%0 Conference Paper %1 swan99extracting %A Swan, Russell %A Allan, James %B CIKM '99: Proceedings of the eighth international conference on Information and knowledge management %C New York, NY, USA %D 1999 %I ACM %K information_extraction nlp text_mining time_series %P 38--45 %R http://doi.acm.org/10.1145/319950.319956 %T Extracting significant time varying features from text %U http://portal.acm.org/citation.cfm?id=319956# %X We propose a simple statistical model for the frequency of occurrence of features in a stream of text. Adoption of this model allows us to use classical significance tests to filter the stream for interesting events. We tested the model by building a system and running it on a news corpus. By a subjective evaluation, the system worked remarkably well: almost all of the groups of identified tokens corresponded to news stories and were appropriately placed in time. A preliminary objective evaluation was also used to measure the quality of the system and it showed some of the weaknesses and the power of our approach. %@ 1-58113-146-1

@inproceedings{swan99extracting, abstract = {We propose a simple statistical model for the frequency of occurrence of features in a stream of text. Adoption of this model allows us to use classical significance tests to filter the stream for interesting events. We tested the model by building a system and running it on a news corpus. By a subjective evaluation, the system worked remarkably well: almost all of the groups of identified tokens corresponded to news stories and were appropriately placed in time. A preliminary objective evaluation was also used to measure the quality of the system and it showed some of the weaknesses and the power of our approach.}, added-at = {2008-06-10T11:30:55.000+0200}, address = {New York, NY, USA}, author = {Swan, Russell and Allan, James}, biburl = {https://www.bibsonomy.org/bibtex/262021e5e9c5f56cef8474b9431076005/hkorte}, booktitle = {CIKM '99: Proceedings of the eighth international conference on Information and knowledge management}, description = {Extracting significant time varying features from text}, doi = {http://doi.acm.org/10.1145/319950.319956}, interhash = {948f930ca71b28c690753291b98b0560}, intrahash = {62021e5e9c5f56cef8474b9431076005}, isbn = {1-58113-146-1}, keywords = {information_extraction nlp text_mining time_series}, location = {Kansas City, Missouri, United States}, pages = {38--45}, publisher = {ACM}, timestamp = {2008-09-30T11:47:41.000+0200}, title = {Extracting significant time varying features from text}, url = {http://portal.acm.org/citation.cfm?id=319956#}, year = 1999 }