Panning for EBMT gold, or “Remembering not to forget”

Abstract

A very useful service to the example-based machine translation (EBMT) community was provided by Harold Somers in his summary article which appeared in 1999, and was extended in our 2003 book Recent advances in example-based machine translation. As well as providing a comprehensive review of the paradigm, Somers gives a categorisation of the different instantiations of the basic model. In this paper, we provide a complementary view to that of Somers. Today's EBMT systems learn by analogy. Perhaps even more so than statistical models of translation, one might view these systems as being incapable of forgetting. We researchers and system developers, on the other hand, often forget or are ignorant of techniques and models presented in prior research. The primary aim of this paper is to try to ensure that golden nuggets from past (now quite distantly so) EBMT research papers are gathered together and presented here for a new generation of researchers keen to operate in the paradigm, especially given the spate of recent open-source releases of EBMT systems. We revisit the findings of the previous main research papers, relate them to some of the major research efforts which have taken place since then, and examine especially the prophecies given in the older pieces of work to see the extent to which they have been borne out in the newer research. Given the strong convergence between the leading corpusbased approaches to MT, especially since the introduction of phrase-based statistical MT, a further hope is that these findings may also prove useful to researchers and developers in other areas of MT.123 178 A. Way Decoding · Postprocessing · String-based models · Tree-based models · Hybrid models · Word alignment · Phrase alignment · Subtree alignment · Generalized templates

A Critique of Statistical Machine Translation

“…that EBMT was also seen (as we have noted above) as a significant challenger to RBMT. Interestingly, Way (2009) notes that similar trends in the language used can be seen in EBMT papers at the time:…”

“…To be fair, Lopez (2008) does cite one EBMT paper, but the steps taken to avoid the term 'EBMT' are remarkable. In Way (2009), we observed that There has undoubtedly been a colossal move away from RBMT to more statistical methods, but now the pendulum is swinging back (slowly) in the opposite direction . .…”

Linguistic Annotation

“…For good summaries of example-based MT (EBMT) (cf. Section 3.3), we encourage the reader to consult Somers (1999;2003b) and Way (2009b). The monograph by Carl and Way (2003) provides a representative sample of the myriad array of techniques used in EBMT.…”