论文信息 - Scalable hierarchical topic detection: exploring a sample based approach

Scalable hierarchical topic detection: exploring a sample based approach

Hierarchical topic detection is a new task in the TDT 2004 evaluation program, which aims to organize an unstructured news collection in a directed acyclic graph (DAG) structure, reflecting the topics discussed. We present a scalable architecture for HTD and compare several alternative choices for agglomerative clustering and DAG optimization in order to minimize the HTD cost metric.

Dolf Trieschnigg | Wessel Kraaij

[1] James Allan,et al. Topic Detection and Tracking , 2002, The Information Retrieval Series.

[2] Alan F. Smeaton,et al. An Architecture for Efficient Document Clustering and Retrieval on a Dynamic Collection of Newspaper Texts , 1998, BCS-IRSG Annual Colloquium on IR Research.

[3] Patrick Pantel,et al. Document clustering with committees , 2002, SIGIR '02.

[4] Anil K. Jain,et al. Data clustering: a review , 1999, CSUR.

[5] James Allan,et al. Flexible intrinsic evaluation of hierarchical clustering for TDT , 2003, CIKM '03.

[6] Dolf Trieschnigg,et al. TNO Hierarchical topic detection report at TDT 2004 , 2004 .

[7] Wessel Kraaij,et al. Unsupervised Event Clustering in Multilingual News Streams , 2002 .

[8] Wessel Kraaij,et al. Variations on language modeling for information retrieval , 2005, SIGF.

[9] David R. Karger,et al. Scatter/Gather: a cluster-based approach to browsing large document collections , 1992, SIGIR '92.