On the scalability of the answer extraction system "EXTRANS"

Diego Mollá, Michael Hess

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contribution

Abstract

There have been many attempts in the history of Information Retrieval (IR) to add some linguistic capabilites to standard IR systems in order to improve their performance (mainly, their precision). These attempts have not been very successful so far, at least not in the standard IR settings.

The two main reasons are the (related but not identical) problems of data volume and of scalability. First, the volume of data typically processed by IR systems is so large that the use of more than a few isolated linguistic components seemed out of the question, and linguistic components do not work well in isolation. Second, NLP systems that work reasonably well in small scale laboratory contexts will often not scale up to real world domains like those for which IR is standardly used. Both of these points seem to all but rule out the use of full-fledged NLP methods in standard text retrieval applications.
Original languageEnglish
Title of host publicationApplications of natural language to information systems
Subtitle of host publicationproceedings : 4th International Conference NLDB '99
EditorsGünther Friedl, Heinrich C. Mayr
Place of PublicationVienna, Austria
PublisherAustrian Computer Society
Pages219-224
Number of pages6
ISBN (Print)3854031297, 9783854031291
Publication statusPublished - 1999
Externally publishedYes
EventNLDB '99 - Klagenfurt, Austria
Duration: 17 Jun 199919 Jun 1999
Conference number: 4th

Publication series

NameSchriftenreihe der Österreichischen Computer Gesellschaft
PublisherÖsterreichische Computer Gesellschaft (Austrian Computer Society)
Volume129

Conference

ConferenceNLDB '99
CountryAustria
CityKlagenfurt
Period17/06/9919/06/99
OtherAlternative conference title: 4th International Conference on Applications of Natural Language to Information Systems

Fingerprint Dive into the research topics of 'On the scalability of the answer extraction system "EXTRANS"'. Together they form a unique fingerprint.

Cite this