Transfer of Natural Language Processing Technology

Experiments, Possibilities and Limitations Case Study: English to Serbian

Abstract

In this paper, we describe research and instructional activities related to a scientific experiment. This study was conducted to examine possibilities and limitations of transferring human language technologies from a technology rich and morphologically modest language like English to a technologically developing and morphologically rich language as Serbian. We briefly present some collaborative achievements that include building of an information retrieval system (SPretS), a part-of-speech tagger (SPaS), a shallow parser (SPaSer), and a topic tracking system (SeToTraS) for Serbian language. Some of the results reported here have already been disseminated through conference papers while the other ones are in the process of being so.