| 摘要 |
A system and method are provided for automatically generating systematic reviews of received information in a field of science and technology, such as scientific literature, where the systematic review includes a systematic review of a research field in the scientific literature. The method is preferably implemented by a programmed computer and includes the steps of constructing a time series networks of words, passages, documents, and citations and/or co-citations within received information into a synthesized network, decomposing the networks into clusters of fields or topics, performing part-of-speech tagging of text within the received information to provide tagged text, constructing semantic structures of concepts and/or assertions extracted from the source text, generating citation-based and content-based summaries of the clusters of fields or topics and the semantic structures including measuring the saliency, novelty, significance, and transformative features of individual entities in the clusters of fields or topics and semantic structures, and generating structured narratives of the clusters of fields or topics and the summaries of the generated semantic structures, including labeling and summarizing features of the clusters of fields or topics and delinearizing the resulting clusters into templates that provide summarizations of the structure and trends of the information in the clusters at multiple levels of abstraction. Narratives of the citation-based and content-based summaries are merged into a systematic review having a predetermined arrangement.
|
