How to Write Summaries with Patterns? Learning towards Abstractive Summarization through Prototype Editing

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, pages 3741–3751, Hong Kong, China, November 3–7, 2019. c⃝2019 Association for Computational Linguistics 3741 How to Write Summaries with Patterns? Learning towards Abstractive Summarization through Prototype Editing Shen Gao ♠∗, Xiuying Chen ♠♣∗, Piji Li ♦, Zhangming Chan ♠♣, Dongyan Zhao ♠♣, Rui Yan ♠♣† ♠Wangxuan Institute of Computer Technology, Peking University, Beijing, China, ♦Tencent AI Lab, Shenzhen, China ♣Center for Data Science, Peking University, Beijing, China {shengao, xy-chen, zhangming.chan, zhaody, ruiyan}@pku.edu.cn pijili@tencent.com Abstract Under special circumstances, summaries should conform to a particular style with pat- terns, such as court judgments and abstracts in academic papers. To this end, the prototype document-summary pairs can be utilized to generate better summaries. There are two main challenges in this task: (1) the model needs to incorporate learned patterns from the prototype, but (2) should avoid copying contents other than the patternized words— such as irrelevant facts—into the generated summaries. To tackle these challenges, we design a model named Prototype Editing based Summary Generator (PESG). PESG first learns summary patterns and prototype facts by analyzing the correlation between a prototype document and its summary. Pro- totype facts are then utilized to help extract facts from the input document. Next, an edit- ing generator generates new summary based on the summary pattern or extracted facts. Finally, to address the second challenge, a fact checker is used to estimate mutual information between the input document and generated summary, providing an additional signal for the generator. Extensive experiments conducted on a large-scale real-world text summarization dataset1 show that PESG achieves the state-of-the-art performance in terms of both automatic metrics and human evaluations. 1 Introduction Abstractive summarization can be regarded as a sequence mapping task that maps the source text to the target summary (Rush et al., 2015; Li et al., 2017; Cao et al., 2018; Gao et al., 2019a). It has drawn significant attention since the introduction ∗Equal contribution. Ordering is decided by a coin flip. † Corresponding author. 1https://github.com/gsh199449/proto-summ prototype summary The court held that the defendant Wang had stolen the property of others for the purpose of illegal possession. The amount was large, and his behavior constituted the crime of theft. The accu- sation of the public prosecution agency was established. The de- fendant Wang has a criminal record and will be considered when sentencing. Since the defendant Wang did not succeed because of reasons other than his will, he could be punished lightly. After the defendant confessed his crimes to the case, he was given a lighter punishment according to law. summary The court held that the accused Zhang and Fan stole property and the amount was large. Their actions constituted the crime of theft. The accusation of the public prosecution agency was established and supported. This crime was committed within two years after the release of the defendants Zhang and Fan. Thus they are recidivists and this situation will be …

Content truncated to 500 words