Hacker News Reader

Comment by Cozumel | Hacker News Reader

I wonder what it'd be like on a novel, say something like 'pride and prejudice', would it be able to essentially summarise the plot or would it end up like 'movie plots explained badly'

Either way, this is great research with a ton of real world applications!

View on HN

> Although this task serves as a nice proof-of-concept, we started looking at more difficult datasets where reading the entire document is necessary to produce good summaries. In those tasks training from scratch with this model architecture does not do as well as some other techniques we’re researching, but it serves as a baseline.

That would suggest that this method doesn't work well for long documents.

A student in a course I TA'd in college used Microsoft Word's built-in summarization to reduce books to ten words. The results were hilarious.

http://jason-huff.com/projects/autosummarize/

by classifying the emotional arcs for a filtered subset of 1,737 stories from Project Gutenberg's fiction collection, we find a set of six core trajectories which form the building blocks of complex narratives. We strengthen our findings by separately applying optimization, linear decomposition, supervised learning, and unsupervised learning

http://arxiv.org/abs/1606.07772

It'll be more remarkable if a machine can read a play script and summarize the plot.

I doubt most humans can even do this well.

Reply on news.ycombinator.com