Abstract | ||
---|---|---|
This paper introduces deep syntactic structures to syntax-based Statistical Machine Translation (SMT). We use a Head-driven Phrase Structure Grammar (HPSG) parser to obtain the deep syntactic structures of a sentence, which include not only a fine-grained syntactic property description but also a semantic representation. Considering the abundant information included in the deep syntactic structures, it is interesting to investigate whether or not they improve the traditional syntax-based translation models based on PCFG parsers. In order to use deep syntactic structures for SMT, this paper focuses on extracting tree-to-string translation rules from aligned HPSG tree---string pairs. The major challenge is to properly localize the non-local relations among nodes in an HPSG tree. To localize the semantic dependencies among words and phrases, which can be inherently non-local, a minimum covering tree is defined by taking a predicate word and its lexical/phrasal arguments as the frontier nodes. Starting from this definition, a linear-time algorithm is proposed to extract translation rules through one-time traversal of the leaf nodes in an HPSG tree. Extensive experiments on a tree-to-string translation system testified the effectiveness of our proposal. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1007/s10590-010-9081-6 | Machine Translation |
Keywords | Field | DocType |
tree-to-string translation rule,translation rule,traditional syntax-based translation model,fine-grained syntactic property description,semantic representation,tree-to-string translation system,non-local relation,typed feature structures · predicate-argument structures · head-driven phrase structure grammar · syntax-based translation,deep syntactic structure,semantic dependency,hpsg tree | Rule-based machine translation,Head-driven phrase structure grammar,Tree traversal,Syntactic predicate,Computer science,Machine translation,Abstract syntax tree,Natural language processing,Artificial intelligence,Parsing,Linguistics,Syntax | Journal |
Volume | Issue | ISSN |
24 | 2 | 1573-0573 |
Citations | PageRank | References |
0 | 0.34 | 28 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xianchao Wu | 1 | 64 | 6.62 |
Takuya Matsuzaki | 2 | 740 | 42.47 |
Jun'ichi Tsujii | 3 | 3610 | 232.96 |