Existing neural generation approaches create multi-sentence text as a single sequence. In this paper we propose a structured convolutional decoder that is guided by the content structure of target summaries. We compare our model with existing sequential decoders on three data sets representing different domains. Automatic and human evaluation demonstrate that our summaries have better content coverage.
Generating Summaries with Topic Templates and Structured Convolutional Decoders
A structured convolutional decoder for text generation improves content coverage in summaries compared to sequential decoders.
- Year
- 2019
- Venue
- generating-summaries-with-topic-templates-and-1
- Authors
- 3
- Hosting
- Abstract onlyARXIV-DEFAULT
Cite
Notes
Only stored in your browser.
Attribution
- Abstract & full text
- arxiv.org/abs/1906.04687ARXIV-DEFAULT
- TL;DR
- Semantic Scholar