Article ID Journal Published Year Pages File Type
1123296 Procedia - Social and Behavioral Sciences 2011 11 Pages PDF
Abstract

In the task of acquiring technical term translation equivalent pairs, we consider situations where a technical term is observed in many parallel patent sentences and is translated into many translation equivalents. This paper especially studies the issue of identifying synonymous translation equivalent pairs of technical terms. First, we collect candidates of synonymous translation equivalent pairs from parallel patent sentences. Then, we analyze features for identifying synonymous translation equivalent pairs. Finally, we apply the Support Vector Machines (SVMs) to the task of identifying bilingual synonymous technical terms, and achieve the performance of almost 98% precision and over 40% F-measure.

Related Topics
Social Sciences and Humanities Arts and Humanities Arts and Humanities (General)