Multilingual Generation and Summarization of Job Adverts: the TREE Project

Multilingual Generation and Summarization of Job Adverts: the TREE Project Harold Somers, Bill Black Joakim Nivre, TorbjSrn Lager Centre for Computational Linguistics, SSKKII, UMIST, University of GSteborg, Manchester, England Sweden Annarosa Multari, Luca Gilardoni Quinary SpA, Milano, Italy Jeremy Ellman, Alex Rogers MARI Computer Systems Ltd, Ashington, Northumberland, England Abstract A multilingual Internet-based employment advertisement system is described. Job ads are submitted as e-mail texts, analysed by an example-based pattern matcher and stored in language-independent schemas in an object-oriented database. Users can search the database in their own language and get customized summaries of the job ads. The query engine uses symbolic case-based reasoning techniques, while the generation module integrates canned text, templates, and grammar rules to produce texts and hypertexts in a simple way. 1 Introduction Free movement of labour across national boundaries is an important aim of the European Union. 1 One of the prerequisites for this open labour market is ac- cessibility of information about employment oppor- tunities, both from the point of view of people seek- ing work, and of their potential employers. However, many EU citizens are denied full access to employ- ment opportunities because information may not be readily available, and even where it is, it may not be available in the right language. The TREE project aims to address this problem by providing a system on the Internet where employers can deposit job ads, and which users can browse, each in their own lan- guage. Access to this service will be either through the user's own Internet provider, or at dedicated ter- minals located in employment centres. There are currently very many Interact sites where jobs are advertised, and indeed using information retrieval 1TREE is Language Engineering project LE 1182 of the European Commission's Fourth Framework Pro- gramme. We would like to express our thanks to other partners on the project: Edy Geerts and Marianne Kamoen (VDAB, Vlaamse Dienst voor Arbeidsbemid- deling en Beroepsopleiding), Mick Riley (Newcastle upon Tyne City Council), and Teresa Paskiewicz and Mark Stairmand (UMIST). The URL for the project's web site is http ://www.mari. co. uk/tree/. techniques next to natural language processing to search job offer databases is not a new application, cf. (Vega, 1990; Caldwell & Korelsky, 1994). But no other application - as far as we can discover - offers the opportunity of searching and of getting summaries of job ads in languages other than that of the original announcement. TREE therefore offers two significant services: in- telligent search and summarization on the one hand, and these independent of the original language of the job ad on the other. It could be argued that the latter at least could be achieved by hooking a com- mercial Machine Translation (MT) system up to an Internet employment service. Although MT has had some success on the Internet (Flanagan, 1996), this is with largely sympathetic users who understand well the limitations of MT. Its use for a more del- icate task aimed at the general public, especially a public which …

Content truncated to 500 words