DCU-UVT.:  Word-Level Language Classification with Code-Mixed Data

Utsab Barman; Joachim Wagner; Grzegorz Chrupala; Jennifer Foster

DCU-UVT. Word-Level Language Classification with Code-Mixed Data

Utsab Barman, Joachim Wagner, Grzegorz Chrupala, Jennifer Foster

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific

Abstract

This paper describes the DCU-UVT team’s participation in the Language Identification in Code-Switched Data shared task in the Workshop on Computational Approaches to Code Switching. Word-level classification experiments were carried out using a simple dictionary-based method, linear kernel support vector machines (SVMs) with and without contextual clues, and a k-nearest neighbour approach. Based on these experiments,
we select our SVM-based system with contextual clues as our final system and present results for the Nepali-English and Spanish-English datasets.

Original language	English
Title of host publication	First Workshop on Computational Approaches to Code Switching
Publisher	Association for Computational Linguistics (ACL)
Pages	127-132
Number of pages	6
ISBN (Electronic)	9781937284961
Publication status	Published - 2014
Event	Conference on Empirical Methods in Natural Language Processing - Doha, Qatar Duration: 25 Oct 2014 → 29 Oct 2014

Conference

Conference	Conference on Empirical Methods in Natural Language Processing
Country/Territory	Qatar
City	Doha
Period	25/10/14 → 29/10/14

Access to Document

http://www.aclweb.org/anthology/W/W14/W14-39.pdf#page=135

Cite this

@inproceedings{5381e8797e60480e81411376ef32a5c6,

title = "DCU-UVT.: Word-Level Language Classification with Code-Mixed Data",

abstract = "This paper describes the DCU-UVT team{\textquoteright}s participation in the Language Identification in Code-Switched Data shared task in the Workshop on Computational Approaches to Code Switching. Word-level classification experiments were carried out using a simple dictionary-based method, linear kernel support vector machines (SVMs) with and without contextual clues, and a k-nearest neighbour approach. Based on these experiments, we select our SVM-based system with contextual clues as our final system and present results for the Nepali-English and Spanish-English datasets. ",

author = "Utsab Barman and Joachim Wagner and Grzegorz Chrupala and Jennifer Foster",

year = "2014",

language = "English",

pages = "127--132",

booktitle = "First Workshop on Computational Approaches to Code Switching",

publisher = "Association for Computational Linguistics (ACL)",

note = "Conference on Empirical Methods in Natural Language Processing ; Conference date: 25-10-2014 Through 29-10-2014",

}

Barman, U, Wagner, J, Chrupala, G & Foster, J 2014, DCU-UVT. Word-Level Language Classification with Code-Mixed Data. in First Workshop on Computational Approaches to Code Switching. Association for Computational Linguistics (ACL), pp. 127-132, Conference on Empirical Methods in Natural Language Processing, Doha, Qatar, 25/10/14. <http://www.aclweb.org/anthology/W/W14/W14-39.pdf#page=135>

TY - GEN

T1 - DCU-UVT.

T2 - Conference on Empirical Methods in Natural Language Processing

AU - Barman, Utsab

AU - Wagner, Joachim

AU - Chrupala, Grzegorz

AU - Foster, Jennifer

PY - 2014

Y1 - 2014

N2 - This paper describes the DCU-UVT team’s participation in the Language Identification in Code-Switched Data shared task in the Workshop on Computational Approaches to Code Switching. Word-level classification experiments were carried out using a simple dictionary-based method, linear kernel support vector machines (SVMs) with and without contextual clues, and a k-nearest neighbour approach. Based on these experiments, we select our SVM-based system with contextual clues as our final system and present results for the Nepali-English and Spanish-English datasets.

AB - This paper describes the DCU-UVT team’s participation in the Language Identification in Code-Switched Data shared task in the Workshop on Computational Approaches to Code Switching. Word-level classification experiments were carried out using a simple dictionary-based method, linear kernel support vector machines (SVMs) with and without contextual clues, and a k-nearest neighbour approach. Based on these experiments, we select our SVM-based system with contextual clues as our final system and present results for the Nepali-English and Spanish-English datasets.

M3 - Conference contribution

SP - 127

EP - 132

BT - First Workshop on Computational Approaches to Code Switching

PB - Association for Computational Linguistics (ACL)

Y2 - 25 October 2014 through 29 October 2014

ER -

DCU-UVT. Word-Level Language Classification with Code-Mixed Data

Abstract

Conference

Access to Document

Fingerprint

Cite this