EVALUATION OF EXTRACTION METHOD OF IMPORTANT SENTENCE BASED ON ASSOCIATIVE CONCEPT DICTIONARY WITH DISTANCE INFORMATION BETWEEN CONCEPTS

摘要

In this paper, we propose a method for calculating scores of importance for sentences for text summarization purposes. In this method, scores for sentences are calculated based on quantitative distance information in an associative concept dictionary (consisting of about 160,000 associated concepts) built from the results of association experiments. The dictionary is constructed using basic nouns found in Japanese elementary school textbooks. In our evaluation of the method, we compared the quality of the importance score ranking resulting from our method and other methods using term frequency (tfidf). In order to judge the quality, we used eight articles from the textbooks and carried out an experiment where 40 human subjects chose the five most important sentences from each of the eight articles. The evaluation results show that sentences chosen by our method using association relationships is more comparable to those chosen by human subjects. The results show that summarization accuracy can be improved by applying our method.