Abstract | ||
---|---|---|
Statistical phrase-based machine translation models crucially rely on word alignments. The search for word-alignments assumes a model of word locality between source and target languages that is violated in starkly different word-order languages such as English-Hindi. In this article, we present models that decouple the steps of lexical selection and lexical reordering with the aim of minimizing the role of word-alignment in machine translation. Indian languages are morphologically rich and have relatively free-word order where the grammatical role of content words is largely determined by their case markers and not just by their positions in the sentence. Hence, lexical selection plays a far greater role than lexical reordering. For lexical selection, we investigate models that take the entire source sentence into account and evaluate their performance for English-Hindi translation in a tourism domain. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1145/1526252.1526256 | ACM Trans. Asian Lang. Inf. Process. |
Keywords | Field | DocType |
grammatical role,global lexical selection,statistical phrase-based machine translation,greater role,discriminative machine translation,english-hindi translation,lexical reordering,content word,entire source sentence,lexical selection,machine translation,word alignment,word order | Rule-based machine translation,Lexical choice,Example-based machine translation,Computer science,Lexical item,Machine translation,Speech recognition,Transfer-based machine translation,Artificial intelligence,Natural language processing,Lexical chain,Lexical density | Journal |
Volume | Issue | Citations |
8 | 2 | 3 |
PageRank | References | Authors |
0.42 | 17 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Sriram Venkatapathy | 1 | 68 | 9.39 |
Srinivas Bangalore | 2 | 1319 | 157.37 |