Non-projective Dependency-based Pre-Reordering with Recurrent Neural Network for Machine Translation
نویسندگان
چکیده
The quality of statistical machine translation performed with phrase based approaches can be increased by permuting the words in the source sentences in an order which resembles that of the target language. We propose a class of recurrent neural models which exploit sourceside dependency syntax features to reorder the words into a target-like order. We evaluate these models on the Germanto-English language pair, showing significant improvements over a phrase-based Moses baseline, obtaining a quality similar or superior to that of hand-coded syntactical reordering rules.
منابع مشابه
A Dependency-Based Neural Reordering Model for Statistical Machine Translation
In machine translation (MT) that involves translating between two languages with significant differences in word order, determining the correct word order of translated words is a major challenge. The dependency parse tree of a source sentence can help to determine the correct word order of the translated words. In this paper, we present a novel reordering approach utilizing a neural network an...
متن کاملLSTM Neural Reordering Feature for Statistical Machine Translation
Artificial neural networks are powerful models, which have been widely applied into many aspects of machine translation, such as language modeling and translation modeling. Though notable improvements have been made in these areas, the reordering problem still remains a challenge in statistical machine translations. In this paper, we present a novel neural reordering model that directly models ...
متن کاملThe RWTH Aachen German-English Machine Translation System for WMT 2015
This paper describes the statistical machine translation system developed at RWTH Aachen University for the German→English translation task of the EMNLP 2015 Tenth Workshop on Statistical Machine Translation (WMT 2015). A phrase-based machine translation system was applied and augmented with hierarchical phrase reordering and word class language models. Further, we ran discriminative maximum ex...
متن کاملNon-Projective Parsing for Statistical Machine Translation
We describe a novel approach for syntaxbased statistical MT, which builds on a variant of tree adjoining grammar (TAG). Inspired by work in discriminative dependency parsing, the key idea in our approach is to allow highly flexible reordering operations during parsing, in combination with a discriminative model that can condition on rich features of the sourcelanguage string. Experiments on tra...
متن کاملKyotoEBMT System Description for the 2nd Workshop on Asian Translation
This paper introduces the KyotoEBMT example-based machine translation framework. Since last year’s workshop we have replaced input trees with forests, improved alignment, added new features, and introduced bilingual neural network reranking. The major benefits of our system include online example retrieval and flexible reordering. We also use syntactic dependency analysis for both source and ta...
متن کامل