Concept Extraction Challenge: University of Twente at MSM2013

Mena B. Habib; Maurice Van Keulen; Zhemin Zhu

Concept Extraction Challenge: University of Twente at MSM2013

Mena B. Habib^*, Maurice Van Keulen, Zhemin Zhu

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceeding › Academic › peer-review

1 Downloads (Pure)

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 use AIDA disambiguation system to disambiguate the extracted named entities and hence find their type.

Original language	English
Title of host publication	Making Sense of Microposts (MSM2013) Concept Extraction Challenge
Pages	17-20
Number of pages	4
Publication status	Published - 2013
Externally published	Yes

Keywords

Named Entity Extraction
Named Entity Classification
Social Media Analysis
Twitter Messages

Cite this

@inproceedings{7219874c10f64541ae627b848dc953fd,

title = "Concept Extraction Challenge: University of Twente at MSM2013",

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 use AIDA disambiguation system to disambiguate the extracted named entities and hence find their type.",

keywords = "Named Entity Extraction, Named Entity Classification, Social Media Analysis, Twitter Messages",

author = "Habib, {Mena B.} and Keulen, {Maurice Van} and Zhemin Zhu",

year = "2013",

language = "English",

pages = "17--20",

booktitle = "Making Sense of Microposts (MSM2013) Concept Extraction Challenge",

}

TY - GEN

T1 - Concept Extraction Challenge: University of Twente at MSM2013

AU - Habib, Mena B.

AU - Keulen, Maurice Van

AU - Zhu, Zhemin

PY - 2013

Y1 - 2013

N2 - 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 use AIDA disambiguation system to disambiguate the extracted named entities and hence find their type.

AB - 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 use AIDA disambiguation system to disambiguate the extracted named entities and hence find their type.

KW - Named Entity Extraction

KW - Named Entity Classification

KW - Social Media Analysis

KW - Twitter Messages

M3 - Conference article in proceeding

SP - 17

EP - 20

BT - Making Sense of Microposts (MSM2013) Concept Extraction Challenge

ER -