SOTAVerified

Generating Summaries with Topic Templates and Structured Convolutional Decoders

2019-06-11ACL 2019Code Available0· sign in to hype

Laura Perez-Beltrachini, Yang Liu, Mirella Lapata

Code Available — Be the first to reproduce this paper.

Reproduce

Code

Abstract

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.

Tasks

Reproductions