Supertag Based Pre-ordering in Machine Translation
نویسندگان
چکیده
This paper presents a novel approach to integrate mildly context sensitive grammar in the context of pre-ordering for machine translation. We discuss the linguistic insights available in this grammar formalism and use it to develop a pre-ordering system. We show that mildly context sensitive grammar proves to be beneficial over context free grammar, which facilitates better reordering rules. For English to Hindi, we see significant improvement of 1.8 BLEU and error reduction of 4.46 TER score over CFG based pre-ordering system, on the WMT14 data set. We also show that our approach improves translation quality for English to Indian languages machine translation over standard phrase based systems.
منابع مشابه
Chinese-to-Japanese Patent Machine Translation based on Syntactic Pre-ordering for WAT 2016
This paper presents our Chinese-to-Japanese patent machine translation system for WAT 2016 (Group ID: ntt) that uses syntactic pre-ordering over Chinese dependency structures. Chinese words are reordered by a learning-to-rank model based on pairwise classification to obtain word order close to Japanese. In this year’s system, two different machine translation methods are compared: traditional p...
متن کاملA Hybrid Machine Translation System Based on a Monotone Decoder
In this paper, a hybrid Machine Translation (MT) system is proposed by combining the result of a rule-based machine translation (RBMT) system with a statistical approach. The RBMT uses a set of linguistic rules for translation, which leads to better translation results in terms of word ordering and syntactic structure. On the other hand, SMT works better in lexical choice. Therefore, in our sys...
متن کاملPre-ordering of phrase-based machine translation input in translation workflow
Word reordering is a difficult task for decoders when the languages involved have a significant difference in syntax. Phrase-based statistical machine translation (PBSMT), preferred in commercial settings due to its maturity, is particularly prone to errors in long range reordering. Source sentence pre-ordering, as a pre-processing step before PBSMT, proved to be an efficient solution that can ...
متن کاملTwo-Stage Pre-ordering for Japanese-to-English Statistical Machine Translation
We propose a new rule-based pre-ordering method for Japanese-to-English statistical machine translation that employs heuristic rules in two-stages. This two-stage framework contributes to experimental results that our method outperforms conventional rule-based methods in BLEU and RIBES.
متن کاملDependency-based Pre-ordering for Chinese-English Machine Translation
In statistical machine translation (SMT), syntax-based pre-ordering of the source language is an effective method for dealing with language pairs where there are great differences in their respective word orders. This paper introduces a novel pre-ordering approach based on dependency parsing for Chinese-English SMT. We present a set of dependency-based preordering rules which improved the BLEU ...
متن کامل