Resumo

DANDAPAT, Sandipan  e  WAY, Andy. Improved Named Entity Recognition using Machine Translation-based Cross-lingual Information. Comp. y Sist. [online]. 2016, vol.20, n.3, pp.495-504. ISSN 2007-9737.  https://doi.org/10.13053/cys-20-3-2468.

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.

Palavras-chave : Named entity recognition; machine translation; cross-lingual information.

        · texto em Inglês     · Inglês ( pdf )