“ New paradigms ” in MT : the state of play now that the dust has settled

Harold L. SOMERS Centre for Computational Linguistics UMIST, PO Box 88, Manchester M60 1QD, England [email protected] 1. Background In 1988, at the Second TMI conference at Carnegie Mellon University, IBM’s Peter Brown shocked the audience by presenting an approach to Machine Translation (MT) which was quite unlike anything that most of the audience had ever seen or even dreamed of before. IBM’s “purely statistical” approach, inspired by successes in speech processing, and characterised by the infamous statement “Every time I fire a linguist, my system’s performance improves” flew in the face of all the received wisdom about how to do MT at that time, eschewing the rationalist linguistic approach in favour of an empirical corpusbased one. There followed something of a flood of “new” approaches to MT, few as overtly statistical as the IBM approach, but all having in common the use of a corpus of translation examples rather than linguistic rules as a significant component. This apparent difference was often seen as a confrontation, especially for example at the 1992 TMI conference in Montreal, which had the explicit theme “Empiricist vs. Rationalist Methods in MT” (Isabelle, 1992), though already by that date most researchers were developing hybrid solutions using both corpus-based and theorybased techniques. The heat has largely evaporated from the debate, so that now the “new” approaches are considered mainstream, in contrast though not in conflict with the older rule-based approaches. In this paper, we will review the achievements of a range of approaches to corpus-based MT which we will consider variants of “example-based MT” (EBMT), although individual authors have used alternative names, perhaps wanting to bring out some key difference that distinguishes their own approach: “analogy-based”, “memorybased”, and “case-based” are all terms that have been used. These approaches all have in common the use of a corpus or database of already translated examples, and involve a process of matching a new input against this database to extract suitable examples which are then recombined in an analogical manner to determine the correct translation. Two variants of the corpus-based approach stand somewhat apart from the scenario suggested here. One, which we will not discuss at all in this paper, is the Connectionist or Neural network approach. So far, only a little work with not very promising results has been done in this area (see Waibel et al., 1991; McLean, 1992; Castaño et al. 1997; Koncar & Guthrie, 1997). The other major “new paradigm” is the purely statistical approach already mentioned, and usually identified with the IBM group’s Candide system (Brown et al. 1990, 1993), though the approach has also been taken up by a number of other researchers. The statistical approach is clearly example-based in that it depends on a bilingual corpus, but the matching and recombination stages that characterise EBMT are implemented in quite a different way in these approaches; more significant is that the important issues for the statistical approach are somewhat different, focusing, as one might expect, on the mathematical aspects of estimation of statistical parameters for the language models. Nevertheless, we will try to include these approaches in our overview.