Name
Abstract | ||
|---|---|---|
This paper describes the development of French--English and English--French machine translation systems for the 2010 WMT shared task evaluation. These systems were standard phrase-based statistical systems based on the Moses decoder, trained on the provided data only. Most of our efforts were devoted to the choice and extraction of bilingual data used for training. We filtered out some bilingual corpora and pruned the phrase table. We also investigated the impact of adding two types of additional bilingual texts, extracted automatically from the available monolingual data. We first collected bilingual data by performing automatic translations of monolingual texts. The second type of bilingual text was harvested from comparable corpora with Information Retrieval techniques. |
Year | Venue | Keywords |
|---|---|---|
2010 | WMT@ACL | moses decoder,bilingual corpus,bilingual data,available monolingual data,additional bilingual text,lium smt machine translation,french machine translation system,information retrieval technique,monolingual text,automatic translation,bilingual text,machine translation |
Field | DocType | Citations |
Example-based machine translation,Computer science,Machine translation,Phrase,Speech recognition,SMT placement equipment,Artificial intelligence,Natural language processing | Conference | 5 |
PageRank | References | Authors |
0.59 | 14 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Patrik Lambert | 1 | 277 | 23.36 |
| Sadaf Abdul-Rauf | 2 | 52 | 4.79 |
| Holger Schwenk | 3 | 2533 | 228.83 |