Automatic Abstracting in a Limited Domain

The present paper discusses a new knowledge-based approach proposed for automatic abstracting (AA) in a limited domain. Unlike most of the automatic abstracting models which do not make use of domain knowledge (an therefore are hardly capable of differentiating the "important" from the other concepts in the area) and linguistic knowledge (the summaries obtained usually do not undergo any additional modifications and the uncontrolled linkage of the text picked up for summary may sometimes be unacceptable), our approach is based on empirical, domain and linguistic knowledge, the latter enabling an additional treatment of the extracted text in order to obtain more coherent and natural text. The principal ideas presented in the paper are incorporated in the development of an automatic abstracting program.

[1]  Gunnel Källgren,et al.  Automatic Abstracting Content in Text , 1988, Nordic Journal of Linguistics.

[2]  Yves Chiaramella,et al.  A prototype of an intelligent system for information retrieval: IOTA , 1987, Inf. Process. Manag..

[3]  Steven L. Lytinen,et al.  ATRANS Automatic Processing of Money Transfer Messages , 1986, AAAI.

[4]  Philip J. Hayes,et al.  Automatic Extraction of Facts from Press Releases to Generate News Stories , 1992, ANLP.

[5]  Bernadette Sharp.  Elaboration and testing of new methodologies for automatic abstracting , 1989 .

[6]  Lisa F. Rau,et al.  SCISOR: extracting information from on-line news , 1990, CACM.

[7]  Sheryl R. Young,et al.  Automatic Classification and Summarization of Banking Telexes , 1985, CAIA.

[8]  Benjamin Ka-Yin T'sou,et al.  A Knowledge-based Machine-aided System for Chinese Text Abstraction , 1992, COLING.

[9]  Udo Hahn,et al.  Text condensation as knowledge base abstraction , 1988, [1988] Proceedings. The Fourth Conference on Artificial Intelligence Applications.

[10]  Chris D. Paice,et al.  The automatic generation of literature abstracts: an approach based on the identification of self-indicating phrases , 1980, SIGIR '80.

[11]  James E. Rush,et al.  Automatic abstracting and indexing. II. Production of indicative abstracts by application of contextual inference and syntactic coherence criteria , 1971 .

[12]  E. F. Skorochod'ko.  Adaptive Method of Automatic Abstracting and Indexing , 1971, IFIP Congress.

[13]  Chris D. Paice,et al.  Constructing literature abstracts by computer: Techniques and prospects , 1990, Inf. Process. Manag..

[14]  Paul S. Jacobs,et al.  Joining Statistics with NLP for Text Categorization , 1992, ANLP.

[15]  Jean-Pierre Desclés,et al.  Knowledge-Based Automatic Abstracting: Experiments in the Sublanguage of Elementary Geometry , 1994 .

[16]  Giovanni Guida,et al.  Evaluating Importance: A Step Towards Text Summarization , 1985, IJCAI.

[17]  H. P. Edmundson,et al.  New Methods in Automatic Extracting , 1969, JACM.

[18]  Ralph Grishman,et al.  A linguistically motivated approach to automated analysis of military messages , 1983 .