This post is about my own paper to appear at ACL later this month. What is interesting about this paper will depend on your research interests, so that’s how I’ve broken down this blog post.
A few key points first:
Data and code are available on Github. The paper is also available. The general-purpose span labeling and linking annotation tool we used is also appearing at ACL. Check out DSTC 8 Track 2, which is based on this work.
Neural abstractive summarisation can be dramatically improved with a beam search that favours output that matches the source document, and further improved with attention based on PageRank, with a modification to avoid attending to the same sentence more than once.