Online New Event Detection Based on IPLSA Export

@incollection{citeulike:5802753, abstract = {New event detection (NED) involves monitoring one or multiple news streams to detect the stories that report on new events. With the overwhelming volume of news available today, NED has become a challenging task. In this paper, we proposed a new NED model based on incremental PLSA(IPLSA), and it can handle new document arriving in a stream and update parameters with less time complexity. Moreover, to avoid the limitation of TF-IDF method, a new approach of term reweighting is proposed. By dynamically exploiting importance of documents in discrimination of terms and documents' topic information, this approach is more accurate. Experimental results on Linguistic Data Consortium (LDC) datasets TDT4 show that the proposed model can improve both recall and precision of NED task significantly, compared to the baseline system and other existing systems.}, author = {Zhang, Xiaoming and Li, Zhoujun}, citeulike-article-id = {5802753}, citeulike-linkout-0 = {http://dx.doi.org/10.1007/978-3-642-03348-3_38}, citeulike-linkout-1 = {http://www.springerlink.com/content/p4ql631068148738}, doi = {10.1007/978-3-642-03348-3_38}, journal = {Advanced Data Mining and Applications}, keywords = {ned, ner, news, nlp, text-mining, text\_classification}, pages = {397--408}, posted-at = {2009-09-18 16:51:37}, priority = {2}, title = {Online New Event Detection Based on IPLSA}, url = {http://dx.doi.org/10.1007/978-3-642-03348-3_38}, year = {2009} }

TY - CHAP ID - citeulike:5802753 L3 - citeulike-article-id:5802753 N2 - New event detection (NED) involves monitoring one or multiple news streams to detect the stories that report on new events. With the overwhelming volume of news available today, NED has become a challenging task. In this paper, we proposed a new NED model based on incremental PLSA(IPLSA), and it can handle new document arriving in a stream and update parameters with less time complexity. Moreover, to avoid the limitation of TF-IDF method, a new approach of term reweighting is proposed. By dynamically exploiting importance of documents in discrimination of terms and documents’ topic information, this approach is more accurate. Experimental results on Linguistic Data Consortium (LDC) datasets TDT4 show that the proposed model can improve both recall and precision of NED task significantly, compared to the baseline system and other existing systems. JF - Advanced Data Mining and Applications EP - 408 TI - Online New Event Detection Based on IPLSA SP - 397 KW - ned KW - ner KW - news KW - nlp KW - text-mining KW - text_classification AU - Zhang, Xiaoming AU - Li, Zhoujun PY - 2009/// UR - http://dx.doi.org/10.1007/978-3-642-03348-3_38 ER -