정보검색 활용을 위한 다국어 데이터베이스의 ILI(Inter-Lingual-Index) 방법론 연구- 유로워드넷의 ILI 확장과 관련하여 -

Abstract

EuroWordNet is an EC- funded project that aims to build a multilingual database consisting of wordnets in several European languages. In this paper we will discuss in detail the multilingual design of the database and the ways in which it should give access to the resources to make this type of comparison possible. The structure of this paper is as follows: In section 2 we will compare different multilingual design options for our database, and motivate our choice for the so-called Inter-Lingual- Index(ILI). This ILI is an unstructured list of concepts that functions only as a fund for interlinking word meanings across languages. We will then further explain the design and the way in which the equivalence relations are expressed. In section 2.3.2 we will discuss the different types of mismatches that can occur across the wordnets, and the way in which they can be compared in the database to extract the most important cases of mismatch. Finally, in section 3 we describe how we improve the ILI (which is mainly based on WordNet1.5 synsets) to get a more consistent matching across the wordnets. Due to differences in the sense- differentiation across resources, many equivalent synsets may not be linked at all. By extending the ILI with coarser synsets that relate several, more specific meanings, we can improve the matching in an elegant and modular way.