Multilingual cataloguing of product information of specific domains: case Mkbeem system

Multilingual Cataloguing of Product Information of Specific Domains: Case Mkbeem System Aarno Lehtola, Jarno Tenni and Tuula Käpylä VTT Information Technology POB 1201, FIN-02044 VTT Finland Aarno.Lehtola@vtt.fi Abstract This paper describes the Cataloguing Tool of the Mkbeem multilingual eCommerce mediation system. The Cataloguing Tool is used by product suppliers to provide necessary product information in a form required by the mediation system. The relevant information includes product ar- ticles that are maintained in a pivot lan- guage and automatically translated to other supported languages. From the sup- plier viewpoint the Cataloguing Tool im- plements "write-once-publish-many" paradigm. Other functionalities of the tool include automatic extraction of product properties from text articles along to an ontological product model and automatic classification of products based on their properties and ontology models. This pa- per describes the Cataloguing Tool and discusses in more detail about the use of ontologies in automatic interpretation of the semantics of product articles and user queries. 1 Introduction In the year 2000 native English speakers became outnumbered by native users of other languages in the Internet population. Since then the trend has continued and in September 2002 the others com- prised already over 63 % of the population [GlobalReach 2002]. The linguistic diversity is huge among the population. Even within Europe there can easily be counted over 60 languages among which even the smaller ones, like the over 100000 Icelandic speakers, comprise potential customers groups for international eShops. There is a remarkable need for cost effective IT solutions for enabling multilinguality in consumer Internet trading. This is the market where the Mkbeem me- diation system has been positioned. The Mkbeem mediation system (Multilingual Knowledge-Based European Electronic Market- place, outcome of the EC project IST-1999-10589) adapts the language and the trading conditions of an Internet sales point according to its international customers [Leger & al. 2001, Mkbeem 2000- 2002]. The system supports three use cases (shown by the big arrows in Figure 1). Each use case has its own tool. The multilingual Cataloguing Tool is for content and service providers to describe their products by means of text articles in a write-once- publish-many manner so that the information is maintained monolingually. There is a tool for the providers to define the contract conditions of their goods within the context of a consumer sales re- lated legislation model, which enables adaptation of the contracts depending on how the transactions cross national borders. Finally, for consumers there is a system that implements cross-lingual IR from the product databases based on combining NL que- ries, graphical navigation in localised product hier- archies and use of search forms – the user chooses the modality. The language and contract adaptation is based on ontological models covering product models, legislation and related generic knowledge like time, materials and colours. The ontologies function for narrowing the scope of NL processing and for mediating in between different languages [Leger & al. 2000, Gomez-Perez & al. 2001]. Figure 1: The operating context of the Mkbeem mediation system. Next this …

Content truncated to 500 words