M
Munpyo Hong
Researcher at Electronics and Telecommunications Research Institute
Publications - 5
Citations - 16
Munpyo Hong is an academic researcher from Electronics and Telecommunications Research Institute. The author has contributed to research in topics: Verb & Reflexive verb. The author has an hindex of 3, co-authored 5 publications receiving 16 citations.
Papers
More filters
Proceedings ArticleDOI
Semi-automatic construction of Korean-Chinese verb patterns based on translation equivalency
TL;DR: A method to construct Korean-Chinese verb patterns semi-automatically from existing Korean- Chinese verb patterns that are manually written by lexicographers is presented.
Book ChapterDOI
Korean-Chinese Machine Translation Based on Verb Patterns
Kim Chang Hyun,Munpyo Hong,Yinxia Huang,Kim Young Kil,Sung Il Yang,Seo Young Ae,Sung-Kwon Choi +6 more
TL;DR: This paper describes the ongoing project “Korean-Chinese Machine Translation System”, where the main knowledge is verb patterns, and accurate analysis can directly lead to natural and correct generation.
Book ChapterDOI
CL-Guided Korean-English MT System for Scientific Papers
TL;DR: It is shown that this CL-guided MT system can improve the translation accuracy by about 13% by adopting CL rewriting rules, but this improvement is still not enough for various purposes, because most of the users of the MT system may want to submit the translated texts to a conference or an academic journal.
Book ChapterDOI
A korean syntactic parser customized for korean-english patent MT system
Kim Chang Hyun,Munpyo Hong +1 more
TL;DR: This work customized a Korean syntactic parser based on the linguistic characteristics of the patent documents, especially focusing on minimizing the noise in acquiring the co-occurrence data for Korean Syntactic parsing.
Book ChapterDOI
Treating unknown light verb construction in korean-to-english patent MT
TL;DR: This paper addresses the problem of the unknown light verb construction in Korean in the context of Korean-to-English patent machine translation by introducing 4 types of unknown LVCs and presenting a method for generating the target word automatically.