In the last decade the dominant models of machine translation (MT) have been data-driven or corpus-based. This is in sharp contrast to the dominant framework of the 1980s and previous decades, which was ‘rule-based ’ (RBMT). In general, a distinction is made between, on the one hand, statistical machine translation (SMT), based primarily on word frequency and word combinations, and on the other hand, example-based machine translation (EBMT), based on the extraction and combination of phrases (or other short segments of texts). In both cases the corpora comprise bilingual texts (originals and their translations). The origin of EBMT can be dated precisely to a conference paper in 1981 by Makoto Nagao (1984). Research, however, did not begin until the late 1980s at the same time as the first appearance of the translation memory (TM) as a translator’s tool and the first research on SMT. The latter in particular gave rise to much dispute in the early 1990s. EBMT was associated with SMT as both were seen as variants of corpus-based approaches to MT systems, and during the 1990s both became familiar at MT conferences. In recent years, SMT has become the dominant (almost ‘mainstream’) approach in MT (as witnessed by the proceedings of almost any conference in the field of computational linguistics), and EBMT systems are less evident than SMT (but now more prevalent than RBMT).

Corpus driven machine translation approaches such as Phrase-Based Statistical Machine Translation and Example-Based Machine Translation have been successful by using word alignment to find translation fragments for matched source parts in a bilingual training corpus. However, they still cannot properly deal with systematic translation for insertion or deletion words between two distant languages. In this work, we used syntactic chunks as translation units to alleviate this problem, improve alignments and show improvement in BLEU for Korean to English and Chinese to English translation tasks. 1

Abstract—Example based machine translation (EBMT) has emerged as one of the most versatile, computationally simple and accurate approaches for machine translation in comparison to rule based machine translation (RBMT) and statistical based machine translation (SBMT). In this paper, a comparative view of EBMT and RBMT is presented on the basis of some specific features. This paper describes the various research efforts on Example based machine translation and shows the various approaches and problems of EBMT. Salient features of Sanskrit grammar and the comparative view of Sanskrit and English are presented. The basic objective of this paper is to show with illustrative examples the divergence between Sanskrit and English languages which can be considered as representing the divergences between the order free and SVO (Subject-Verb-Object) classes of languages. Another aspect is to illustrate the different types of adaptation mechanism. Index Terms—Example based machine translation, Devnagari, language divergence, matching.

Since sub-sentential alignment is critically important to the translation quality of an Example-Based Machine Translation (EBMT) system, which operates by finding and combining phrase-level matches against the training examples, we developed a new alignment algorithm for the purpose of improving the EBMT system’s performance. This new Symmetric Probabilistic Alignment (SPA) algorithm treats the source and target languages in a symmetric fashion. We describe our basic algorithm and its primary extensions that enable use of surrounding context, and of positional preference information, compare its alignment accuracy with IBM Model 4, and report on experiments in which either IBM Model 4 or SPA alignments are substituted for the aligner currently built into the EBMT system. Both Model 4 and SPA are significantly better than the internal aligner. Then we extend SPA to exploit external alignment information from Moses and to output non-contiguous target phrases. We also alter SPA so that the weights for its feature scores are tuned using minimum error rate training. Our experiments show that exploiting