Un syst\`eme modulaire d'acquisition automatique de traductions \`a partir du Web

TL;DR

This paper introduces a modular web-based method for automatically translating complex lexical units between French and English, leveraging linguistic properties and web data to improve bilingual lexicon extraction.

Contribution

It presents a novel modular system that uses linguistic features and web validation to enhance automatic translation of complex lexical units.

Findings

High precision in translation extraction demonstrated

Effective use of web data for validation and term collection

Modular approach handles various linguistic properties

Abstract

We present a method of automatic translation (French/English) of Complex Lexical Units (CLU) for aiming at extracting a bilingual lexicon. Our modular system is based on linguistic properties (compositionality, polysemy, etc.). Different aspects of the multilingual Web are used to validate candidate translations and collect new terms. We first build a French corpus of Web pages to collect CLU. Three adapted processing stages are applied for each linguistic property : compositional and non polysemous translations, compositional polysemous translations and non compositional translations. Our evaluation on a sample of CLU shows that our technique based on the Web can reach a very high precision.