PROTEUS (PROtotype TExt Understanding System) and PUNDIT (Prolog UNDerstander of Integrated Text): Research in Text Understanding at the Department of Computer Science, New York University and System Development Corporation--A Bur

摘要

We are engaged in the development systems capable of analyzing short narrative messages dealing with a limited domain and extracting the information contained in the narrative. These systems are initially being applied to messages describing equipment failure. This work is a joint effort of New York University and the System Development Corp. for the DARPA Strategic Computing Program. Our aim is to create a system reliable enough for use in an operational environment. This is a formidable task, both because the texts are unedited (and so contain various errors) and because the complexity of any real domain precludes us from assembling a complete collection of the relationships and domain knowledge relevant to understanding texts in the domain. Our basic approach to increasing reliability will be to bring to bear on the analysis task as many different types of constraints as possible. These include constraints related to syntax, semantics, domain knowledge, and discourse structure. In order to be able to capture the detailed knowledge about the domain that is needed for correct message analyses, we are initially limiting ourselves to messages about one particular piece of equipment (the starting air compressor); if we are successful in this narrow domain, we intend to gradually broaden our system.