EBMT of POS-Tagged Sentences by Recursive Division Via Inductive Learning

Andriamanankasina, Tantely; Araki, Kenji; Tochinai, Koji

doi:10.1007/978-94-010-0181-6_8

Cited by 2 publications

(4 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sato (1993), who notes that "an open problem in example-based translation of noun phrases is article selection" (p. 68). Even a decade or so later, Andriamanankasina et al (2003) state that one possible new avenue of investigation was "a special consideration of high frequency words" (p. 251), while Aramaki and Kurohashi (2004) bemoan the fact that two of the remaining problems for their system were the wrong translation of function words, and a lack of subject pronouns. In contrast, Sumita et al (1993a) affirm that "EBMT can achieve accurate word selection not only for content words but also for function words" (p. 89).…”

Section: Word Alignmentmentioning

confidence: 96%

“…Andriamanankasina et al (2003) state one issue for further research in their system to be the development of "a language-independent method capable of generating all possible results and selecting the correct result from the candidate translations" (p. 251).…”

Section: Filtering/correcting Translationsmentioning

confidence: 99%

“…Instances of 'runtime' EBMT systems includeAndriamanankasina et al (2003),Bond and Shirai (2003),Sumita (2003), and evenLopez (2008), cf. footnote 4.…”

mentioning

confidence: 99%

See 2 more Smart Citations

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

Way

2010

Machine Translation

View full text Add to dashboard Cite

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

show abstract

Section: Word Alignmentmentioning

confidence: 96%

Section: Filtering/correcting Translationsmentioning

confidence: 99%

See 1 more Smart Citation

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

Way

2010

Machine Translation

View full text Add to dashboard Cite

show abstract

“…4, the early EBMT models following Nagao (1984) focused on translation by analogy against a large library of translation examples for lexical collocations as in Sumita and Iida (1991) and updated in Sumita (2003), with fairly ad hoc numerical measures. Modern versions of this "pure" EBMT approach include Andriamanankasina et al (2003), Bond and Shirai (2003), and Lepage and Denoual (2005). Subsequent development pushed in different directions.…”

Section: Mt Model Spacementioning

confidence: 97%

MT model space: statistical versus compositional versus example-based machine translation

2007

Machine Translation

View full text Add to dashboard Cite

We offer a perspective on EBMT from a statistical MT standpoint, by developing a three-dimensional MT model space based on three pairs of definitions:(1) logical versus statistical MT, (2) schema-based versus example-based MT, and (3) lexical versus compositional MT. Within this space we consider the interplay of three key ideas in the evolution of transfer, example-based, and statistical approaches to MT. We depict how all translation models face these issues in one way or another, regardless of the school of thought, and suggest where the real questions for the future may lie.

show abstract

EBMT of POS-Tagged Sentences by Recursive Division Via Inductive Learning

Cited by 2 publications

References 1 publication

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

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

MT model space: statistical versus compositional versus example-based machine translation

Contact Info

Product

Resources

About