The Spanish<>Catalan machine translation system interNOSTRUM

The Spanish�Catalan machine translation system interNOSTRUM R. Canals-Marote, A. Esteve-Guillén, A. Garrido-Alenda, M.I. Guardiola-Savall, A. Iturraspe-Bellver, S. Montserrat-Buendia, S. Ortiz-Rojas, H. Pastor-Pina, P.M. Pérez-Antón, and M.L. Forcada, interNOSTRUM Departament de Llenguatges i Sistemes Informàtics, Universitat d'Alacant, E-03071 Alacant E-mail: mlf@dlsi.ua.es Abstract This paper describes interNOSTRUM, a Spanish3Catalan machine translation system currently under development that achieves great speed through the use of finite-state technologies (so that it may be integrated with internet browsing) and a reasonable accuracy using an advanced morphological transfer strategy (to produce fast translation drafts ready for light postedition). Keywords: Spanish, Catalan, finite-state, internet browsing, morphological transfer. 1 Introduction This paper describes a Spanish3Catalan machine translation system, interNOSTRUM. The main reason for the demand of translations from Spanish (official language of Spain) into Catalan is the impulse toward `linguistic normalization' in the Catalan-speaking areas (10 million inhabitants, about 6 million speakers) where Catalan was receding and where the language is now co- official; translation from Catalan into Spanish (mainly for assimilation purposes) allows the access to documents in Catalan by Spanish-speaking people in Spain or Latin America. The interNOSTRUM system is still under development and a prototype has been serving the Universitat d'Alacant, a medium-sized university, and the Caja de Ahorros del Mediterráneo (CAM), one of the largest savings banks in Spain, for about two years now, and a test version is freely available at http://internostrum.com. These two institutions started and currently fund this three-year project (1999-2001), which has a staff of two linguists and four computer engineers. Even though translation accuracy and vocabulary coverage can still be much improved (especially in the Catalan to Spanish version), the speed of the system -- thousands of words per second or tens of millions of words per day on a 1999-model desktop machine acting as an Internet server-- has prompted its use as a system to obtain instantaneous rough translations that are relatively easy to turn into publishable documents and as an aid to information assimilation during internet browsing (accesses to our server have been steadily increasing every month; we had 120,000 visits in March 2001). These speeds are achieved through the use of finite-state technology (Roche and Schabes, 1997) in most of its modules. 2 Current prototype and future versions As has been said, interNOSTRUM is not yet a finished product; however, it has been available for some time now. This is because two of the basic objectives of our project have been, first, to generate an operational version of interNOSTRUM as soon as possible (Spanish-to- Catalan system launched November 1999) and, second, to make the latest stable version available as soon as it is ready. These are the main reasons for its current configuration as a single Internet server instead of as distributable software. Currently, interNOSTRUM translates ANSI, RTF (Microsoft's Rich Text Format) and HTML (HyperText Markup Language) texts from Castillian Spanish to the central or Barcelona variety of Catalan and vice-versa. A version generating and accepting the València and the Balearic varieties should be ready in September …

Content truncated to 500 words