Title

Evaluating A Semantic Network Automatically Constructed From Lexical Co-Occurrence On A Word Sense Disambiguation Task

Abstract

We describe the extension and objective evaluation of a network1 of semantically related noun senses (or concepts) that has been automatically acquired by analyzing lexical co occurrence in Wikipedia. The acquisition process makes no use of the metadata or links that have been manually built into the encyclopedia, and nouns in the network are automatically disambiguated to their corresponding noun senses without supervision. For this task, we use the noun sense inventory of Word Net 3.0. Thus, this work can be conceived of as augmenting the Word Net noun ontology with un weighted, undirected related to edges between synsets. Our network contains 208,832 such edges. © 2011 Association for Computational Linguistics.

Publication Date

12-1-2011

Publication Title

CoNLL 2011 - Fifteenth Conference on Computational Natural Language Learning, Proceedings of the Conference

Number of Pages

190-199

Document Type

Article; Proceedings Paper

Personal Identifier

scopus

Socpus ID

84862288586 (Scopus)

Source API URL

https://api.elsevier.com/content/abstract/scopus_id/84862288586

This document is currently not available here.

Share

COinS