Towards an open question answering architecture
Research output: Contributions to collected editions/works › Article in conference proceedings › Research › peer-review
Standard
SEMANTiCS 2014: Proceedings of the 10th International Conference on Semantic Systems. ed. / Harald Sack; Agata Filipowska; Jens Lehmann; Sebastian Hellmann. New York: Association for Computing Machinery, Inc, 2014. p. 57-60 (ACM International Conference Proceeding Series; Vol. 2014-September, No. September).
Research output: Contributions to collected editions/works › Article in conference proceedings › Research › peer-review
Harvard
APA
Vancouver
Bibtex
}
RIS
TY - CHAP
T1 - Towards an open question answering architecture
AU - Marx, Edgard
AU - Usbeck, Ricardo
AU - Ngomo, Axel Cyrille Ngonga
AU - Höffner, Konrad
AU - Lehmann, Jens
AU - Auer, Sören
N1 - Conference code: 10
PY - 2014/9/4
Y1 - 2014/9/4
N2 - Billions of facts pertaining to a multitude of domains are now available on the Web as RDF data. However, accessing this data is still a difficult endeavour for non-expert users. In order to meliorate the access to this data, approaches imposing minimal hurdles to their users are required. Although many question answering systems over Linked Data have being proposed, retrieving the desired data is still significantly challenging. In addition, developing and evaluating question answering systems remains a very complex task. To overcome these obstacles, we present a modular and extensible open-source question answering framework. We demonstrate how the framework can be used by integrating two state-of-the-art question answering systems. As a result our evaluation shows that overall better results can be achieved by the use of combination rather than individual stand-alone versions.
AB - Billions of facts pertaining to a multitude of domains are now available on the Web as RDF data. However, accessing this data is still a difficult endeavour for non-expert users. In order to meliorate the access to this data, approaches imposing minimal hurdles to their users are required. Although many question answering systems over Linked Data have being proposed, retrieving the desired data is still significantly challenging. In addition, developing and evaluating question answering systems remains a very complex task. To overcome these obstacles, we present a modular and extensible open-source question answering framework. We demonstrate how the framework can be used by integrating two state-of-the-art question answering systems. As a result our evaluation shows that overall better results can be achieved by the use of combination rather than individual stand-alone versions.
KW - Informatics
KW - Business informatics
UR - http://www.scopus.com/inward/record.url?scp=84937693913&partnerID=8YFLogxK
U2 - 10.1145/2660517.2660519
DO - 10.1145/2660517.2660519
M3 - Article in conference proceedings
AN - SCOPUS:84937693913
SN - 9781450329279
T3 - ACM International Conference Proceeding Series
SP - 57
EP - 60
BT - SEMANTiCS 2014
A2 - Sack, Harald
A2 - Filipowska, Agata
A2 - Lehmann, Jens
A2 - Hellmann, Sebastian
PB - Association for Computing Machinery, Inc
CY - New York
T2 - 10th International Conference on Semantic Systems, SEMANTiCS 2014
Y2 - 4 September 2014 through 5 September 2014
ER -