A System to Mine Large-Scale Bilingual Dictionaries from Monolingual Web Pages

Guihong Cao


Le 13 juin 2007 à 11 h 30

Salle 3195, Pavillon André-Aisenstadt

I will describe a system that automatically mines English-Chinese translation pairs from large amount of monolingual Chinese web pages. Our approach is motivated by the observation that many Chinese terms (e.g., named entities that are not stored in a conventional dictionary) are accompanied by their English translations in the Chinese web pages. Candidate translations are extracted using pre-defined templates. Transliterations and translation pairs are then identified using statistical learning methods. We compare several approaches for aligning transliterations and mining translations on more than 300GB of Chinese web pages.

Pour recevoir les annonces hebdomadaires par courriel, envoyez un message à l'adresse majordomo@iro.umontreal.ca

Liste des autres séminaires