This paper conducts functional structure analysis of research articles, using the Categories, the author previously proposed as a framework for analysing informational content of research articles. Automatic assignment of the Categories is conducted to the corpus of research articles selected from three specialties, using matching of the lexcal-clue-combination-patterns and stochastic rules. The result is, 86–91% of Category fixed sentences are assinged correct Categories automatically. And through analysis of errors and related studies followings are suggested to improve efficiency of automatic assignment; (1) to consider inter-sentences relationship, (2) to adopt syntactic patterns of lexical clues combination, (3) to introduce the wholistic processing strategy, (4) to examine on modification of the Categories, which are needed content evaluation.
© 1994 三田図書館・情報学会© 1994 Mita Society for Library and Information Science
This page was created on 2022-03-16T10:55:09.485+09:00
This page was last modified on