Intelligence, Natural Language Processing

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

In Natural Language Processing

Citations in the corpus

Diachronic Word Embeddings Reveal Statistical Laws of Semantic Change (2016, methodology): “, number of senses in WordNet (Dorow and Widdows, 2003; Ferret, 2004); however, it does have a slight bias towards rating contextually-diverse discourse function words (e.”
Word sense disambiguation: A survey (2009, methodology): “The construction of a cooccurrence graph based on grammatical relations between words in context was described by Widdows and Dorow [2002] (see also Dorow and Widdows [2003]). Given a target ambiguous word w, a local graph Gw is built around w. By normalizing the adjacency matrix associated with Gw,”
Discovering word senses from a network of lexical cooccurrences (2004, methodology): “From a global viewpoint, these two differences lead (Véronis, 2003) and (Dorow and Widdows, 2003) to build finer senses than ours.”
Graph Clustering Via a Discrete Uncoupling Process (2008, methodology): “Additionally, MCL has been applied in corpus linguistics [13, 14, 25], content-based image retrieval [32], peer-to-peer network analysis [57], and social network analysis [46].”
A Survey of Text Clustering Algorithms (2012, methodology): “guage processing research community, with particular interests in discovering word clusters that can characterize word senses [34] or a semantic concept [21].”