ICADL 2007 - LNCS 4822

QRselect: A User-Driven System for Collecting Translation Document Pairs from the Web

Kyo Kageura¹, Takeshi Abekawa¹, and Satoshi Sekine²

¹Graduate School of Education, University of Tokyo, 7–3–1 Hongo, Bunkyo-ku, Tokyo 113–0033, Japan
kyo@p.u-tokyo.ac.jp
abekawa@p.u-tokyo.ac.jp

²Computer Science Department, New York University, 715 Broadway, New York, NY 10003 USA
sekine@cs.nyu.edu

Abstract. In this paper we introduce a system that collects English-Japanese translation document pairs from the Web that are relevant to subject keywords specified by the user. The system, QRselect, is specifically designed to meet the needs of online volunteer translators who, in the process of translation, want to refer to a small and specific set of translation document pairs which are relevant to what they are translating. A system which collects relevant existing translated documents and makes them available for reference in the translation process will therefore greatly help these translators. Against this backdrop, we developed a prototype translated document collection system and evaluated its performance. We also examined the users’ role in improving the system.

LNCS 4822, p. 131 ff.

Full article in PDF | BibTeX