论文信息 - Interactive, Domain-Independent Identification and Summarization of Topically Related News Articles

Interactive, Domain-Independent Identification and Summarization of Topically Related News Articles

In this paper we present NewsInEssence, a fully deployed digital news system. A user selects a current news story of interest which is useda s a seed article by NewsInEssence to find in real time other related stories from a large number of news sources. The output is a single document summary presenting the most salient information gleaned from the different sources. We discuss the algorithm used by NewsInEssence, module interoperability, and conclude the paper with a number of empirical analyses.

[1] Dragomir R. Radev,et al. Generating summaries of multiple news articles , 1995, SIGIR '95.

[2] Karen Spärck Jones. Automatic summarising: factors and directions , 1998, ArXiv.

[3] Dragomir R. Radev,et al. Centroid-based summarization of multiple documents: sentence extraction, utility-based evaluation, and user studies , 2000, ArXiv.

[4] Inderjeet Mani,et al. Using Cohesion and Coherence Models for Text Summarization , 1998 .

[5] Kathleen R. McKeown,et al. A description of the CIDR system as used for TDT-2 , 1999 .

[6] Jade Goldstein-Stewart,et al. The use of MMR, diversity-based reranking for reordering documents and producing summaries , 1998, SIGIR '98.

[7] Inderjeet Mani,et al. Multi-Document Summarization by Graph Search and Matching , 1997, AAAI/IAAI.

[8] Weiguo Fan,et al. Automatic summarization of search engine hit lists , 2000 .

[9] Walter Bender,et al. Enriching Communities: Harbingers of News in the Future , 1996, IBM Syst. J..

[10] Kathleen R. McKeown,et al. Generating natural language summaries from multiple on-line sources , 1998 .