You have already added 0 works in your ORCID record related to the merged Research product.
Guided Neural Language Generation for Abstractive Summarization using Abstract Meaning Representation
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}
Comment: Accepted in EMNLP 2018
Microsoft Academic Graph classification: Meaning (linguistics) Artificial intelligence business.industry business Parsing computer.software_genre computer Representation (mathematics) Computer science Automatic summarization Natural language processing
Computation and Language (cs.CL), FOS: Computer and information sciences, Computer Science - Computation and Language
Computation and Language (cs.CL), FOS: Computer and information sciences, Computer Science - Computation and Language
Microsoft Academic Graph classification: Meaning (linguistics) Artificial intelligence business.industry business Parsing computer.software_genre computer Representation (mathematics) Computer science Automatic summarization Natural language processing
- University of Cambridge United Kingdom
- University of Sheffield
- University of Sheffield United Kingdom
- The University of Sheffield Greece
- University of Cambridge United Kingdom
- University of Sheffield
- University of Sheffield United Kingdom
- The University of Sheffield Greece
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}
Comment: Accepted in EMNLP 2018