ERIC Number: ED071686
Record Type: Non-Journal
Publication Date: 1972-Dec
Reference Count: N/A
Techniques for the Evaluation and Improvement of Computer-Produced Abstracts.
Mathis, Betty Ann
An automatic abstracting system, named ADAM, implemented on the IBM 370, receives journal articles as input and produces abstracts as output. An algorithm has been developed which considers every sentence in the input text and rejects sentences which are not suitable for inclusion in the abstract. All sentences which are not rejected are included in the set of sentences which are candidates for inclusion in the abstract. The quality of the abstracts can be evaluated by means of a two-step evaluation procedure. The first step determines the conformity of the abstracts to the defined criteria for an acceptable abstract. The second step provides an objective evaluation criterion for abstract quality based on a comparison of the abstract with its parent document. Based on the results of this evaluation, several techniques have been developed to improve the quality of the abstracts. These procedures modify the form, arrangement, and content of the sentences selected for the abstract. The revision, deletion, or creation of sentences is performed according to a number of generalized rules which are based on the structural characteristics of the sentences. This modification produces abstracts in which the flow of ideas is improved and which represent a more nearly coherent whole. (Author/SJ)
Publication Type: N/A
Education Level: N/A
Sponsor: National Science Foundation, Washington, DC.
Authoring Institution: Ohio State Univ., Columbus. Computer and Information Science Research Center.