Abstract | ||
---|---|---|
This paper describes our submissions for the WMT-12 translation task using Kriya - our hierarchical phrase-based system. We submitted systems in French-English and English-Czech language pairs. In addition to the baseline system following the standard MT pipeline, we tried ensemble decoding for French-English. The ensemble decoding method improved the BLEU score by 0.4 points over the baseline in newstest-2011. For English-Czech, we segmented the Czech side of the corpora and trained two different segmented models in addition to our baseline system. |
Year | Venue | Keywords |
---|---|---|
2012 | WMT@NAACL-HLT | wmt-12 translation task,czech side,baseline system,standard mt pipeline,hierarchical phrase-based system,english-czech language pair,different segmented model,sfu system,bleu score |
Field | DocType | Citations |
BLEU,Czech,Computer science,Phrase,Speech recognition,Artificial intelligence,Natural language processing,Baseline system,Decoding methods | Conference | 3 |
PageRank | References | Authors |
0.46 | 8 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Majid Razmara | 1 | 94 | 8.49 |
Baskaran Sankaran | 2 | 155 | 13.65 |
Ann Clifton | 3 | 45 | 5.86 |
Anoop Sarkar | 4 | 1017 | 88.82 |