Reordering by Parsing
نویسندگان
چکیده
We present a new discriminative reordering model for statistical machine translation. The model employs a standard data-driven dependency parser to predict reorderings based on syntactic information. This is made possible through the introduction of a reordering structure, which is a word alignment structure where the target word order is transposed onto the source sentence as a path. The approach is integrated in a phrase-based system. Experiments show a large increase in long distance reorderings. Both automatic and human evaluations show substantial increases in translation quality on an English to German task.
منابع مشابه
Effects of Parsing Errors on Pre-Reordering Performance for Chinese-to-Japanese SMT
Linguistically motivated reordering methods have been developed to improve word alignment especially for Statistical Machine Translation (SMT) on long distance language pairs. However, since they highly rely on the parsing accuracy, it is useful to explore the relationship between parsing and reordering. For Chinese-toJapanese SMT, we carry out a three-stage incremental comparative analysis to ...
متن کاملAnalyzing the Influence of Parsing Errors on Pre-reordering Performance for SMT
Word alignment for long distance language pairs is problematic in state-of-the-art phrasebased statistical machine translation. Linguistically motivated reordering models have been widely studied to conquer this challenge. One of the most popular and effective methods is called pre-reordering, where words in sentences from the source language are re-arranged with the objective to resemble the w...
متن کاملReordering Models for Statistical Machine Translation: A Literature Survey
In this survey, we briefly study various reordering models that are used with statistical translation models. Reordering model is one of the important component of any statistical machine translation system. Problem of reordering is NP-Hard itself. In this survey, we study various reordering approaches that can be used to solve this problem. We first study simple distortion-based reordering whi...
متن کاملJapanese Word Reordering Integrated with Dependency Parsing
Although Japanese has relatively free word order, Japanese word order is not completely arbitrary and has some sort of preference. Since such preference is incompletely understood, even native Japanese writers often write Japanese sentences which are grammatically well-formed but not easy to read. This paper proposes a method for reordering words in a Japanese sentence so that the sentence beco...
متن کاملJapanese Word Reordering Executed Concurrently with Dependency Parsing and Its Evaluation
This paper proposes a method for reordering words in a Japanese sentence based on concurrent execution with dependency parsing so that the sentence becomes more readable. Our contributions are summarized as follows: (1) we extend a probablistic model used in the previous work which concurrently performs word reordering and dependency parsing; (2) we conducted an evaluation experiment using our ...
متن کاملSoft Dependency Constraints for Reordering in Hierarchical Phrase-Based Translation
Long-distance reordering remains one of the biggest challenges facing machine translation. We derive soft constraints from the source dependency parsing to directly address the reordering problem for the hierarchical phrasebased model. Our approach significantly improves Chinese–English machine translation on a large-scale task by 0.84 BLEU points on average. Moreover, when we switch the tuning...
متن کامل