Using Measures of Semantic Relatedness for Word Sense Disambiguation

By Siddharth Patwardhan, Satanjeev Banerjee, Ted Pedersen. Conference on Intelligent Text Processing and Computational Linguistics, 2003

581 citations recorded by the source corpus.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/eaa82498a122bb846f13c6419d5752f1e2109320

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

Human and Machine Judgements for Russian Semantic Relatedness (2016, background): “Semantic relatedness is an important building block of NLP techniques, such as text similarity [5,6], word sense disambiguation [7], query expansion [8] and some others [9].”
WordNet::Similarity - Measuring the Relatedness of Concepts (2004, methodology): “There are three such measures in the package: hso (Hirst and St-Onge, 1998), lesk (Banerjee and Pedersen, 2003), and vector (Patwardhan, 2003).”
Measuring the Semantic Similarity of Texts (2005, methodology): “We use the WordNet-based implementation of these metrics, as available in the WordNet::Similarity package (Patwardhan et al., 2003).”
Automatically Creating Datasets for Measures of Semantic Relatedness (2006, background): “The latter question is tackled by application-speciﬁc evaluation, where a measure is tested within the framework of a certain application, e.g. word sense disambiguation (Patwardhan et al., 2003) or malapropism detection (Budanitsky and Hirst, 2006).”
Turkers, Scholars, "Arafat" and "Peace": Cultural Communities and Algorithmic Gold Standards (2015, background): “These applications range from low-level tasks like word sense disambiguation (e.g. [28]) and coreference resolution (e.g. [32]) to high-level technologies like search [6, 34] and information visualization systems [4, 37, 3].”
Measures of semantic similarity and relatedness in the biomedical domain (2007, methodology): “But it has also been shown [10] that assigning all of the concepts mapped to a single term, the same frequency count as the term also works well.”
Using the Structure of a Conceptual Network in Computing Semantic Relatedness (2005, background): “textual definitions of words therein as an underlying knowledge base [1, 11], or operate on the structure of a conceptual network, whereby textual definitions themselves are not available [9, 7].”
An Improved Model of Semantic Similarity Based on Lexical Co-Occurrence (2005, methodology): “There have been several efforts to base a measure of semantic similarity on the WordNet database, some of which are reviewed in Budanitsky and Hirst (2001), Patwardhan, Banerjee, and Pedersen (2003), and Jarmasz and Szpakowicz (2003).”
Using WordNet-based Context Vectors to Estimate the Semantic Relatedness of Concepts (2006, background): “It has also been shown that these techniques prove useful for tasks such as word sense disambiguation (Patwardhan et al., 2003), real-word spelling correction (Budanitsky and Hirst, 2001) and information extraction (Stevenson and Greenwood, 2005), among others.”
A Survey of Text Similarity Approaches (2013, background): “In other words, Semantic similarity is a kind of relatedness between two words, it covers a broader range of relationships between concepts that includes extra similarity relations such as is-a-kind-of, is-a-specificexample-of, is-a-part-of, is-the-opposite-of [28].”
Unsupervised Graph-basedWord Sense Disambiguation Using Measures of Word Semantic Similarity (2007, unknown): “We use the WordNet-based implementation of these metrics, as available in the WordNet::Similarity package [14].”
Cross-lingual Semantic Relatedness Using Encyclopedic Knowledge (2009, methodology): “Measures of word relatedness were found useful in a large number of natural language processing applications, including word sense disambiguation (Patwardhan et al., 2003), synonym identiﬁcation (Turney, 2001), automated essay scoring (Foltz et al., 1999), malapropism detection (Budanitsky and…”
Text-to-Text Semantic Similarity for Automatic Short Answer Grading (2009, methodology): “For the knowledge-based measures, we use the WordNet-based implementation of the word-to-word similarity metrics, as available in the Word-Net::Similarity package (Patwardhan et al., 2003).”
Evaluating WordNet-based Measures of Lexical Semantic Relatedness (2006, background): “21 Patwardhan et al.’s measure is based on the idea, originally due to Lesk (1986), of measuring the degree of relatedness of two words by the number of string overlaps in their dictionary definitions or glosses.”
Semantic similarity methods in wordNet and their application to information retrieval on the web (2005, background): “Word sense disambiguation [11] can also be applied to detecting the correct sense to expand (rather than expanding the most common sense of each term).”
Corpus-based and Knowledge-based Measures of Text Semantic Similarity (2006, methodology): “Such measures have been successfully applied to language processing tasks such as malapropism detection (Budanitsky & Hirst 2001), word sense disambiguation ( Patwardhan, Banerjee, & Pedersen 2003 ), and synonym identification (Turney 2001).”