Summarizing Similarities and Differences Among Related Documents
Information Retrieval
The rhetorical parsing of unrestricted texts: a surface-based approach
Computational Linguistics
The Smart/Empire TIPSTER IR system
TIPSTER '98 Proceedings of a workshop on held at Baltimore, Maryland: October 13-15, 1998
Improving robust domain independent summarization
TIPSTER '98 Proceedings of a workshop on held at Baltimore, Maryland: October 13-15, 1998
NHS: a tool for the automatic construction of news hypertext
IRSG'98 Proceedings of the 20th Annual BCS-IRSG conference on Information Retrieval Research
Hi-index | 0.00 |
With the widespread use of full-text information retrieval, passage-retrieval techniques are becoming increasingly popular. Larger texts can then be replaced by important text excerpts, thereby simplifying the retrieval task and improving retrieval effectiveness. Passage-level evidence about the use of words in local contexts is also useful for resolving language ambiguities and improving retrieval output. Two main text decomposition strategies are introduced in this study, including a chronological decomposition into {\em text segments}, and semantic decomposition into {\em text themes}. The interaction between text segments and text themes is then used to characterize text structure, and to formulate specifications for information retrieval, text traversal, and text summarization.