A Rule-Driven Dynamic Programming Decoder for Statistical MT
نویسنده
چکیده
The paper presents an extension of a dynamic programming (DP) decoder for phrase-based SMT (Koehn, 2004; Och and Ney, 2004) that tightly integrates POS-based re-order rules (Crego and Marino, 2006) into a left-to-right beam-search algorithm, rather than handling them in a pre-processing or re-order graph generation step. The novel decoding algorithm can handle tens of thousands of rules efficiently. An improvement over a standard phrase-based decoder is shown on an ArabicEnglish translation task with respect to translation accuracy and speed for large re-order window sizes.
منابع مشابه
A 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 کاملIntegrating a Rule-based with a Hierarchical Translation System
Recent developments on hybrid systems that combine rule-based machine translation (RBMT) systems with statistical machine translation (SMT) generally neglect the fact that RBMT systems tend to produce more syntactically well-formed translations than data-driven systems. This paper proposes a method that alleviates this issue by preserving more useful structures produced by RBMT systems and util...
متن کاملLearning Transfer Rules for Machine Translation with Limited Data
The transfer-based approach to machine translation (MT) captures structural transfers between the source language and the target language, with the goal of producing grammatical translations. The major drawback of the approach is the development bottleneck, requiring many human-years of rule development. On the other hand, data-driven approaches such as example-based and statistical MT achieve ...
متن کاملHybrid Architectures for Multi-Engine Machine Translation
We describe different architectures that combine rule-based and statistical machine translation (RBMT and SMT) engines into hybrid systems. One of them allows to combine many existing MT engines in a multi-engine setup, which can be done under the control of a decoder for SMT. Another architecture uses lexical entries induced via SMT technology to be included in a rule-based system. For all the...
متن کاملMT goes farming
In the paper we present detailed analyses of two machine translation systems when applied to documents of a previously unseen domain: agricultural texts from the European Union. The two systems compared are a statistical machine translation (SMT) system using the freely available ISI ReWrite Decoder (Germann, 2003a), and the rule-based machine translation system MATS (Sågvall Hein et al., 2002)...
متن کامل