Ambiguity And Disambiguation In Korean-to-Chinese Machine Translation

Ambiguity is a common phenomenon in many languages,and it is also a difficulty in the field of Natural Language Processing.This paper examines the ambiguity phenomenon and disambiguation in Korean and Chinese machine translation,based on the models in contrastive linguistics,then attempts to find methods to improve the application of Machine translation and Natural Language Processing in the two languages.The first chapter introduces the rationale of the paper,objectives,research methodology,previous work done in the field and the significance of the study.The second chapter illustrates the important concepts in this study.The third chapter compares ambiguity in Korean and Chinese,and divides ambiguity into three types,namely lexical ambiguity,lexical grammatical ambiguity and grammatical ambiguity.Lexical ambiguity includes ambiguity caused by homophones,ambiguity caused by polyphones,ambiguity caused by polysemous words,and ambiguity caused by idioms.Lexical grammatical ambiguity includes ambiguity caused by different parts of speech and ambiguity caused by predicates.Grammatical ambiguity includes ambiguity caused by vague modifiers,ambiguity caused by the juxtaposition of components,ambiguity caused by word spacing,ambiguity caused by comparative structures and ambiguity caused by scope.In addition,a contrastive study of each type of ambiguity in Korean and Chinese is made,and their similarities and differences are expounded.The fourth chapter discusses the ambiguities that arise from human factors in Machine Translation and the ways to disambiguate them.The fifth chapter is the conclusion,which summarizes the whole article.