Large-Scale Named Entity Disambiguation Based on Wikipedia Data
S. Cucerzan. Proceedings of EMNLP-CoNLL 2007, page 708–716. (2007)
Abstract
This paper presents a large-scale system for the recognition and semantic disambiguation of named entities based on information extracted from a large encyclopedic collection and Web search results. It describes in detail the disambiguation paradigm employed and the information extraction process from Wikipedia. Through a process of maximizing the agreement between the contextual information extracted from Wikipedia and the context of a document, as well as the agreement among the category tags associated with the candidate entities, the implemented system shows high disambiguation accuracy on both news stories and Wikipedia articles.
%0 Conference Paper
%1 cucerzan07
%A Cucerzan, Silviu
%B Proceedings of EMNLP-CoNLL 2007
%D 2007
%K disambiguation entitity name
%P 708–716
%T Large-Scale Named Entity Disambiguation Based on Wikipedia Data
%X This paper presents a large-scale system for the recognition and semantic disambiguation of named entities based on information extracted from a large encyclopedic collection and Web search results. It describes in detail the disambiguation paradigm employed and the information extraction process from Wikipedia. Through a process of maximizing the agreement between the contextual information extracted from Wikipedia and the context of a document, as well as the agreement among the category tags associated with the candidate entities, the implemented system shows high disambiguation accuracy on both news stories and Wikipedia articles.
@inproceedings{cucerzan07,
abstract = {This paper presents a large-scale system for the recognition and semantic disambiguation of named entities based on information extracted from a large encyclopedic collection and Web search results. It describes in detail the disambiguation paradigm employed and the information extraction process from Wikipedia. Through a process of maximizing the agreement between the contextual information extracted from Wikipedia and the context of a document, as well as the agreement among the category tags associated with the candidate entities, the implemented system shows high disambiguation accuracy on both news stories and Wikipedia articles.},
added-at = {2009-02-05T22:13:45.000+0100},
author = {Cucerzan, Silviu},
biburl = {https://www.bibsonomy.org/bibtex/223ede35d6d952febac1530873268a50e/pitman},
booktitle = {Proceedings of EMNLP-CoNLL 2007},
interhash = {87b9ac8996ae301051b7382f7bda9cb5},
intrahash = {23ede35d6d952febac1530873268a50e},
keywords = {disambiguation entitity name},
pages = {708–716},
timestamp = {2009-02-05T22:13:45.000+0100},
title = { Large-Scale Named Entity Disambiguation Based on Wikipedia Data},
year = 2007
}