Paper: To Parse Or Not To Parse: Relation-Driven Text Skimming

ACL ID C90-2034
Title To Parse Or Not To Parse: Relation-Driven Text Skimming
Venue International Conference on Computational Linguistics
Session Main Conference
Year 1990
Authors
  • Paul S. Jacobs (GE Corporate Research & Development, Schenectady NY)

We have designed and implemented a text processing system that can extract impor- tant information from hundreds of para- graphs per hour and can be transported within weeks to a new domain. The sys- tem performs efficiently because it deter- mines the level of processing required to un- derstand a text. This "skimming" method identifies surface relations in the input text that are likely to contribute to its interpre- tation in a domain. This approach differs from previous skimming techniques in that it uses conceptual information as part of bottom-up linguistic processing, thus using linguistic knowledge more fully while limit- ing grammatical complexity.