Exploiting semantic role labeling, WordNet and Wikipedia for coreference resolution

From WikiLit
Jump to: navigation, search
Publication (help)
Exploiting semantic role labeling, WordNet and Wikipedia for coreference resolution
Authors: Simone Paolo Ponzetto, Michael Strube [edit item]
Citation: HLT-NAACL '06 Proceedings of the main conference on Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics  : 192-199. 2006.
Publication type: Conference paper
Peer-reviewed: Yes
Database(s):
DOI: 10.3115/1220835.1220860.
Google Scholar cites: Citations
Link(s): Paper link
Added by Wikilit team: Added on initial load
Search
Article: Google Scholar BASE PubMed
Other scholarly wikis: AcaWiki Brede Wiki WikiPapers
Web search: Bing Google Yahoo!Google PDF
Other:
Services
Format: BibTeX
Exploiting semantic role labeling, WordNet and Wikipedia for coreference resolution is a publication by Simone Paolo Ponzetto, Michael Strube.


[edit] Abstract

In this paper we present an extension of a machine learning based coreference resolution system which uses features induced from different semantic knowledge sources. These features represent knowledge mined from {WordNet} and Wikipedia, as well as information about semantic role labels. We show that semantic features indeed improve the performance on different referring expression types such as pronouns and common nouns.

[edit] Research questions

"This paper explores whether coreference resolution can benefit from semantic knowledge sources. More specifically, whether a machine learning based approach to coreference resolution can be improved and which phenomena are affected by such information. We investigate the use of the WordNet and Wikipedia taxonomies for extracting semantic similarity and relatedness measures, as well as semantic parsing information in terms of semantic role labeling (Gildea & Jurafsky, 2002, SRL henceforth)."

Research details

Topics: Other natural language processing topics [edit item]
Domains: Computer science [edit item]
Theory type: Design and action [edit item]
Wikipedia coverage: Sample data [edit item]
Theories: "Undetermined" [edit item]
Research design: Experiment [edit item]
Data source: Experiment responses, Websites, Wikipedia pages [edit item]
Collected data time dimension: Cross-sectional [edit item]
Unit of analysis: Article [edit item]
Wikipedia data extraction: Dump [edit item]
Wikipedia page type: Article [edit item]
Wikipedia language: English [edit item]

[edit] Conclusion

"Empirical results show that coreference resolution benefits from semantics. The generated model is able to learn selectional preferences in cases where surface morpho-syntactic features do not suffice, i.e. pronoun and common name resolution. While the results given by using ‘the free encyclopedia that anyone can edit’ are satisfactory, major improvements can come from developing efficient query strategies – i.e. a more refined disambiguation technique taking advantage of the context in which the queries (e.g. referring expressions) occur."

[edit] Comments


Further notes[edit]

Facts about "Exploiting semantic role labeling, WordNet and Wikipedia for coreference resolution"RDF feed
AbstractIn this paper we present an extension of aIn this paper we present an extension of a machine learning based coreference resolution system which uses features induced from different semantic knowledge sources. These features represent knowledge mined from {WordNet} and Wikipedia, as well as information about semantic role labels. We show that semantic features indeed improve the performance on different referring expression types such as pronouns and common nouns.n types such as pronouns and common nouns.
Added by wikilit teamAdded on initial load +
Collected data time dimensionCross-sectional +
ConclusionEmpirical results show that coreference reEmpirical results show that coreference resolution

benefits from semantics. The generated model is able to learn selectional preferences in cases where surface morpho-syntactic features do not suffice, i.e. pronoun and common name resolution. While the results given by using ‘the free encyclopedia that anyone can edit’ are satisfactory, major improvements can come from developing efficient query strategies – i.e. a more refined disambiguation technique taking advantage of the context in which the

queries (e.g. referring expressions) occur.
ueries (e.g. referring expressions) occur.
Data sourceExperiment responses +, Websites + and Wikipedia pages +
Doi10.3115/1220835.1220860 +
Google scholar urlhttp://scholar.google.com/scholar?ie=UTF-8&q=%22Exploiting%2Bsemantic%2Brole%2Blabeling%2C%2BWordNet%2Band%2BWikipedia%2Bfor%2Bcoreference%2Bresolution%22 +
Has authorSimone Paolo Ponzetto + and Michael Strube +
Has domainComputer science +
Has topicOther natural language processing topics +
Pages192-199 +
Peer reviewedYes +
Publication typeConference paper +
Published inHLT-NAACL '06 Proceedings of the main conference on Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics +
Research designExperiment +
Research questionsThis paper explores whether coreference reThis paper explores whether coreference resolution

can benefit from semantic knowledge sources. More specifically, whether a machine learning based approach to coreference resolution can be improved and which phenomena are affected by such information. We investigate the use of the WordNet and Wikipedia taxonomies for extracting semantic similarity and relatedness measures, as well as semantic parsing information in terms of semantic role labeling

(Gildea & Jurafsky, 2002, SRL henceforth).
(Gildea & Jurafsky, 2002, SRL henceforth).
Revid10,761 +
TheoriesUndetermined
Theory typeDesign and action +
TitleExploiting semantic role labeling, WordNet and Wikipedia for coreference resolution
Unit of analysisArticle +
Urlhttp://dl.acm.org/citation.cfm?id=1220835.1220860 +
Wikipedia coverageSample data +
Wikipedia data extractionDump +
Wikipedia languageEnglish +
Wikipedia page typeArticle +
Year2006 +