Exploiting Semantic Role Labeling, Wordnet and Wikipedia for Coreference Resolution

From Wikipedia Quality
Revision as of 02:48, 11 June 2019 by Sophia (talk | contribs) (Creating a new page - Exploiting Semantic Role Labeling, Wordnet and Wikipedia for Coreference Resolution)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to: navigation, search

Exploiting Semantic Role Labeling, Wordnet and Wikipedia for Coreference Resolution - scientific work related to Wikipedia quality published in 2006, written by Simone Paolo Ponzetto and Michael Strube.

Overview

In this paper authors 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. Authors show that semantic features indeed improve the performance on different referring expression types such as pronouns and common nouns.