Improved Named Entity Recognition using Machine Translation-based Cross-lingual Information
Document title: Improved Named Entity Recognition using Machine Translation-based Cross-lingual Information
Journal: Computación y sistemas
Database: PERIÓDICA
System number: 000411077
ISSN: 1405-5546
Authors: 1
2
Institutions: 1Microsoft India, Hyderabad, Andhra Pradesh. India
2Dublin City University, ADAPT Centre, Dublín. Irlanda
Year:
Season: Jul-Sep
Volumen: 20
Number: 3
Pages: 495-504
Country: México
Language: Inglés
Document type: Artículo
Approach: Experimental, aplicado
English abstract In this paper, we describe a technique to improve named entity recognition in a resource-poor language (Hindi) by using cross-lingual information. We use an on-line machine translation system and a separate word alignment phase to find the projection of each Hindi word into the translated English sentence. We estimate the cross-lingual features using an English named entity recognizer and the alignment information. We use these cross-lingual features in a support vector machine-based classifier. The use of cross-lingual features improves F i score by 2.1 points absolute (2.9% relative) over a good-performing baseline model
Disciplines: Ciencias de la computación,
Literatura y lingüística
Keyword: Procesamiento de datos,
Lingüística aplicada,
Lingüística computacional,
Traducción automática,
Reconocimiento de entidades nombradas
Keyword: Computer science,
Literature and linguistics,
Data processing,
Applied linguistics,
Computing linguistics,
Machine translation,
Named entity recognition
Full text: Texto completo (Ver HTML)