Handling Structural Divergences and Recovering Dropped Arguments in a Korean/English Machine Translation System

Han, Chung–hye; Lavoie, Benoit; Palmer, Martha; Rambow, Owen; Kittredge, Richard; Korelsky, Tanya; Kim, Nari; Kim, Myung‐Hee

doi:10.1007/3-540-39965-8_5

Cited by 20 publications

(19 citation statements)

References 7 publications

(14 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…al., 1997), and extends recent work reported in (Han et al, 2000) about Korean to English transfer in particular. Whereas Han et al focus on high quality domain-specific translation using handcrafted transfer rules, in this work we instead focus on automating the acquisition of such rules.…”

Section: Introductionsupporting

confidence: 86%

Inducing lexico-structural transfer rules from parsed Bi-texts

Lavoie¹,

White²,

Korelsky³

2001

Proceedings of the Workshop on Data-Driven Methods in Machine Translation -

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Introductionsupporting

confidence: 86%

Inducing lexico-structural transfer rules from parsed Bi-texts

Lavoie¹,

White²,

Korelsky³

2001

Proceedings of the Workshop on Data-Driven Methods in Machine Translation -

Self Cite

View full text Add to dashboard Cite

show abstract

“…DSyntS is abstract enough to avoid all types of lexical and syntactic divergences that result from performing the transfer at the surface-syntactic level (where restricted lexical co-occurrence and language-specific constructions are represented). Therefore, as has already been pointed out for example by Sanromán Vilas et al (1999) and Han et al (2000), DSyntS is well suited to MT. 4 In accordance with the stratificational character of an MTT-model, our transfer schema looks as shown in Fig.…”

Section: The Theoretical Frameworksupporting

confidence: 54%

Syntactic mismatches in machine translation

Mel’čuk

Wanner

2007

Machine Translation

View full text Add to dashboard Cite

This paper addresses one of the central problems arising at the transfer stage in machine translation: syntactic mismatches, that is, mismatches between a source-language sentence structure and its equivalent target-language sentence structure. The level at which we assume the transfer to be carried out is the Deep-Syntactic Structure (DSyntS) as proposed in the Meaning-Text Theory (MTT). DSyntS is abstract enough to avoid all types of divergences that result either from restricted lexical co-occurrence or from surface-syntactic discrepancies between languages. As for the remaining types of syntactic divergences, all of them occur not only interlinguistically, but also intralinguistically; this means that establishing correspondences between semantically equivalent expressions of the source and target languages that diverge with respect to their syntactic structure is nothing else than paraphrasing. This allows us to adapt the powerful intralinguistic paraphrasing mechanism developed in MTT for purposes of interlinguistic transfer.

show abstract

“…The syntax literature dating back to Chomsky (1981), together with a rich computational literature on translation divergences (e.g. (Abeille et al, 1990;Dorr, 1994;Han et al, 2000)), is concerned with characterizing in a systematic way the apparent diversity of mechanisms used by languages to express meanings syntactically. For example, current theories claim that languages employ stable headcomplement orders across construction types.…”

Section: Problems With the Dcamentioning

confidence: 99%