EBMT Seen as Case-Based Reasoning

Collins, Bróna; Somers, Harold

doi:10.1007/978-94-010-0181-6_4

Cited by 9 publications

(4 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition to parallel computing, Sumita and Iida (1991) observed that smarter use of the example-base, in terms of indexing the examples, would improve retrieval speed. Collins and Somers (2003) suggested that "better structured case-memory schemas [are needed] to support smart indexing and case storage" (p. 146), while Nirenburg et al (1993) suggested awarding bonuses for contiguous word matches. Sumita (2003) notes that his parallel approach was improved by following Bown's (2003) clustering approach to automatically generate equivalence classes compared to using hand-coded thesauri.…”

Section: Search/retrievalmentioning

confidence: 98%

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: Search/retrievalmentioning

confidence: 98%

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

Way

2010

Machine Translation

View full text Add to dashboard Cite

show abstract

“…Lepage and Denoual 2005), example-based methods belong to the tradition of analogical models arising in the mid-1980s under various similar names including "case-based reasoning" (CBR) as in Kolodner (1983a,b), "exemplar-based reasoning" as in Porter and Bareiss (1986) or Kibler and Aha (1997), "instance-based reasoning" as in Aha et al (1991), "memorybased reasoning" as in Stanfill and Waltz (1988), or "analogy-based reasoning" as in Hall (1989) or Veloso and Carbonell (1993). One detailed point-by-point elaboration of EBMT as an application of CBR is given by Collins and Somers (2003). Analogical reasoning at translation runtime is also identified by Turcato and Popowich (2003) as the main distinguishing property of EBMT approaches.…”

Section: What Is Ebmt?mentioning

confidence: 99%

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

“…We visualize by shading the fact that, while the first a de (9) corresponds to the first a of (10), on the other hand the first b to the left of the conformity in p in (9) corresponds the second b to the right of the equal sign in (2).…”

Section: A2 Proofs For Reductions A21 General Case Of Multiplication ...mentioning

confidence: 99%

“…In particular domains such as machine translation, this type of analogical reasoning has been used [35,26] and the connection with case-based reasoning is well recognized [9]. Still in natural language processing, analogy-based approaches have been used for the tasks of morphological analysis [41,42] or word generation [17].…”

Section: Introductionmentioning

confidence: 99%

Yves Thériault et les Éditions Jeunesse

Lepage¹

2006

View full text Add to dashboard Cite

Les archives des Éditions Jeunesse, déposées aux Archives nationales du Québec à Sainte-Foy, contiennent une correspondance intéressante entre le romancier Yves Thériault et le directeur des Éditions Jeunesse, Real d'Anjou. Échangées dans les années I960, ces lettres éclairent le fonctionnement de la maison d'édition, mettent en lumière la conception qu'Yves Thériault se faisait de l'écriture pour la jeunesse, font ressortir les caractéristiques de sa personnalité d'écrivain et renseignent sur la genèse de certains personnages (Vol-pek) et de certaines oeuvres, telles Kuanuten, vent d'est et, surtout, L'or de la felouque. Les sources de ce roman, que le romancier qualifiait « d'authentiques », font ici l'objet d'un examen particulier.The archives of Éditions Jeunesse, held by the Archives nationales du Québec in Sainte-Foy, include an interesting correspondence between the novelist Yves Thériault and Real d'Anjou, director of Éditions Jeunesse. The letters, exchanged in the 1960s, shed light on the workings of the publishing house, Yves Thériault's view of writing for young readers, distinctive aspects of his personality as a writer, and the genesis of specific characters (Volpek) and works, including Kuanuten, vent d'est and, especially, L'or de la felouque. Careful attention is given to the sources of this novel, described by the novelist as "authentic"

show abstract

EBMT Seen as Case-Based Reasoning

Cited by 9 publications

References 21 publications

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

Yves Thériault et les Éditions Jeunesse

Contact Info

Product

Resources

About