English-to-Korean Web translator : “FromTo/Web-EK”

MT Summit VII Sept. 1999 English-to-Korean Web Translator: "FromTo/Web-EK" Sung-Kwon Choi, Taewan Kim, Sang-Hwa Yuh, Han-Min Jung, Chul-Min Sim, Sang-Kyu Park Knowledge Processing Research Team Electronics and Telecommunications Research Institute Korea Abstract. The previous English-Korean MT system that have been developed in Korea have dealt with only written text as translation object. Most of them enumerated a following list of the problems that had not seemed to be easy to solve in the near future : 1) processing of non-continuous idiomatic expressions 2) reduction of too many POS or structural ambiguities 3) robust processing for long sentence and parsing failure 4) selecting correct word correspondence between several alternatives. The problems can be considered as important factors that have influence on the translation quality of machine translation system. This paper describes not only the solutions of problems of the previous English-to-Korean machine translation systems but also the HTML tags management between two structurally different languages, English and Korean. Through the solutions we translate successfully English web documents into Korean one in the English-to-Korean web translator "FromTo/Web-EK" which has been developed from 1997. 1 Introduction The huge growth of the Internet allows human to get the unrestricted useful information from Internet. But the problem is always the language barrier, and becomes worse between structurally different language group, as we know well. In order to solve the language barrier the machine translation systems from either English or Japanese to Korean or reverse have been developed actively in Korea since 1987. The previous English-to-Korean MT systems that have been developed in Korea have dealt with only written text as translation object. Most of them enumerated a following list of the problems that had not seemed to be easy to solve in the near future in terms of the problems for evolution of the system (Choi et al, 1994): • processing of non-continuous idiomatic expressions • reduction of too many ambiguities of POS or structural ambiguities • robust processing for long sentences and failed or ill-formed sentences • selecting correct word correspondency between several alternatives The problems result in dropping a translation assessment such as fidelity, intelligibility, and style (Hutchins and Somers, 1992). They can be the problems with which previous English-to-Korean MT systems as well as other MT systems also have faced. This paper describes not only the solutions of problems of previous English-to-Korean machine translation systems but also the methods transferring the HTML tags for web-based machine translation on Internet between two structurally different languages such as English and Korean. This paper is written on the basis of the English-to-Korean web translator "FromTo/Web-EK" which has been developed from 1997. 2 System Overview English-to-Korean web translator FromTo/Web-EK has been developed from 1997 to 1998, solving the problems of machine translation systems for written text and expanding its coverage to WWW. FromTo/Web-EK belongs to the rule-based methodology for machine translation and has tree transduction formalism that does English sentence analysis, transforms the result (parse tree) into an intermediate representation, and then transforms it - 432- …

Content truncated to 500 words