Abstract | ||
---|---|---|
Most of the world languages are resource-poor for statistical machine translation; still, many of them are actually related to some resource-rich language. Thus, we propose three novel, language-independent approaches to source language adaptation for resource-poor statistical machine translation. Specifically, we build improved statistical machine translation models from a resource-poor language POOR into a target language TGT by adapting and using a large bitext for a related resource-rich language RICH and the same target language TGT. We assume a small POOR-TGT bitext from which we learn word-level and phrase-level paraphrases and cross-lingual morphological variants between the resource-rich and the resource-poor language. Our work is of importance for resource-poor machine translation because it can provide a useful guideline for people building machine translation systems for resource-poor languages. Our experiments for Indonesian/Malay-English translation show that using the large adapted resource-rich bitext yields 7.26 BLEU points of improvement over the unadapted one and 3.09 BLEU points over the original small bitext. Moreover, combining the small POOR-TGT bitext with the adapted bitext outperforms the corresponding combinations with the unadapted bitext by 1.93-3.25 BLEU points. We also demonstrate the applicability of our approaches to other languages and domains. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1162/COLI_a_00248 | Computational Linguistics |
Field | DocType | Volume |
Rule-based machine translation,Example-based machine translation,Evaluation of machine translation,Computer science,Machine translation,Speech recognition,Machine translation software usability,Transfer-based machine translation,Artificial intelligence,Natural language processing | Journal | 42 |
Issue | ISSN | Citations |
2 | 0891-2017 | 0 |
PageRank | References | Authors |
0.34 | 32 | 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 |