Difference between revisions of "Coreference in Wikipedia: Main Concept Resolution"
(+ links) |
(Adding infobox) |
||
Line 1: | Line 1: | ||
+ | {{Infobox work | ||
+ | | title = Coreference in Wikipedia: Main Concept Resolution | ||
+ | | date = 2016 | ||
+ | | authors = [[Abbas Ghaddar]]<br />[[Phillippe Langlais]] | ||
+ | | doi = 10.18653/v1/K16-1023 | ||
+ | | link = http://aclweb.org/anthology/K16-1023 | ||
+ | }} | ||
'''Coreference in Wikipedia: Main Concept Resolution''' - scientific work related to [[Wikipedia quality]] published in 2016, written by [[Abbas Ghaddar]] and [[Phillippe Langlais]]. | '''Coreference in Wikipedia: Main Concept Resolution''' - scientific work related to [[Wikipedia quality]] published in 2016, written by [[Abbas Ghaddar]] and [[Phillippe Langlais]]. | ||
== Overview == | == Overview == | ||
Wikipedia is a resource of choice exploited in many NLP applications, yet authors are not aware of recent attempts to adapt coreference resolution to this resource. In this work, authors revisit a seldom studied task which consists in identifying in a [[Wikipedia]] article all the mentions of the main concept being described. Authors show that by exploiting the Wikipedia markup of a document, as well as links to external knowledge bases such as Freebase, authors can acquire useful information on entities that helps to classify mentions as coreferent or not. Authors designed a classifier which drastically outperforms fair baselines built on top of state-of-the-art coreference resolution systems. Authors also measure the benefits of this classifier in a full coreference resolution pipeline applied to Wikipedia texts. | Wikipedia is a resource of choice exploited in many NLP applications, yet authors are not aware of recent attempts to adapt coreference resolution to this resource. In this work, authors revisit a seldom studied task which consists in identifying in a [[Wikipedia]] article all the mentions of the main concept being described. Authors show that by exploiting the Wikipedia markup of a document, as well as links to external knowledge bases such as Freebase, authors can acquire useful information on entities that helps to classify mentions as coreferent or not. Authors designed a classifier which drastically outperforms fair baselines built on top of state-of-the-art coreference resolution systems. Authors also measure the benefits of this classifier in a full coreference resolution pipeline applied to Wikipedia texts. |
Revision as of 10:25, 16 December 2019
Authors | Abbas Ghaddar Phillippe Langlais |
---|---|
Publication date | 2016 |
DOI | 10.18653/v1/K16-1023 |
Links | Original |
Coreference in Wikipedia: Main Concept Resolution - scientific work related to Wikipedia quality published in 2016, written by Abbas Ghaddar and Phillippe Langlais.
Overview
Wikipedia is a resource of choice exploited in many NLP applications, yet authors are not aware of recent attempts to adapt coreference resolution to this resource. In this work, authors revisit a seldom studied task which consists in identifying in a Wikipedia article all the mentions of the main concept being described. Authors show that by exploiting the Wikipedia markup of a document, as well as links to external knowledge bases such as Freebase, authors can acquire useful information on entities that helps to classify mentions as coreferent or not. Authors designed a classifier which drastically outperforms fair baselines built on top of state-of-the-art coreference resolution systems. Authors also measure the benefits of this classifier in a full coreference resolution pipeline applied to Wikipedia texts.