%0 Conference Paper %1 citeulike:1925072 %A Yang, Yiming %A Zhang, Jian %A Carbonell, Jaime %A Jin, Chun %B KDD '02: Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining %C New York, NY, USA %D 2002 %I ACM %K named-entity news novelty %P 688--693 %R 10.1145/775047.775150 %T Topic-conditioned novelty detection %U http://dx.doi.org/10.1145/775047.775150 %X Automated detection of the first document reporting each new event in temporally-sequenced streams of documents is an open challenge. In this paper we propose a new approach which addresses this problem in two stages: 1) using a supervised learning algorithm to classify the on-line document stream into pre-defined broad topic categories, and 2) performing topic-conditioned novelty detection for documents in each topic. We also focus on exploiting named-entities for event-level novelty detection and using feature-based heuristics derived from the topic histories. Evaluating these methods using a set of broadcast news stories, our results show substantial performance gains over the traditional one-level approach to the novelty detection problem. %@ 1-58113-567-X

@inproceedings{citeulike:1925072, abstract = {{Automated detection of the first document reporting each new event in temporally-sequenced streams of documents is an open challenge. In this paper we propose a new approach which addresses this problem in two stages: 1) using a supervised learning algorithm to classify the on-line document stream into pre-defined broad topic categories, and 2) performing topic-conditioned novelty detection for documents in each topic. We also focus on exploiting named-entities for event-level novelty detection and using feature-based heuristics derived from the topic histories. Evaluating these methods using a set of broadcast news stories, our results show substantial performance gains over the traditional one-level approach to the novelty detection problem.}}, added-at = {2018-03-19T12:24:51.000+0100}, address = {New York, NY, USA}, author = {Yang, Yiming and Zhang, Jian and Carbonell, Jaime and Jin, Chun}, biburl = {https://www.bibsonomy.org/bibtex/2d41ab2d084174b5d304b1f9fa4434e30/aho}, booktitle = {KDD '02: Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining}, citeulike-article-id = {1925072}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=775047.775150}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/775047.775150}, doi = {10.1145/775047.775150}, interhash = {1f0f7b64ea4ec066e07f55dae1503375}, intrahash = {d41ab2d084174b5d304b1f9fa4434e30}, isbn = {1-58113-567-X}, keywords = {named-entity news novelty}, location = {Edmonton, Alberta, Canada}, pages = {688--693}, posted-at = {2008-09-18 20:03:22}, priority = {2}, publisher = {ACM}, timestamp = {2018-03-19T12:24:51.000+0100}, title = {{Topic-conditioned novelty detection}}, url = {http://dx.doi.org/10.1145/775047.775150}, year = 2002 }