Summarizing Procedural Text: Data and Approach

Abstract

Procedural text is a widely used genre that contains many steps of instructions of how to cook a dish or how to conduct a chemical experiment and analyzing the procedural text has become a popular task in the NLP field. Since the procedural text can be very long and contains many details, summarizing the whole procedural text or giving an overview for each complicated procedure step can save time for readers and help the reader to capture the core action in the procedure. In this paper, we propose the procedural text summarization task with two summarization granularity: step-view and globalview, which summarizes each step in procedural text separately or gives an overall summary for all steps respectively. To tackle this task, we propose an Entity-State Graph-based Summarizer (ESGS) which is based on stateof-the-art entity state tracking methods and constructs a heterogeneous graph to aggregate contextual information for each procedure. In order to help the summarization model focus on the salient entity, we propose to use the contextualized procedure graph representation to predict the salient entity. Experiments conducted on two datasets verify the effectiveness of our proposed model, and the code and datasets will be released on https://github. com/gsh199449/procedural-summ.Li Zhang, Qing Lyu, and Chris Callison-Burch. 2020c.Reasoning about goals, steps, and temporal ordering with wikihow. In EMNLP.Tiancheng Zhao, Ran Zhao, and Maxine Eskenazi. 2017. Learning discourse-level diversity for neural dialog models using conditional variational autoencoders. In ACL.