Toward Abstractive Summarization Using Semantic Representations
This work addresses the problem of generating concise summaries for general text processing, though it is incremental as it builds on existing AMR tools.
The authors tackled abstractive summarization by developing a framework that uses Abstract Meaning Representation (AMR) graphs to parse source text, transform it into a summary graph, and generate text, achieving promising results in experiments on gold-standard and system-parsed AMR annotations.
We present a novel abstractive summarization framework that draws on the recent development of a treebank for the Abstract Meaning Representation (AMR). In this framework, the source text is parsed to a set of AMR graphs, the graphs are transformed into a summary graph, and then text is generated from the summary graph. We focus on the graph-to-graph transformation that reduces the source semantic graph into a summary graph, making use of an existing AMR parser and assuming the eventual availability of an AMR-to-text generator. The framework is data-driven, trainable, and not specifically designed for a particular domain. Experiments on gold-standard AMR annotations and system parses show promising results. Code is available at: https://github.com/summarization