Towards Automatic Construction of News Overview Articles by News Synthesis

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2111–2116 Copenhagen, Denmark, September 7–11, 2017. c⃝2017 Association for Computational Linguistics Towards Automatic Construction of News Overview Articles by News Synthesis Jianmin Zhang and Xiaojun Wan Institute of Computer Science and Technology, Peking University The MOE Key Laboratory of Computational Linguistics, Peking University {zhangjianmin2015, wanxiaojun}@pku.edu.cn Abstract In this paper we investigate a new task of automatically constructing an overview article from a given set of news arti- cles about a news event. We propose a news synthesis approach to address this task based on passage segmentation, rank- ing, selection and merging. Our proposed approach is compared with several typi- cal multi-document summarization meth- ods on the Wikinews dataset, and achieves the best performance on both automatic e- valuation and manual evaluation. 1 Introduction There are usually many news articles about a news event, and news summaries can be used for read- ers to quickly learn the most salient information of the news articles. News summaries in previous studies are usually very short, and most of them consist of about one or two hundred words. How- ever, in many circumstances, readers want to learn more about an event, but the news summary is in- sufficient to read, and people are reluctant to read each news article one by one. A possible solution to this problem is constructing a long and compre- hensive news overview article to summarize and present all important facts about the news even- t in an unbiased way. The news overview articles can be considered long summaries, however, news overview articles are more comprehensive and the article texts are harder to arrange and organize. In this paper, we conduct a pilot study to inves- tigate the new task of automatic construction of a news overview article from a set of news articles about an event. We argue that traditional multi- document summarization methods can be applied to this task, but they do not perform well because sentence-based extraction used in these method- s is not suitable for constructing and organizing a long article. Instead, we propose a news synthesis approach to address this task. Our approach uses passage as the basic unit. In this study, passage does not mean a natural paragraph, but means a block of text (maybe multiple paragraphs) about a subtopic of an event. Our approach first segments news articles into passages with the SenTiling al- gorithm, and then ranks the passages with the Di- vRank algorithm. Finally, it selects and merges a few passages to construct the long news overview article. We automatically build an evaluation dataset based on English Wikinews 1. Most Wikinews ar- ticles are synthesis articles and they are written us- ing information from other online news sources. All the important facts available from all sources about a news event are combined into a single ar- ticle for the reader’s convenience, and the infor- mation is presented in a neutral manner avoiding the bias that may be present …

Content truncated to 500 words