Abstract | ||
---|---|---|
We propose a novel, language-independent approach for improving machine translation from a resource-poor language to X by adapting a large bi-text for a related resource-rich language and X (the same target language). We assume a small bi-text for the resource-poor language to X pair, which we use to learn word-level and phrase-level paraphrases and cross-lingual morphological variants between the resource-rich and the resource-poor language; we then adapt the former to get closer to the latter. Our experiments for Indonesian/Malay--English translation show that using the large adapted resource-rich bi-text yields 6.7 BLEU points of improvement over the unadapted one and 2.6 BLEU points over the original small bi-text. Moreover, combining the small bi-text with the adapted bi-text outperforms the corresponding combinations with the unadapted bi-text by 1.5--3 BLEU points. We also demonstrate applicability to other languages and domains. |
Year | Venue | Keywords |
---|---|---|
2012 | EMNLP-CoNLL | resource-poor language,unadapted bi-text,resource-rich bi-text yield,target language,bleu point,resource-poor machine translation,large bi-text,source language adaptation,related resource-rich language,x pair,small bi-text,original small bi-text |
Field | DocType | Volume |
BLEU,Malay,Computer science,Evaluation of machine translation,Machine translation,Natural language processing,Artificial intelligence,Indonesian | Conference | D12-1 |
Citations | PageRank | References |
8 | 0.48 | 16 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Pidong Wang | 1 | 16 | 1.99 |
Preslav I. Nakov | 2 | 1771 | 138.66 |
Hwee Tou Ng | 3 | 4092 | 300.40 |