Abstract | ||
---|---|---|
Abstract—The aim of this paper is to describe the first steps of research towards a hybrid MT system that combines the strengths of rule-based syntactic transfer with recently developed syntax- based statistical translation methods within a unified fram ework. The similarities of both paradigms concerning the processing of syntactically parsed input trees serve as a basis for this reseach. We focus on the statistical part of the future system and present a syntax-based statistical machine translation system— BONSAI—for Polish-to-French translation. Although B ONSAI is still under develepmont, it reaches a translation quality on par with that of a modern,phrase-based system. We provide the theoretical background as well as some implementation details and preliminary evaluation results for B ONSAI. At the end of this paper we shortly discuss the benefits of a combined approach. I. I NTRODUCTION A |
Year | DOI | Venue |
---|---|---|
2009 | 10.1109/IMCSIT.2009.5352722 | IMCSIT |
Keywords | Field | DocType |
rule based,history,data mining,language translation,transducers,production,pediatrics | Rule-based machine translation,Language translation,Programming language,Computer science,Machine translation,Phrase,Artificial intelligence,Natural language processing,Transfer-based machine translation,Abstract syntax,Parsing,Syntax | Conference |
Citations | PageRank | References |
2 | 0.41 | 10 |
Authors | ||
1 |
Name | Order | Citations | PageRank |
---|---|---|---|
Marcin Junczys-Dowmunt | 1 | 312 | 24.24 |