Abducing term variant translations in aligned texts

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, we describe an ‘Abductive Terminological Database’ (ATDB) aiming to detect translations of terms and their variants in bilingual texts. We describe abduction as the process to infer specific term translation templates from multiple resources which have been induced from a bilingual text. We show that precision and recall of the ATDB increase when using more resources and when the resources interfere in a less restricted way. We 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.

Controlled Document Authoring in a Machine Translation Age

“…• The typology of Japanese and English term variations can be used as a point of reference for future investigation of term variations. Whereas there are several established monolingual typologies of variants, such as Jacquemin (2001) for English, Daille (2003) for French and Yoshikane et al (2003) for Japanese, and a few bilingual typologies, Carl et al (2004) for English and French, no typology has been proposed that deals with Japanese and English.…”

“…Moreover, from a contrastive viewpoint, fewer studies investigated term variations bilingually (Daille et al, 1994;Carl et al, 2004). Carl et al (2004) examined English-French bilingual parallel texts and created generalised variation patterns based on Daille (1996) and Jacquemin (2001).…”

“…Moreover, from a contrastive viewpoint, fewer studies investigated term variations bilingually (Daille et al, 1994;Carl et al, 2004). Carl et al (2004) examined English-French bilingual parallel texts and created generalised variation patterns based on Daille (1996) and Jacquemin (2001). The intended application of these patterns is in the area of controlled terminology, and they are as follows (provided with English examples): The typologies above supply the point of departure for our study, i.e.…”

Terminologija v Evropski uniji

“…V korpusu angleško-francoskih besedil, ki so ga za prepoznavanje prevodov terminov in njihovih variaciji oblikovali M. Carl, E. Rascu, J. Haller in P. Langlais (2004), so avtorji potrdili naslednje tipe terminoloških variacij: elipso (supervised safety precautions > safety precautions); vrivanje ene ali več sestavin v variacijo glede na osnovni termin (prone position > prone supported position); permutacijo (c3a1 sniper rifle > sniper rifle c3a1); združevanje (visual ability, visual acuity > visual ability and acuity); sopomenskost (spotting telescope > spotting scope) in tipografske variacije (hand stop > handstop).…”