T. Brants, F. Chen, and A. Farahat. Annual ACM Conference on Research and Development in Information Retrieval (SIGIR), (2003)
Abstract
We present a new method and system for performing the New Event Detection task, i.e., in one or multiple streams of news stories, all stories on a previously unseen (new) event are marked. The method is based on an incremental TF-IDF model. Our extensions include: generation of source-specific models, similarity score normalization based on document-specific averages, similarity score normalization based on source-pair specific averages, term reweighting based on inverse event frequencies, and segmentation of the documents. We also report on extensions that did not improve results. The system performs very well on TDT3 and TDT4 test data and scored second in the TDT-2002 evaluation.
%0 Journal Article
%1 Brants2003
%A Brants, Thorsten
%A Chen, Francine
%A Farahat, Ayman
%D 2003
%J Annual ACM Conference on Research and Development in Information Retrieval (SIGIR)
%K detection erc event event_detection new
%P 330--337
%T A System for New Event Detection
%U http://portal.acm.org/citation.cfm?id=860435.860495
%X We present a new method and system for performing the New Event Detection task, i.e., in one or multiple streams of news stories, all stories on a previously unseen (new) event are marked. The method is based on an incremental TF-IDF model. Our extensions include: generation of source-specific models, similarity score normalization based on document-specific averages, similarity score normalization based on source-pair specific averages, term reweighting based on inverse event frequencies, and segmentation of the documents. We also report on extensions that did not improve results. The system performs very well on TDT3 and TDT4 test data and scored second in the TDT-2002 evaluation.
@article{Brants2003,
abstract = {We present a new method and system for performing the New Event Detection task, i.e., in one or multiple streams of news stories, all stories on a previously unseen (new) event are marked. The method is based on an incremental TF-IDF model. Our extensions include: generation of source-specific models, similarity score normalization based on document-specific averages, similarity score normalization based on source-pair specific averages, term reweighting based on inverse event frequencies, and segmentation of the documents. We also report on extensions that did not improve results. The system performs very well on TDT3 and TDT4 test data and scored second in the TDT-2002 evaluation.},
added-at = {2012-09-17T17:48:52.000+0200},
author = {Brants, Thorsten and Chen, Francine and Farahat, Ayman},
biburl = {https://www.bibsonomy.org/bibtex/2d01ef926bfb5fc9969e5ea93a47737e5/lillejul},
interhash = {541643ea82065c3783546507d86063d7},
intrahash = {d01ef926bfb5fc9969e5ea93a47737e5},
journal = {Annual ACM Conference on Research and Development in Information Retrieval (SIGIR)},
keywords = {detection erc event event_detection new},
pages = {330--337},
timestamp = {2012-09-17T17:54:07.000+0200},
title = {{A System for New Event Detection}},
url = {http://portal.acm.org/citation.cfm?id=860435.860495},
year = 2003
}