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

Abstract

The invention provides a translation rule extraction method and a translation method based on a dependency grammar tree. A translation sequence adjusting relationship is directly expressed in the translation rule that a source end is used as a head word and a dependency grammar tree fragment and a target end consisting of modifiers of the head word are used as strings, and thus the translation rule can be used for definitely guiding the translation process. According to the translation rule extracted by the method, the performance of the translation method based on the dependency grammar tree can be improved. On a data set of 1.54 million of parallel bilingual corpus, the performance of a dependency grammar tree to a string translation model is improved by 1.68 BLEU (Bilingual Evaluation Understudy) points compared with that of a component tree to the string model.

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. ADependency Treelet String Correspondence Model for Statistical Machine Translation. In Proceedings of Second Workshop on Statistical Machine Translation. 2007.) is based on the source ...

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. ADependency Treelet String Correspondence Model for Statistical Machine Translation. In Proceedings of Second Workshop on Statistical Machine Translation. 2007.) is based on the source Arbitrary connected subgraphs in the language-dependent syntactic tree are used as the basic structure of translation rules. This kind of translation rules has no clear linguistic meaning. More importantly, this kind of translation rules cannot express all order relations. Order model to constrain the word order of translated strings to complete the entire translation process

In addition, 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