Noun Phrase Translation for Cross-Language Document Selection

Abstract. This paper presents results for the CLEF interactive Cross-Language Document Selection task at the UNED. Two translations tech-niques were compared: the standard Systran translations provided by CLEF organizers as baseline, and a phrase-based pseudo-translation approach that uses a phrase alignment algorithm based on comparable corpora. The hy-pothesis being tested was that noun phrase translations could serve as sum-marized information for relevance judgment without compromising the pre-cision of such judgments. In addition, we wanted to have an indirect measure of the quality of our phrase extraction process, that had been previously de-veloped for an interactive CLIR application. The results of the experiment conrm that the hypothesis is reasonable: a set of 8 monolingual Spanish speakers judged English documents with the same precision for both systems, but achieved 52 % more recall using phrasal translations than using full Systran translations.