Concept Extraction Challenge: University of Twente at \MSM2013
M. Habib, D. van Keulen, and M. Zhu. 3rd workshop on Making Sense of Microposts, \MSM 2013, Brazil, CEUR, (May 2013)
Abstract
Twitter messages are a potentially rich source of continuously and instantly updated information. Shortness and informality of such messages are challenges for Natural Language Processing tasks. In this paper we present a hybrid approach for Named Entity Extraction (NEE) and Classification (NEC) for tweets. The system uses the power of the Conditional Random Fields (CRF) and the Support Vector Machines (SVM) in a hybrid way to achieve better results. For named entity type classification we used AIDA YosefHBSW11 disambiguation system to disambiguate the extracted named entities and hence find their type.
Description
Concept Extraction Challenge: University of Twente at #MSM2013 - UTpublications
%0 Conference Paper
%1 so85507
%A Habib, Mena B.
%A van Keulen, Dr.ir. Maurice
%A Zhu, MSc. Zhemin
%B 3rd workshop on Making Sense of Microposts, \MSM 2013
%C Brazil
%D 2013
%I CEUR
%K entitylinking microlink@l3s msm2013
%T Concept Extraction Challenge: University of Twente at \MSM2013
%U http://doc.utwente.nl/85507/
%X Twitter messages are a potentially rich source of continuously and instantly updated information. Shortness and informality of such messages are challenges for Natural Language Processing tasks. In this paper we present a hybrid approach for Named Entity Extraction (NEE) and Classification (NEC) for tweets. The system uses the power of the Conditional Random Fields (CRF) and the Support Vector Machines (SVM) in a hybrid way to achieve better results. For named entity type classification we used AIDA YosefHBSW11 disambiguation system to disambiguate the extracted named entities and hence find their type.
@inproceedings{so85507,
abstract = {Twitter messages are a potentially rich source of continuously and instantly updated information. Shortness and informality of such messages are challenges for Natural Language Processing tasks. In this paper we present a hybrid approach for Named Entity Extraction (NEE) and Classification (NEC) for tweets. The system uses the power of the Conditional Random Fields (CRF) and the Support Vector Machines (SVM) in a hybrid way to achieve better results. For named entity type classification we used AIDA \cite{YosefHBSW11} disambiguation system to disambiguate the extracted named entities and hence find their type. },
added-at = {2015-01-26T17:37:44.000+0100},
address = {Brazil},
author = {{Habib}, Mena B. and van {Keulen}, Dr.ir. Maurice and {Zhu}, MSc. Zhemin},
biburl = {https://www.bibsonomy.org/bibtex/2e0646764ec782ce243428da655eb77e7/asmelash},
booktitle = {3rd workshop on Making Sense of Microposts, \MSM 2013},
description = {Concept Extraction Challenge: University of Twente at #MSM2013 - UTpublications},
interhash = {8af0e9665b3e20486717c712b01464e9},
intrahash = {e0646764ec782ce243428da655eb77e7},
keywords = {entitylinking microlink@l3s msm2013},
month = may,
publisher = {CEUR},
timestamp = {2015-01-26T17:37:44.000+0100},
title = {Concept Extraction Challenge: University of Twente at \MSM2013},
url = {http://doc.utwente.nl/85507/},
year = 2013
}