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 ieKey
%A Cucerzan, Silviu
%D 2007
%J The EMNLP-CoNLL Joint Conference
%K wikipedia wsd
%T Large Scale Named Entity Disambiguation Based on Wikipedia Data
%U http://research.microsoft.com/users/silviu/Papers/emnlp07.pdf
%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{ieKey,
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 = {2007-12-05T16:32:35.000+0100},
author = {Cucerzan, Silviu},
biburl = {https://www.bibsonomy.org/bibtex/23ec97d4bf4a3bd866f9ec24fa0b6c1ed/aquablue},
date = {2007},
interhash = {87b9ac8996ae301051b7382f7bda9cb5},
intrahash = {3ec97d4bf4a3bd866f9ec24fa0b6c1ed},
journal = {The EMNLP-CoNLL Joint Conference},
keywords = {wikipedia wsd},
month = {June},
tech = {Prague},
timestamp = {2007-12-05T16:32:36.000+0100},
title = {Large Scale Named Entity Disambiguation Based on Wikipedia Data },
url = {http://research.microsoft.com/users/silviu/Papers/emnlp07.pdf},
year = 2007
}