INFORMATION EXTRACTION - BEYOND DOCUMENT-RETRIEVAL

In this paper we give a synoptic view of the growth of the text proces sing technology of information extraction (Ie) whose function is to ex tract information about a pre-specified set of entities, relations or events from natural language texts and to record this information in s tructured representations called templates. Here we describe the natur e of the re task, review the history of the area from its origins in A I work in the 1960s and 70s till the present, discuss the techniques b eing used to carry out the task, describe application areas where IE s ystems are or are about to be at work, and conclude with a discussion of the challenges facing the area. What emerges is a picture of an exc iting new text processing technology with a host of new applications, both on its own and in conjunction with other technologies, such as in formation retrieval, machine translation and data mining.