Automatic Lossless-Summarization of News Articles with Abstract Meaning Representation
Ritwik Mishra, Tirthankar Gayen · Procedia Computer Science · 2018
The continuously growing size of the textual content needs a way to be designed to store the information in condensed manner with minimal information loss. Hence, the concept of lossless-summary is introduced which aims to address the problem of dangling anaphoras and incoherency in extractive summaries. A pipeline of operations has been proposed by this work in order to generate lossless-summaries. Co-reference resolution is performed pairwise on the sentences before generating the Abstract Meaning Representation (AMR) of the sentences. An algorithm to merge AMR graphs is developed and finally the text is generated using the merged AMR graphs. CNN/Dailymail dataset of news article is used for evaluations and results obtained shows the potential for lossless-summarization.