Title | ||
---|---|---|
Dependency treelet translation: the convergence of statistical and example-based machine-translation? |
Abstract | ||
---|---|---|
We describe a novel approach to MT that combines the strengths of the two leading corpus-based approaches: Phrasal SMT and EBMT. We use a syntactically informed decoder and reordering model based on the source dependency tree, in combination with conventional SMT models to incorporate the power of phrasal SMT with the linguistic generality available in a parser. We show that this approach significantly outperforms a leading string-based Phrasal SMT decoder and an EBMT system. We present results from two radically different language pairs, and investigate the sensitivity of this approach to parse quality by using two distinct parsers and oracle experiments. We also validate our automated bleu scores with a small human evaluation. |
Year | DOI | Venue |
---|---|---|
2006 | 10.1007/s10590-006-9008-4 | Machine Translation |
Keywords | Field | DocType |
example-based machine-translation,ebmt system,dependency treelet translation,novel approach,automated bleu score,example-based machine translation · ebmt · statistical machine translation · smt · syntax · dependency analysis,different language pair,leading string-based phrasal smt,leading corpus-based approach,syntactically informed decoder,phrasal smt,conventional smt model,distinct parsers,machine translation,dependency analysis,dependence analysis,example based machine translation,syntax | Example-based machine translation,Computer science,Machine translation,Computational linguistics,Oracle,Machine translation software usability,Artificial intelligence,Natural language processing,Transfer-based machine translation,Parsing,Linguistics,Syntax | Journal |
Volume | Issue | ISSN |
20 | 1 | 1573-0573 |
Citations | PageRank | References |
22 | 0.78 | 28 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Chris Quirk | 1 | 1362 | 77.61 |
Arul Menezes | 2 | 470 | 29.57 |