Natural Language Generation in an MT System Based on a Multi-Level Processing Strategy

Li, Huifeng; Kang, Sin-Jae; Lee, Jong-Hyeok

doi:10.1142/s021942790100028x

Cited by 2 publications

(6 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among previous research on Chinese to Korean machine translation is Mtran-CK [1], a structural interlingua based MT, where an interlingual representation (IR) is generated by the Chinese analysis section, then the IR is transformed to a Korean semantic tree. Since Mtran-CK is an interlingua based approach, it is not suitable for the large-scale application domain, as noted in the previous section.…”

Section: Problem Discussion and Related Workmentioning

confidence: 99%

“…Similarities in word order. 1 To show an additional similarity, some adverbs precede a verb in Chinese and most adverbs appear in front of a verb in Korean. Surprisingly, we found that between Korean and Chinese a variety of similarities exist in a word order topology.…”

Section: Word Order Typologymentioning

confidence: 99%

“…The first subject in a double-subject sentence is more appropriately analyzed as a topic with the concept of topic [3]. Example (1) shows that the first subject (elephant) is more appropriately analyzed as a topic in a Chinese double sentence. The topic relation is equivalently transferred to its Korean topic relation in example (2).…”

Section: Grammatical Relationmentioning

confidence: 99%

“…The Knowledge and Language Engineering Laboratory (KLE) at the Pohang University of Science and Technology (POSTECH) previously developed the Chinese-to-Korean MT system (Mtran-CK), an interlingua based system [1]. Based on our work in Mtran-CK, in order to target the large-scale practical domain, we propose a new model, a prototype transfer based machine translator, called TOTAL-CK (Translator Of Three Asian Languages -Chinese to Korean).…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Resolving Structural Transfer Ambiguity in Chinese-to-Korean Machine Translation

Kim¹,

Zheng²,

Li³

et al. 2003

Int. J. Comp. Proc. Lang.

Self Cite

View full text Add to dashboard Cite

We propose a new prototype Chinese-to-Korean machine translation system called TOTAL-CK, a prototype transfer based MT system designed for the large-scale practical domain. TOTAL-CK consists of the components of analysis, transfer, and generation. In this paper, we mainly discuss the transfer issues resulting from stylistic structural differences between Chinese and Korean. The dependency grammar formalism is employed for Chinese parsed trees and their equivalent Korean parsed trees. We deal with structural transfer ambiguities that arise when a given source language syntactic pattern is potentially translated by a number of different target language syntactic patterns. Also, structural transfer ambiguities are the major complex transfer problem appearing during dependency transferring, in an SVO pattern that most frequently occurs in Chinese sentences. There are three types of structural transfer ambiguity: transitive transfer, subject-governing transfer and verbgoverning transfer. They are discovered by analyzing the ambiguity and the related formalism. Finally, we present a thesaurus-based disambiguation approach for dependency structural transfer, which is adopted in TOTAL-CK. Our approach achieves 94.6% in precision for SVO sentences and 93.5% for overall sentences.

show abstract

Section: Problem Discussion and Related Workmentioning

confidence: 99%

Section: Word Order Typologymentioning

confidence: 99%

Section: Grammatical Relationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Resolving Structural Transfer Ambiguity in Chinese-to-Korean Machine Translation

Kim¹,

Zheng²,

Li³

et al. 2003

Int. J. Comp. Proc. Lang.

Self Cite

View full text Add to dashboard Cite

show abstract

“…We modified the KSG (Korean Sentence Generation) of Mtran C/K [10] to generate a surface sentence from FSR. Mtran C/K generates a Korean sentence from IR (interlingual representations) in an interlingua-based Chinese-to-Korean machine translation system.…”

Section: Surface Realizationmentioning

confidence: 99%

XExplainer: a tool for generating descriptive text from database

Roh

Kang

Lee

Proceedings 22nd International Conference on Distributed Computing Systems Workshops

View full text Add to dashboard Cite

We focus on how to generate well-written texts to describe an object from a database, and propose several strategies that are needed in generation stages. To build reliable generation rules, we performed corpus analysis through annotating descriptive texts. This paper also describes an implemented text generation system called XExplainer, which can dynamically produce a description of an object in Korean. XExplainer was applied to two domains -a home shopping database and a business administration database -to show that it can be applied to any domain as long as the information is provided in the required format. The Generated texts were evaluated by humans using several criteria, such as content completeness, structural coherence, expression conciseness, and text layout.

show abstract

Natural Language Generation in an MT System Based on a Multi-Level Processing Strategy

Cited by 2 publications

References 2 publications

Resolving Structural Transfer Ambiguity in Chinese-to-Korean Machine Translation

Resolving Structural Transfer Ambiguity in Chinese-to-Korean Machine Translation

XExplainer: a tool for generating descriptive text from database

Contact Info

Product

Resources

About