Automatic identification of parallel documents with light or without linguistic resources (2005)
| Venue: | In Proc. of Canadian AI |
| Citations: | 3 - 1 self |
BibTeX
@INPROCEEDINGS{Patry05automaticidentification,
author = {Re Patry},
title = {Automatic identification of parallel documents with light or without linguistic resources},
booktitle = {In Proc. of Canadian AI},
year = {2005},
pages = {354--365}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
Abstract. Parallel corpora are playing a crucial role in multilingual natural language processing. Unfortunately, the availability of such a resource is the bottleneck in most applications of interest. Mining the web for parallel corpora is a viable solution that comes at a price: it is not always easy to identify parallel documents among the crawled material. In this study we address the problem of automatically identifying the pairs of texts that are translation of each other in a set of documents. We show that it is possible to automatically build particularly efficient content-based methods that make use of very little lexical knowledge. We also evaluate our approach toward a front-end translation task and demonstrate that our parallel text classifier yields better performances than another approach based on a rich lexicon. 1
