The Goldilocks Principle: Reading Children's Books with Explicit Memory Representations — mentioned by nl

Thu, 02 Jun 2016 04:28:56 GMT

Facebook have one of the leading teams on doing Deep Learning question answering. Jason Weston et. al wrote a paper introducing a machine-generated textual dataset[1] similar to what you describe, eg: Daniel picked up the football. Daniel drops the football. Daniel got the milk. Daniel took the apple. How many objects is Daniel holding? There have been plenty other papers published by them and others tackling that and similar but harder problems eg[2] [1]http://arxiv.org/pdf/1502.05698v10.pdf [2] http://arxiv.org/abs/1511.02301

Paper and discussion history. A mention is not an endorsement.

The Goldilocks Principle: Reading Children's Books with Explicit Memory Representations — HN submission

Thu, 18 Feb 2016 19:33:08 GMT

The Goldilocks Principle

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

The Goldilocks Principle: Reading Children's Books with Explicit Memory Representations · HackerPapers discussions

The Goldilocks Principle: Reading Children's Books with Explicit Memory Representations — mentioned by nl

The Goldilocks Principle: Reading Children's Books with Explicit Memory Representations — HN submission