Guided Neural Language Generation for Abstractive Summarization using Abstract Meaning Representation
This work addresses the challenge of generating coherent summaries for natural language processing applications, representing an incremental advance by enhancing existing methods with semantic guidance.
The paper tackles the problem of abstractive summarization by incorporating Abstract Meaning Representation (AMR) to guide neural language generation, resulting in improvements of 7.4 and 10.5 ROUGE-2 points with gold standard and parser-based AMR parses, respectively, and outperforming a baseline by 2 ROUGE-2 points.
Recent work on abstractive summarization has made progress with neural encoder-decoder architectures. However, such models are often challenged due to their lack of explicit semantic modeling of the source document and its summary. In this paper, we extend previous work on abstractive summarization using Abstract Meaning Representation (AMR) with a neural language generation stage which we guide using the source document. We demonstrate that this guidance improves summarization results by 7.4 and 10.5 points in ROUGE-2 using gold standard AMR parses and parses obtained from an off-the-shelf parser respectively. We also find that the summarization performance using the latter is 2 ROUGE-2 points higher than that of a well-established neural encoder-decoder approach trained on a larger dataset. Code is available at \url{https://github.com/sheffieldnlp/AMR2Text-summ}