Translation rule extraction method and translation method based on dependency syntax tree

Abstract

The invention provides a translation rule extraction method and a translation method based on a dependency syntax tree. A translation reordering relationship is directly expressed in a translation rule of which a source end has dependency syntax tree segments consisting of a head and all dependent components and a target end has strings, so the translation rule can definitely guide a translation process. The translation rule which is extracted by the translation rule extraction method can improve the performance of the translation method based on the dependency syntax tree. The invention has the advantage that: on a data set of 1.54-million bilingual parallel corpuses, compared with the performance of a component tree-to-string model, the performance of a dependency syntax tree-to-string translation model is improved by 1.68 Bleu points.

Description

technical field [0001] The invention belongs to the technical field of natural language processing, and in particular relates to a statistical machine translation method based on a dependency syntax tree. Background technique [0002] Dependency grammars are one of the most popular grammars in natural language processing. Compared with the phrase structure grammar, the dependency grammar has both grammatical and semantic information, and has the following characteristics: the dependency structure has the best phrasal cohesion properties; the dependency edge gives the semantic information. Therefore, dependency grammars are very attractive resources in the field of machine translation. But the existing dependency syntax tree to string model (reference 1: Deyi Xiong, Qun Liu, and Shouxun Lin. A Dependency Treelet String Correspondence Model for Statistical Machine Translation. In Proceedings of Second Workshop on Statistical Machine Translation. 2007.) with The source langua...

AI Technical Summary

Problems solved by technology

But the existing dependency syntax tree to string model (reference 1: Deyi Xiong, Qun Liu, and Shouxun Lin. A Dependency Treelet String Correspondence Model for Statistical Machine Translation. In Proceedings of Second Workshop on Statistical Machine Translation. 2007.) with The source language depends on any connected subgraph in the syntactic tree as the basic structure of the translation rules. This kind of translation rules has no clear linguistic meaning. More importantly, this kind of translation rules cannot express all the ordering relationships, so heuristic or An ordering model to constrain the word order of translated strings to complete the entire translation process

Moreover, even if heuristics or ordering models are introduced to constrain the word order of translation results, the performance of existing dependency syntax tree-to-string models still lags behind mainstream component tree-to-string models (Reference 2: Yang Liu, Qun Liu, and Shouxun Lin.2006. Tree-to-String Alignment Template for Statistical Machine Translation. In Proceedings of COLING / ACL 2006, pages 609-616, Sydney, Australia, July.)

Images