Exportar Publicação

Marujo, L., Ribeiro, R., Gershman, A., de Matos, D. M., Neto, J. P. & Carbonell, J. (2017). Event-based summarization using a centrality-as-relevance model. Knowledge and Information Systems. 50 (3), 945-968

L. Marujo et al.,  "Event-based summarization using a centrality-as-relevance model", in Knowledge and Information Systems, vol. 50, no. 3, pp. 945-968, 2017

@article{marujo2017_1715020975353,
	author = "Marujo, L. and Ribeiro, R. and Gershman, A. and de Matos, D. M. and Neto, J. P. and Carbonell, J.",
	title = "Event-based summarization using a centrality-as-relevance model",
	journal = "Knowledge and Information Systems",
	year = "2017",
	volume = "50",
	number = "3",
	doi = "10.1007/s10115-016-0966-4",
	pages = "945-968",
	url = "http://link.springer.com/article/10.1007%2Fs10115-016-0966-4"
}

TY  - JOUR
TI  - Event-based summarization using a centrality-as-relevance model
T2  - Knowledge and Information Systems
VL  - 50
IS  - 3
AU  - Marujo, L.
AU  - Ribeiro, R.
AU  - Gershman, A.
AU  - de Matos, D. M.
AU  - Neto, J. P.
AU  - Carbonell, J.
PY  - 2017
SP  - 945-968
SN  - 0219-1377
DO  - 10.1007/s10115-016-0966-4
UR  - http://link.springer.com/article/10.1007%2Fs10115-016-0966-4
AB  - Event detection is a fundamental information extraction task, which has been explored largely in the context of question answering, topic detection and tracking, knowledge base population, news recommendation, and automatic summarization. In this article, we explore an event detection framework to improve a key phrase-guided centrality-based summarization model. Event detection is based on the fuzzy fingerprint method, which is able to detect all types of events in the ACE 2005 Multilingual Corpus. Our base summarization approach is a two-stage method that starts by extracting a collection of key phrases that will be used to help the centrality-as-relevance retrieval model. We explored three different ways to integrate event information, achieving state-of-the-art results in text and speech corpora: (1) filtering of nonevents, (2) event fingerprints as features, and (3) combination of filtering of nonevents and event fingerprints as features.
ER  -