7 June 2002, ILLC talks, Wessel Kraaij

Abstract:
Although Cross-Language Information Retrieval (CLIR) is available for more and more language pairs, based on MT services, many languages are still not covered. An attractive alternative is to construct translation models based on parallel corpora mined from the web. Since these corpora are noisy, embedding translation models in the retrieval model is not without problems. However, experiments showed that retrieval effectiveness can surpass MT systems in a CLIR evaluation task.