Abstract. In the last ten years there has been a significant amount of research in Machine Translation within a “new ” paradigm of empirical approaches, often labelled collectively as “Example-based” approaches. The first manifestation of this approach caused some surprise and hostility among observers more used to different ways of working, but the techniques were quickly adopted and adapted by many researchers, often creating hybrid systems. This paper reviews the various research efforts within this paradigm reported to date, and attempts a categorisation of different manifestations of the general approach.

Previous work on marker-based EBMT [Gough & Way, 2003, Way & Gough, 2004] suffered from problems such as data-sparseness and disparity between the training and test data. We have developed a largescale robust EBMT system. In a comparison with the systems listed in [Somers, 2003], ours is the third largest EBMT system and certainly the largest English-French EBMT system. Previous work used the on-line MT system Logomedia to translate source language material as a means of populating the system’s database where bitexts were unavailable. We derive our sententially aligned strings from a Sun Translation Memory (TM) and limit the integration of Logomedia to the derivation of our word-level lexicon. We also use Logomedia to provide a baseline comparison for our system and observe that we outperform Logomedia and previous marker-based EBMT systems in a number of tests. 1

This paper is a survey of the current machine translation research in the US, Europe and Japan. A short history of machine translation is presented first, followed by an overview of the current research work. Representative examples of a wide range of different approaches adopted by machine translation researchers are presented. These are described in detail along with a discussion of the practicalities of scaling up these approaches for operational environments. In support of this discussion, issues in, and techniques for, evaluating machine translation systems are addressed.

This paper describes the interaction of two CBMT approaches, an example-based machine translation (EBMT) system and a tagged Translation Memory system, with two concrete RBMT systems. It is hoped that the linkage of different MT approaches will essentially improve the quality of machine translation, ensure a better performance, and make it easier to tune to varying needs. The objective of this activity is to investigate the consequences of this linkage and to determine exactly what kind of linguistic entities to be translated (syntactic constructions, lexicographic types, collocations etc. . . ) can be dynamically exchanged between the different components without producing additional translation errors. Extensive research in this area will contribute to a better understanding of translation as a human activity and help to optimize the general paradigm of machine translation

This paper looks at EBMT from the perspective of the Case-based Reasoning (CBR) paradigm. We attempt to describe the task of machine translation (MT) seen as a potential application of CBR, and attempt to describe MT in standard CBR terms. The aim is to see if other applications of CBR can suggest better ways to approach EBMT.

Abstract not found

which had been established in the late 1970s. These were the systems which had built upon experi-ence gained in what may be called the 'quiet ' decade of machine translation, the ten years after the publication of the ALPAC report in 1966 had brought to an end MT research in the United States and had profoundly affected its support elsewhere. Throughout the 1980s, it can be asserted without contradiction, the dominant framework of MT research was the essentially syntax-oriented 'transfer ' approach exemplified by such systems as ARIANE at Grenoble University, METAL at Texas, SUSY at Saarbrücken, the Mu system at Kyoto University, and of course the multilingual Eurotra project of the European Communities. In addition, many of the commercial systems which appeared at this time were based on the same principles. For some time it appeared as if the 'interlingua ' approach was not viable. Earlier efforts in the 1970s had been unsuccessful at Grenoble- the CETA system- and at the University of Texas. These were, however, essentially syntax-oriented approaches: while structural transfer was via interlingual ('universal') tree representations, lexical transfer was still via bilingual dictionary substitution. Dur-ing the 1980s, new approaches to the interlingua model appeared. Some remained essentially lin-

This paper describes a prototype of an example-based machine translation system. In this system, key language resources are EDR corpus and concept classification dictionary. The corpus consists of a pair of sentences, their morphological representations, their syntactic representations, and their semantic representations. The semantic representations are described by an interlingua. Therefore the corpus can be viewed either as a mono-lingual corpus or as a parallel corpus between a natural language and an interlingua. The system analyses source sentences and generates target sentences by example databases. Similarity calculations play essential roles in analysis and generation phases. These calculations uses the concept classification dictionary. The translation system is realized by directly combining a source language analysis and a target language generation without a transfer phase. The system has been implemented and the state of the current prototype showed evaluation data which suggested the corpus-based MT approach would be good prospects. 1.

An approach to Example-Based Machine Translation is presented which operates by extracting translation patterns from a bilingual corpus aligned at the level of the sentence. This is carried out using a language-neutral recursive machine-learning algorithm based on the principle of similar distributions of strings. The translation patterns extracted represent generalisations of sentences that are translations of each other and, to some extent, resemble transfer rules but with fewer constraints. The strings and variables, of which translations patterns are composed, are aligned in order to provide a more refined bilingual knowledge source, necessary for the recombination phase. A non-structural approach based on surface forms is error prone and liable to produce translation patterns that are false translations. Such errors are highlighted and solutions are proposed by the addition of external linguistic resources, namely morphological analysis and part-of-speech tagging. The amount of linguistic resources added has consequences for computational complexity and portability.

Abstract This chapter has two main aims: (i) to present the state-of-the-art in Machine Translation (MT), namely Phrase-Based Statistical MT, together with the major competing paradigms used in MT research and development today; and (ii) to provide an overview of the MT research carried out by my team here at DCU, characterised here in terms of ‘hybrid MT’. In addition, we provide our views on the directions that MT research might take in the near future, and conclude the chapter with lists of further reading for the interested reader.