BibSonomy :: publication ::

tag user group author concept BibTeX key search:all search:sonntag

The blue social bookmark and publication sharing system.

entry of sonntag:

(0)

This publication has not been reviewed yet.

rating distribution

average user rating

The average rating is computed over all reviews. However, some of them may be invisible to you due to the visibility setting chosen by the reviewers.

(0.0 of 5.0 based on 0 reviews)

Querying Structured Knowledge Sources

by: Anette Frank, Hans-Ulrich Krieger, Feiyu Xu, Hans Uszkoreit, Berthold Crysmann, Brigitte Jörg, and Ulrich Schäfer

In: Proceedings of AAAI-05. Workshop on Question Answering in Restricted Domains Pittsburgh, Pennsylvania: (2005) , p. 10--19.

Resources (URL, PDF, PS...)

URL:	ws1305FrankA.pdf

We present an implemented approach for domain-restricted question answering from structured knowledge sources, based on robust semantic analysis in a hybrid NLP system architecture. We build on a lexical-semantic conceptual structure for question interpretation, which is interfaced with domain-specific concepts and properties in a structured knowledge base. Question interpretation involves a limited amount of domain-specific inferences and accounts for quantificational questions. We extract so-called proto queries from the linguistic representation, which provide partial constraints for answer extraction from the underlying knowledge sources. The search queries we construct from proto queries effectively constitute minimum spanning trees that restrict the possible answer candidates. Our approach naturally extends to multilingual question answering and has been developed as a prototype system for two application domains: the domain of Nobel prize winners and the domain of Language Technology, on the basis of the large ontology underlying the information portal LT World.

Description

Daniel Sonntag all references

BibTeX record

@inproceedings{frank05,
  abstract = {We present an implemented approach for domain-restricted question
	answering from structured knowledge sources, based on robust semantic
	analysis in a hybrid NLP system architecture. We build on a lexical-semantic
	conceptual structure for question interpretation, which is interfaced
	with domain-specific concepts and properties in a structured knowledge
	base. Question interpretation involves a limited amount of domain-specific
	inferences and accounts for quantificational questions. We extract
	so-called proto queries from the linguistic representation, which
	provide partial constraints for answer extraction from the underlying
	knowledge sources. The search queries we construct from proto queries
	effectively constitute minimum spanning trees that restrict the possible
	answer candidates. Our approach naturally extends to multilingual
	question answering and has been developed as a prototype system for
	two application domains: the domain of Nobel prize winners and the
	domain of Language Technology, on the basis of the large ontology
	underlying the information portal LT World. },
  added-at = {2009-11-25T18:41:14.000+0100},
  address = {Pittsburgh, Pennsylvania},
  author = {Frank, Anette and Krieger, Hans-Ulrich and Xu, Feiyu and Uszkoreit, Hans and Crysmann, Berthold and J\"{o}rg, Brigitte and Sch\"{a}fer, Ulrich},
  biburl = {http://www.bibsonomy.org/bibtex/2190d632a2f30a31a026cbbc6e23e31a3/sonntag},
  booktitle = {Proceedings of AAAI-05. Workshop on Question Answering in Restricted
	Domains},
  description = {Daniel Sonntag all references},
  interhash = {e0469dd85a6b78646775d7fa016cf1cc},
  intrahash = {190d632a2f30a31a026cbbc6e23e31a3},
  keywords = {QABook imported},
  owner = {sonntag},
  pages = {10--19},
  timestamp = {2009-11-25T18:41:14.000+0100},
  title = {{Querying Structured Knowledge Sources}},
  url = {ws1305FrankA.pdf},
  year = 2005
}

Endnote record

%0 Conference Paper
%1 frank05
%A Frank, Anette
%A Krieger, Hans-Ulrich
%A Xu, Feiyu
%A Uszkoreit, Hans
%A Crysmann, Berthold
%A J\"{o}rg, Brigitte
%A Sch\"{a}fer, Ulrich
%B Proceedings of AAAI-05. Workshop on Question Answering in Restricted
	Domains
%C Pittsburgh, Pennsylvania
%D 2005
%K 
%P 10--19
%T {Querying Structured Knowledge Sources}
%U ws1305FrankA.pdf
%X We present an implemented approach for domain-restricted question
	answering from structured knowledge sources, based on robust semantic
	analysis in a hybrid NLP system architecture. We build on a lexical-semantic
	conceptual structure for question interpretation, which is interfaced
	with domain-specific concepts and properties in a structured knowledge
	base. Question interpretation involves a limited amount of domain-specific
	inferences and accounts for quantificational questions. We extract
	so-called proto queries from the linguistic representation, which
	provide partial constraints for answer extraction from the underlying
	knowledge sources. The search queries we construct from proto queries
	effectively constitute minimum spanning trees that restrict the possible
	answer candidates. Our approach naturally extends to multilingual
	question answering and has been developed as a prototype system for
	two application domains: the domain of Nobel prize winners and the
	domain of Language Technology, on the basis of the large ontology
	underlying the information portal LT World.