论文信息 - 1 Multi-document Summarization Focusing on Extracting and Integrating Similarities and Differences among Documents

1 Multi-document Summarization Focusing on Extracting and Integrating Similarities and Differences among Documents

The study was to develop a method for automatic summarization of sets of related research abstracts. This summarization method focused on extracting and integrating similarities and differences among different abstracts. In the research studies which aim to look for relationships between research concepts, similarities and differences are mainly reflected through research concepts and relationships expressed in the text. Thus the summarization method extracts research concepts and relationships from each research abstract, integrates similar concepts and relationships across different abstracts, and incorporates them into new sentences to produce a summary. This paper reports the three main summarization steps – discourse parsing, concept extraction and integration, and relationship extraction and integration. Each step was evaluated by comparing the machine output against

Christopher S. G. Khoo

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

[2] Chinatsu Aone,et al. Fast and effective text mining using linear-time document clustering , 1999, KDD '99.

[3] Dragomir R. Radev. A Common Theory of Information Fusion from Multiple Text Sources Step One: Cross-Document Structure , 2000, SIGDIAL Workshop.

[4] Jaime Carbonell,et al. Multi-Document Summarization By Sentence Extraction , 2000 .

[5] Inderjeet Mani,et al. The Challenges of Automatic Summarization , 2000, Computer.

[6] Inderjeet Mani,et al. Summarizing Similarities and Differences Among Related Documents , 1997, Information Retrieval.

[7] Ou Shi-yan,et al. Constructing a taxonomy to support multi-document summarization of dissertation abstracts , 2005 .

[8] Christopher S. G. Khoo,et al. Automatic multidocument summarization of research abstracts: Design and user evaluation , 2007, J. Assoc. Inf. Sci. Technol..