JIRS Language-Independent Passage Retrieval System A Comparative Study

Passage Retrieval (PR) systems are used as the first step of the actual Question An-swering (QA) systems. Usually, PR sys-tems are traditional information retrieval systems which are not oriented to the spe-cific problematic of QA. In fact, these sys-tems only search for the question key-words. We have developed a QA-oriented PR system which searches the question structures in the document collection in order to find the passages with the great-est probability to contain the answer. In this paper, we have carried out a com-parative study of our system with other well-known PR models. The experiments show that with our language-independent n-gram model is possible to improve the coverage of the correct answers using nat-ural language questions. The JIRS Dis-tance Density N-gram system has been already adapted to several European lan-guages. At the moment, we have been adapting it also to some of the official In-dian languages in order to prove further the independence of the language.