Difference between revisions of "Concept-Based Selectional Preferences and Distributional Representations from Wikipedia Articles"

From Wikipedia Quality
Jump to: navigation, search
(+ Infobox work)
(Embed)
 
Line 9: Line 9:
 
== Overview ==
 
== Overview ==
 
This paper describes the derivation of distributional semantic representations for open class words relative to a concept inventory, and of concepts relative to open class words through grammatical relations extracted from [[Wikipedia]] articles. The concept inventory comes from WikiNet, a large-scale concept network derived from Wikipedia. The distinctive feature of these representations are their relation to a concept network, through which authors can compute selectional preferences of open-class words relative to general concepts. The resource thus derived provides a meaning representation that complements the relational representation captured in the concept network. It covers English open-class words, but the concept base is language independent. The resource can be extended to other languages, with the use of language specific dependency parsers. Good results in metonymy resolution show the resource’s potential use for NLP applications.
 
This paper describes the derivation of distributional semantic representations for open class words relative to a concept inventory, and of concepts relative to open class words through grammatical relations extracted from [[Wikipedia]] articles. The concept inventory comes from WikiNet, a large-scale concept network derived from Wikipedia. The distinctive feature of these representations are their relation to a concept network, through which authors can compute selectional preferences of open-class words relative to general concepts. The resource thus derived provides a meaning representation that complements the relational representation captured in the concept network. It covers English open-class words, but the concept base is language independent. The resource can be extended to other languages, with the use of language specific dependency parsers. Good results in metonymy resolution show the resource’s potential use for NLP applications.
 +
 +
== Embed ==
 +
=== Wikipedia Quality ===
 +
<code>
 +
<nowiki>
 +
Judea, Alex; Nastase, Vivi; Strube, Michael. (2012). "[[Concept-Based Selectional Preferences and Distributional Representations from Wikipedia Articles]]".
 +
</nowiki>
 +
</code>
 +
 +
=== English Wikipedia ===
 +
<code>
 +
<nowiki>
 +
{{cite journal |last1=Judea |first1=Alex |last2=Nastase |first2=Vivi |last3=Strube |first3=Michael |title=Concept-Based Selectional Preferences and Distributional Representations from Wikipedia Articles |date=2012 |url=https://wikipediaquality.com/wiki/Concept-Based_Selectional_Preferences_and_Distributional_Representations_from_Wikipedia_Articles}}
 +
</nowiki>
 +
</code>
 +
 +
=== HTML ===
 +
<code>
 +
<nowiki>
 +
Judea, Alex; Nastase, Vivi; Strube, Michael. (2012). &amp;quot;<a href="https://wikipediaquality.com/wiki/Concept-Based_Selectional_Preferences_and_Distributional_Representations_from_Wikipedia_Articles">Concept-Based Selectional Preferences and Distributional Representations from Wikipedia Articles</a>&amp;quot;.
 +
</nowiki>
 +
</code>

Latest revision as of 02:40, 24 May 2020


Concept-Based Selectional Preferences and Distributional Representations from Wikipedia Articles
Authors
Alex Judea
Vivi Nastase
Michael Strube
Publication date
2012
Links
Original

Concept-Based Selectional Preferences and Distributional Representations from Wikipedia Articles - scientific work related to Wikipedia quality published in 2012, written by Alex Judea, Vivi Nastase and Michael Strube.

Overview

This paper describes the derivation of distributional semantic representations for open class words relative to a concept inventory, and of concepts relative to open class words through grammatical relations extracted from Wikipedia articles. The concept inventory comes from WikiNet, a large-scale concept network derived from Wikipedia. The distinctive feature of these representations are their relation to a concept network, through which authors can compute selectional preferences of open-class words relative to general concepts. The resource thus derived provides a meaning representation that complements the relational representation captured in the concept network. It covers English open-class words, but the concept base is language independent. The resource can be extended to other languages, with the use of language specific dependency parsers. Good results in metonymy resolution show the resource’s potential use for NLP applications.

Embed

Wikipedia Quality

Judea, Alex; Nastase, Vivi; Strube, Michael. (2012). "[[Concept-Based Selectional Preferences and Distributional Representations from Wikipedia Articles]]".

English Wikipedia

{{cite journal |last1=Judea |first1=Alex |last2=Nastase |first2=Vivi |last3=Strube |first3=Michael |title=Concept-Based Selectional Preferences and Distributional Representations from Wikipedia Articles |date=2012 |url=https://wikipediaquality.com/wiki/Concept-Based_Selectional_Preferences_and_Distributional_Representations_from_Wikipedia_Articles}}

HTML

Judea, Alex; Nastase, Vivi; Strube, Michael. (2012). &quot;<a href="https://wikipediaquality.com/wiki/Concept-Based_Selectional_Preferences_and_Distributional_Representations_from_Wikipedia_Articles">Concept-Based Selectional Preferences and Distributional Representations from Wikipedia Articles</a>&quot;.