{"id":{"repo_id":"unt","oai_identifier":"info:ark/67531/metadc4969"},"canonical_url":"https://search.dev.ndltd.org/etd/unt/info:ark/67531/metadc4969","repository":{"repo_id":"unt","name":"University of North Texas","base_url":"https://digital.library.unt.edu/oai/"},"display":{"title":"A Minimally Supervised Word Sense Disambiguation Algorithm Using Syntactic Dependencies and Semantic Generalizations","abstract":"Natural language is inherently ambiguous. For example, the word \"bank\" can mean a financial institution or a river shore. Finding the correct meaning of a word in a particular context is a task known as word sense disambiguation (WSD), which is essential for many natural language processing applications such as machine translation, information retrieval, and others. While most current WSD methods try to disambiguate a small number of words for which enough annotated examples are available, the method proposed in this thesis attempts to address all words in unrestricted text. The method is based on constraints imposed by syntactic dependencies and concept generalizations drawn from an external dictionary. The method was tested on standard benchmarks as used during the SENSEVAL-2 and SENSEVAL-3 WSD international evaluation exercises, and was found to be competitive.","abstract_html":"Natural language is inherently ambiguous. For example, the word "bank" can mean a financial institution or a river shore. Finding the correct meaning of a word in a particular context is a task known as word sense disambiguation (WSD), which is essential for many natural language processing applications such as machine translation, information retrieval, and others. While most current WSD methods try to disambiguate a small number of words for which enough annotated examples are available, the method proposed in this thesis attempts to address all words in unrestricted text. The method is based on constraints imposed by syntactic dependencies and concept generalizations drawn from an external dictionary. The method was tested on standard benchmarks as used during the SENSEVAL-2 and SENSEVAL-3 WSD international evaluation exercises, and was found to be competitive.","abstract_has_math":false,"creators":["Faruque, Md. Ehsanul"],"institution":"University of North Texas","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":["Mihalcea, Rada, 1974-","Tarau, Paul","Chen, Jiangping"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2005,"date_issued":"2005-12","date_published":"2005-12","updated_at":"2026-07-24T05:35:09Z","subjects":["Computational linguistics.","Discourse analysis.","Semantics -- Data processing.","word sense disambiguation","minimally supervised algorithm","semantic generalizations","machine translation","syntactic dependencies"],"languages":["English"],"rights":["Public","Copyright","Faruque, Md. Ehsanul","Copyright is held by the author, unless otherwise noted. All rights reserved."],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["oclc: 68903162","https://digital.library.unt.edu/ark:/67531/metadc4969/","ark: ark:/67531/metadc4969"],"render_values":[{"text":"oclc: 68903162","href":null,"code":true},{"text":"https://digital.library.unt.edu/ark:/67531/metadc4969/","href":"https://digital.library.unt.edu/ark:/67531/metadc4969/","code":true},{"text":"ark: ark:/67531/metadc4969","href":null,"code":true}]}]},"links":{"outbound_url":"https://doi.org/10.12794/metadc4969","outbound_label":"DOI","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Mihalcea, Rada, 1974-","Tarau, Paul","Chen, Jiangping"]},{"key":"dc:creator","label":"Author","values":["Faruque, Md. Ehsanul"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2005-12"]},{"key":"dc:publisher","label":"Institution","values":["University of North Texas"]},{"key":"dc:type","label":"Dc Type","values":["Thesis or Dissertation"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Computational linguistics.","Discourse analysis.","Semantics -- Data processing.","word sense disambiguation","minimally supervised algorithm","semantic generalizations","machine translation","syntactic dependencies"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["English"]},{"key":"dc:rights","label":"Dc Rights","values":["Public","Copyright","Faruque, Md. Ehsanul","Copyright is held by the author, unless otherwise noted. All rights reserved."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["oclc: 68903162","doi: 10.12794/metadc4969","https://digital.library.unt.edu/ark:/67531/metadc4969/","ark: ark:/67531/metadc4969"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Natural language is inherently ambiguous. For example, the word \"bank\" can mean a financial institution or a river shore. Finding the correct meaning of a word in a particular context is a task known as word sense disambiguation (WSD), which is essential for many natural language processing applications such as machine translation, information retrieval, and others. While most current WSD methods try to disambiguate a small number of words for which enough annotated examples are available, the method proposed in this thesis attempts to address all words in unrestricted text. The method is based on constraints imposed by syntactic dependencies and concept generalizations drawn from an external dictionary. The method was tested on standard benchmarks as used during the SENSEVAL-2 and SENSEVAL-3 WSD international evaluation exercises, and was found to be competitive."]},{"key":"dc:format","label":"Dc Format","values":["Text"]},{"key":"dc:title","label":"Title","values":["A Minimally Supervised Word Sense Disambiguation Algorithm Using Syntactic Dependencies and Semantic Generalizations"]}]}],"canonical_facts":{"dc:contributor":["Mihalcea, Rada, 1974-","Tarau, Paul","Chen, Jiangping"],"dc:creator":["Faruque, Md. Ehsanul"],"dc:date":["2005-12"],"dc:description":["Natural language is inherently ambiguous. For example, the word \"bank\" can mean a financial institution or a river shore. Finding the correct meaning of a word in a particular context is a task known as word sense disambiguation (WSD), which is essential for many natural language processing applications such as machine translation, information retrieval, and others. While most current WSD methods try to disambiguate a small number of words for which enough annotated examples are available, the method proposed in this thesis attempts to address all words in unrestricted text. The method is based on constraints imposed by syntactic dependencies and concept generalizations drawn from an external dictionary. The method was tested on standard benchmarks as used during the SENSEVAL-2 and SENSEVAL-3 WSD international evaluation exercises, and was found to be competitive."],"dc:format":["Text"],"dc:identifier":["oclc: 68903162","doi: 10.12794/metadc4969","https://digital.library.unt.edu/ark:/67531/metadc4969/","ark: ark:/67531/metadc4969"],"dc:language":["English"],"dc:publisher":["University of North Texas"],"dc:rights":["Public","Copyright","Faruque, Md. Ehsanul","Copyright is held by the author, unless otherwise noted. All rights reserved."],"dc:subject":["Computational linguistics.","Discourse analysis.","Semantics -- Data processing.","word sense disambiguation","minimally supervised algorithm","semantic generalizations","machine translation","syntactic dependencies"],"dc:title":["A Minimally Supervised Word Sense Disambiguation Algorithm Using Syntactic Dependencies and Semantic Generalizations"],"dc:type":["Thesis or Dissertation"]},"updated_at":"2026-07-24T05:35:09Z"}