Extractive Topical Summarization With Aspects

Abstract

Extractive summarization is a task of highlighting the most important parts of the text. We introduce a new approach to extractive summarization task using hidden topical structure and information about aspects of the text. Experimental results on CNN/DailyMail demonstrate that our approach generates more accurate summarizations than baseline methods, achieving state-of-the-art results in terms of ROUGE metric. Additionally, we show that aspect information is extremely important in extractive summarization scenario.

Tasks

Reproductions