Publications
Publication details [#7328]
Carl, Michael, Ecaterina Rascu, Johann Haller and Philippe Langlais. 2004. Abducing term variant translations in aligned texts. In Daille, Béatrice, Kyo Kageura, Hiroshi Nakagawa and Lee-Feng Chien, eds. Recent trends in computational terminology. Special issue of Terminology. International Journal of Theoretical and Applied Issues in Specialized Communication 10 (1): 103–133. ![DOI logo](https://benjamins.com/logos/doi-logo.svg)
Publication type
Article in Special issue
Publication language
English
Keywords
Journal DOI
10.1075/term
Abstract
Term variation is an important issue in various applications of natural language processing (NLP) such as machine translation, information retrieval and text indexing. In this paper, the authors describe an ‘Abductive Terminological Database’ (ATDB) aiming to detect translations of terms and their variants in bilingual texts. They describe abduction as the process to infer specific term translation templates from multiple resources which have been induced from a bilingual text. They show that precision and recall of the ATDB increase when using more resources and when the resources interfere in a less restricted way. Finally, the authors discuss a way to feed back evaluation values into the induced resources thus allowing for weighted abduction which further enhances the precision of the tool.
Source : Based on abstract in journal