Inducing translation templates with type constraints

Çiçekli, İlyas

doi:10.1007/s10590-006-9014-6

Cited by 8 publications

(15 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although learning by substituting similarities or differences with variables yields templates that can be successfully used by the translation component, the templates are usually over generalized [4]. When the algorithm replaces some parts of the examples with variables, the type information of the replaced parts are lost.…”

Section: Type Associated Template Learningmentioning

confidence: 99%

“…Given that the supertype of "+Sg" and "+Pl" is "NounSufCount", the variable that replaces the difference in (6) would be X Noun NounSufCount . The hierarchical structure that represents the subtypesupertype relations between the type labels is modeled as a lattice in our system [4,8]. There are two such lattices, one for English and one for Turkish.…”

Section: Type Associated Template Learningmentioning

confidence: 99%

“…In order to increase the learning effectiveness, we learn from not only example pairs, but also the pairs of the previously learned templates [4].…”

Section: Learning From Previously Learned Templatesmentioning

confidence: 99%

“…Since the template tree specified in the co-occurrence rule matches the subtree 2 (4,5) in the parse tree of the result and the context of the matching subtree is [1 (1) ], the aggregate confidence factor specified in the rule overrides the original confidence factors of the nodes in the matching subtree; and the new confidence value of the translation result becomes…”

Section: Using the Context-dependent Co-occurrence Rulesmentioning

confidence: 99%

“…In this paper, we propose several improvements to an existing EBMT system [3,4,8]. We present here a new method for ranking the translation results generated by this system.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A ranking method for example based machine translation results by learning from user feedback

Daybelge

Çiçekli

2010

Appl Intell

Self Cite

View full text Add to dashboard Cite

Example-Based Machine Translation (EBMT) is a corpus based approach to Machine Translation (MT), that utilizes the translation by analogy concept. In our EBMT system, translation templates are extracted automatically from bilingual aligned corpora by substituting the similarities and differences in pairs of translation examples with variables. In the earlier versions of the discussed system, the translation results were solely ranked using confidence factors of the translation templates. In this study, we introduce an improved ranking mechanism that dynamically learns from user feedback. When a user, such as a professional human translator, submits his evaluation of the generated translation results, the system learns "context-dependent co-occurrence rules" from this feedback. The newly learned rules are later consulted, while ranking the results of the subsequent translations. Through successive translation-evaluation cycles, we expect that the output of the ranking mechanism complies better with user expectations, listing the more preferred results in higher ranks. We also present the evaluation of our ranking method which uses the precision values at top results and the BLEU metric. © 2010 Springer Science+Business Media, LLC

show abstract

Section: Type Associated Template Learningmentioning

confidence: 99%

Section: Type Associated Template Learningmentioning

confidence: 99%

“…In order to increase the learning effectiveness, we learn from not only example pairs, but also the pairs of the previously learned templates [4].…”

Section: Learning From Previously Learned Templatesmentioning

confidence: 99%

Section: Using the Context-dependent Co-occurrence Rulesmentioning

confidence: 99%

“…In this paper, we propose several improvements to an existing EBMT system [3,4,8]. We present here a new method for ranking the translation results generated by this system.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A ranking method for example based machine translation results by learning from user feedback

Daybelge

Çiçekli

2010

Appl Intell

Self Cite

View full text Add to dashboard Cite

show abstract

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

A system-theoretical view of EBMT

Carl¹

2006

Machine Translation

View full text Add to dashboard Cite

According to the system theory of von Bertalanffy (1968), a "system" is an entity that can be distinguished from its environment and that consists of several parts. System theory investigates the role of the parts, their interaction and the relation of the whole with its environment. System theory of the second order examines how an observer relates to the system. This paper traces some of the recent discussion of example-based machine translation (EBMT) and compares a number of EBMT and statistical MT systems. It is found that translation examples are linguistic systems themselves that consist of words, phrases and other constituents. Two properties of Luhmann's (2002) system theory are discussed in this context: EBMT has focussed on the properties of structures suited for translation and the design of their reentry points, and SMT develops connectivity operators which select the most likely continuations of structures. While technically the SMT and EBMT approaches complement each other, the principal distinguishing characteristic results from different sets of values which SMT and EBMT followers prefer.

show abstract

Inducing translation templates with type constraints

Cited by 8 publications

References 12 publications

A ranking method for example based machine translation results by learning from user feedback

A ranking method for example based machine translation results by learning from user feedback

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

A system-theoretical view of EBMT

Contact Info

Product

Resources

About