Details
| Originalsprache | Englisch |
|---|---|
| Titel des Sammelwerks | CIKM 2015 - Proceedings of the 24th ACM International Conference on Information and Knowledge Management |
| Seiten | 1815-1818 |
| Seitenumfang | 4 |
| ISBN (elektronisch) | 9781450337946 |
| Publikationsstatus | Veröffentlicht - 17 Okt. 2015 |
| Veranstaltung | 24th ACM International Conference on Information and Knowledge Management, CIKM 2015 - Melbourne, Australien Dauer: 19 Okt. 2015 → 23 Okt. 2015 |
Publikationsreihe
| Name | International Conference on Information and Knowledge Management, Proceedings |
|---|---|
| Band | 19-23-Oct-2015 |
Abstract
Manually inspecting text to assess whether an event occurs in a document collection is an onerous and time consuming task. Although a manual inspection to discard the false events would increase the precision of automatically detected sets of events, it is not a scalable approach. In this paper, we automatize event validation, defined as the task of determining whether a given event occurs in a given document or corpus. The introduction of automatic event validation as a post-processing step of event detection can boost the precision of the detected event set, discarding false events and preserving the true ones. We propose a novel automatic method for event validation, which relies on a supervised model to predict the occurrence of events in a non-annotated corpus. The data for training the model is gathered via crowdsourcing. Experiments on real-world events and documents show that our method (i) outperforms the state-of-the-art event validation approach and (ii) increases the precision of event detection while preserving recall.
ASJC Scopus Sachgebiete
- Entscheidungswissenschaften (insg.)
- Allgemeine Entscheidungswissenschaften
- Betriebswirtschaft, Management und Rechnungswesen (insg.)
- Allgemeine Unternehmensführung und Buchhaltung
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
CIKM 2015 - Proceedings of the 24th ACM International Conference on Information and Knowledge Management. 2015. S. 1815-1818 (International Conference on Information and Knowledge Management, Proceedings; Band 19-23-Oct-2015).
Publikation: Beitrag in Buch/Bericht/Sammelwerk/Konferenzband › Aufsatz in Konferenzband › Forschung › Peer-Review
}
TY - GEN
T1 - Improving event detection by automatically assessing validity of event occurrence in text
AU - Ceroni, Andrea
AU - Gadiraju, Ujwal
AU - Fisichella, Marco
N1 - Publisher Copyright: Copyright 2015 ACM.
PY - 2015/10/17
Y1 - 2015/10/17
N2 - Manually inspecting text to assess whether an event occurs in a document collection is an onerous and time consuming task. Although a manual inspection to discard the false events would increase the precision of automatically detected sets of events, it is not a scalable approach. In this paper, we automatize event validation, defined as the task of determining whether a given event occurs in a given document or corpus. The introduction of automatic event validation as a post-processing step of event detection can boost the precision of the detected event set, discarding false events and preserving the true ones. We propose a novel automatic method for event validation, which relies on a supervised model to predict the occurrence of events in a non-annotated corpus. The data for training the model is gathered via crowdsourcing. Experiments on real-world events and documents show that our method (i) outperforms the state-of-the-art event validation approach and (ii) increases the precision of event detection while preserving recall.
AB - Manually inspecting text to assess whether an event occurs in a document collection is an onerous and time consuming task. Although a manual inspection to discard the false events would increase the precision of automatically detected sets of events, it is not a scalable approach. In this paper, we automatize event validation, defined as the task of determining whether a given event occurs in a given document or corpus. The introduction of automatic event validation as a post-processing step of event detection can boost the precision of the detected event set, discarding false events and preserving the true ones. We propose a novel automatic method for event validation, which relies on a supervised model to predict the occurrence of events in a non-annotated corpus. The data for training the model is gathered via crowdsourcing. Experiments on real-world events and documents show that our method (i) outperforms the state-of-the-art event validation approach and (ii) increases the precision of event detection while preserving recall.
KW - Event detection
KW - Event validation
KW - Precision boosting
UR - http://www.scopus.com/inward/record.url?scp=84958247064&partnerID=8YFLogxK
U2 - 10.1145/2806416.2806624
DO - 10.1145/2806416.2806624
M3 - Conference contribution
AN - SCOPUS:84958247064
T3 - International Conference on Information and Knowledge Management, Proceedings
SP - 1815
EP - 1818
BT - CIKM 2015 - Proceedings of the 24th ACM International Conference on Information and Knowledge Management
T2 - 24th ACM International Conference on Information and Knowledge Management, CIKM 2015
Y2 - 19 October 2015 through 23 October 2015
ER -