Chained System: A Linear Combination of Different Types of Statistical Machine Translation Systems
نویسندگان
چکیده
The paper explores a way to learn post-editing fixes of raw MT outputs automatically by combining two different types of statistical machine translation (SMT) systems in a linear fashion. Our proposed system (which we call a chained system) consists of two SMT systems: (i) a syntax-based SMT system and (ii) a phrase-based SMT system (Koehn, 2004). We first translate source sentences of the bitext training data into a target language, using the syntax-based SMT. This provides us the monolingual parallel data that consist of the raw MT outputs and their corresponding human translations. We then build a phrasebased SMT system, using the monolingual parallel corpus. Our system is thus a chain of a syntax-based SMT system and a phrase-based SMT system. The benefit of the chained system is to learn post-editing fixes automatically via a phrase-based SMT system (Simard, et al., 2007a/b). We investigated the impact from the chained system on the initial SMT system in terms of BLEU, using typologically different language pairs. The results of our experiments strongly indicate that the second part of the chained system can compensate the weaknesses of the initial SMT system in a robust way by providing human-like fixes.
منابع مشابه
Fault diagnosis in a distillation column using a support vector machine based classifier
Fault diagnosis has always been an essential aspect of control system design. This is necessary due to the growing demand for increased performance and safety of industrial systems is discussed. Support vector machine classifier is a new technique based on statistical learning theory and is designed to reduce structural bias. Support vector machine classification in many applications in v...
متن کاملOn the Translation Quality of Google Translate: With a Concentration on Adjectives
Translation, whose first traces date back at least to 3000 BC (Newmark, 1988), has always been considered time-consuming and labor-consuming. In view of this, experts have made numerous efforts to develop some mechanical systems which can reduce part of this time and labor. The advancement of computers in the second half of the twentieth century paved the ground for the invention of machine tra...
متن کاملThe Correlation of Machine Translation Evaluation Metrics with Human Judgement on Persian Language
Machine Translation Evaluation Metrics (MTEMs) are the central core of Machine Translation (MT) engines as they are developed based on frequent evaluation. Although MTEMs are widespread today, their validity and quality for many languages is still under question. The aim of this research study was to examine the validity and assess the quality of MTEMs from Lexical Similarity set on machine tra...
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 کاملDomain Adaptation in Statistical Machine Translation of User-Forum Data using Component-Level Mixture Modelling
This paper reports experiments on adapting components of a Statistical Machine Translation (SMT) system for the task of translating online user-generated forum data from Symantec. Such data is monolingual, and differs from available bitext MT training resources in a number of important respects. For this reason, adaptation techniques are important to achieve optimal results. We investigate the ...
متن کامل