KIELIKONE Machine Translation Workstation

[MT Summit III, Washington, DC, USA, July 1991] KIELIKONE Machine Translation Workstation H. Jäppinen, L. Kulikov, A. Ylä-Rotiala SITRA Foundation, KIELIKONE-project P.O. Box 329, 00121 Helsinki, Finland Abstract All human languages are open and complex communication systems. No machine transla- tion system will ever be able to automatically translate all possible sentences from one lan- guage to another in high quality. One way to combat complexity and openness of language translation is to decompose the task into well- defined sequential subtasks and solve each us- ing declarative, modular rules. This paper describes such an MT system. A language- independent MT Machine has been designed for the transformation of linguistic trees in a gen- eral fashion. A full MT system is composed of a sequence of instances of that machine. Finnish- English implementation is discussed. 1 Introduction The great majority of Finns speak a language which differs radically from main Indo-European languages. Finnish is highly inflectional and words have potenti- ally thousands of distinct forms. Word forms carry syn- tactic information in their suffixes and therefore word order is relatively free in Finnish sentences. Because Finnish is syntactically so different from most other Western languages, Finns face a higher language barrier than other Western Europeans do. Increasing foreign trade has forced major Finnish companies to systemati- cally look for ways of making language translation more productive. Machine translation would of course seem to provide an ideal solution, but in practice both the state- of-the-art of MT research and the lack of computational models of Finnish have so far discouraged the compa- nies in their attempts to apply MT software to alleviate the translation load. SITRA Foundation in Finland is a public fund which allocates money for projects of notable national impor- tance. In 1982 SITRA established the KIELIKONE project for the purpose of designing computational mod- els of the Finnish language. The short term goals were to obtain concrete language technology products; the si- multaneous long term goal was to build an infrastructure for MT research. During its period of activity so far the project has designed, implemented, and introduced to the market various software products for the Finnish language: a morphological analyzer (Jäppinen and Ylil- ammi, 1986) and spelling checkers based on that model, a morphological synthesizer (Lassila, 1988), a hyphen- ation algorithm, and dependency parsers (Nelimarkka et al., 1984; Jäppinen et al., 1986; Valkonen et al., 1987; Lassila, 1989). Also, a synonym dictionary for Finnish has been produced both in book (Jäppinen, 1989) and electronic form. As more direct steps toward MT, the project first de- veloped an electronic bilingual Finnish-English dictio- nary. Later on, upon the request of a foreign customer, the project designed and implemented an MT worksta- tion for a syntactically and semantically constrained sub- language {Kulikov and Jäppinen, 1989; Takala et al., 1990). In 1986 it was decided that the project should con- centrate on full-scale MT research in cooperation with two major Finnish companies. Telenokia OY exports telecommunication equipment, and all of their products …

Content truncated to 500 words