Text Summarization using Abstract Meaning Representation

Abstract

With an ever increasing size of text present on the Internet, automatic summary generation remains an important problem for natural language understanding. In this work we explore a novel full-fledged pipeline for text summarization with an intermediate step of Abstract Meaning Representation (AMR). The pipeline proposed by us first generates an AMR graph of an input story, through which it extracts a summary graph and finally, generate summary sentences from this summary graph. Our proposed method achieves state-of-the-art results compared to the other text summarization routines based on AMR. We also point out some significant problems in the existing evaluation methods, which make them unsuitable for evaluating summary quality.

10 pages, 4 figures, Update: Added more results , corrected figures and tables

References in corpus (1)

• SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of Documents

Cited by in corpus (7)

• Point-less: More Abstractive Summarization with Pointer-Generator Networks
• Dynamic Semantic Graph Construction and Reasoning for Explainable Multi-hop Science Question Answering
• Self-Attentive Constituency Parsing for UCCA-based Semantic Parsing
• SemEval 2019 Shared Task: Cross-lingual Semantic Parsing with UCCA - Call for Participation
• Automatic Accuracy Prediction for AMR Parsing
• Automatic Summarization of Natural Language
• A Differentiable Relaxation of Graph Segmentation and Alignment for AMR Parsing