Dependency-based answer validation for German

Svitlana Babych, Alexander Henn, Jan Pawellek, Sebastian Pado

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

This article describes the Heidelberg contribution to the CLEF 2011 QA4MRE task for German. We focus on the objective of not using any external resources, building a system that represents questions, answers and texts as formulae in propositional logic derived from dependency structure. Background knowledge is extracted from the background corpora using several knowledge extraction strategies. We answer questions by attempting to infer answers from the test documents complemented by background knowledge, with a distance measure as fall-back. The main challenge is to specify the translation from dependency structure into a logical representation. For this step, we suggest different rule sets and evaluate various configuration parameters that tune accuracy and coverage. All of runs exceed a random baseline, but show different coverage/accuracy profiles (accuracy up to 44%, coverage up to 65%).

Original languageEnglish (US)
JournalCEUR Workshop Proceedings
Volume1177
StatePublished - 2011
Externally publishedYes

Keywords

  • German
  • Knowledge extraction
  • Logical inference
  • Machine reading
  • QA4MRE
  • Question answering

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Babych, S., Henn, A., Pawellek, J., & Pado, S. (2011). Dependency-based answer validation for German. CEUR Workshop Proceedings, 1177.

Dependency-based answer validation for German. / Babych, Svitlana; Henn, Alexander; Pawellek, Jan; Pado, Sebastian.

In: CEUR Workshop Proceedings, Vol. 1177, 2011.

Research output: Contribution to journalArticle

Babych, S, Henn, A, Pawellek, J & Pado, S 2011, 'Dependency-based answer validation for German', CEUR Workshop Proceedings, vol. 1177.
Babych, Svitlana ; Henn, Alexander ; Pawellek, Jan ; Pado, Sebastian. / Dependency-based answer validation for German. In: CEUR Workshop Proceedings. 2011 ; Vol. 1177.
@article{7e88f2bfb3874a5a8ce90ddd79e66859,
title = "Dependency-based answer validation for German",
abstract = "This article describes the Heidelberg contribution to the CLEF 2011 QA4MRE task for German. We focus on the objective of not using any external resources, building a system that represents questions, answers and texts as formulae in propositional logic derived from dependency structure. Background knowledge is extracted from the background corpora using several knowledge extraction strategies. We answer questions by attempting to infer answers from the test documents complemented by background knowledge, with a distance measure as fall-back. The main challenge is to specify the translation from dependency structure into a logical representation. For this step, we suggest different rule sets and evaluate various configuration parameters that tune accuracy and coverage. All of runs exceed a random baseline, but show different coverage/accuracy profiles (accuracy up to 44{\%}, coverage up to 65{\%}).",
keywords = "German, Knowledge extraction, Logical inference, Machine reading, QA4MRE, Question answering",
author = "Svitlana Babych and Alexander Henn and Jan Pawellek and Sebastian Pado",
year = "2011",
language = "English (US)",
volume = "1177",
journal = "CEUR Workshop Proceedings",
issn = "1613-0073",

}

TY - JOUR

T1 - Dependency-based answer validation for German

AU - Babych, Svitlana

AU - Henn, Alexander

AU - Pawellek, Jan

AU - Pado, Sebastian

PY - 2011

Y1 - 2011

N2 - This article describes the Heidelberg contribution to the CLEF 2011 QA4MRE task for German. We focus on the objective of not using any external resources, building a system that represents questions, answers and texts as formulae in propositional logic derived from dependency structure. Background knowledge is extracted from the background corpora using several knowledge extraction strategies. We answer questions by attempting to infer answers from the test documents complemented by background knowledge, with a distance measure as fall-back. The main challenge is to specify the translation from dependency structure into a logical representation. For this step, we suggest different rule sets and evaluate various configuration parameters that tune accuracy and coverage. All of runs exceed a random baseline, but show different coverage/accuracy profiles (accuracy up to 44%, coverage up to 65%).

AB - This article describes the Heidelberg contribution to the CLEF 2011 QA4MRE task for German. We focus on the objective of not using any external resources, building a system that represents questions, answers and texts as formulae in propositional logic derived from dependency structure. Background knowledge is extracted from the background corpora using several knowledge extraction strategies. We answer questions by attempting to infer answers from the test documents complemented by background knowledge, with a distance measure as fall-back. The main challenge is to specify the translation from dependency structure into a logical representation. For this step, we suggest different rule sets and evaluate various configuration parameters that tune accuracy and coverage. All of runs exceed a random baseline, but show different coverage/accuracy profiles (accuracy up to 44%, coverage up to 65%).

KW - German

KW - Knowledge extraction

KW - Logical inference

KW - Machine reading

KW - QA4MRE

KW - Question answering

UR - http://www.scopus.com/inward/record.url?scp=84922032481&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84922032481&partnerID=8YFLogxK

M3 - Article

VL - 1177

JO - CEUR Workshop Proceedings

JF - CEUR Workshop Proceedings

SN - 1613-0073

ER -