This work explores the problem of cross-lingual pairwise similarity, where the task is to extract similar pairs of documents across two different languages. Solutions to this pro...
In order to search corpora written in two or more languages, the simplest and most efficient approach is to translate the query submitted into the required language(s). To achieve...
Following the recent adoption by the machine translation community of automatic evaluation using the BLEU/NIST scoring process, we conduct an in-depth study of a similar idea for ...
Translation of proper names is generally recognized as a significant problem in many multi-lingual text and speech processing applications. Even when large bilingual lexicons use...
Multi-word terms are traditionally identified using statistical techniques or, more recently, using hybrid techniques combining statistics with shallow linguistic information. Al)...