HackerPapers

arXiv:1506.03340cs.CL

Teaching Machines to Read and Comprehend

Karl Moritz Hermann, Tomáš Kočiský, Edward Grefenstette, Lasse Espeholt, Will Kay, Mustafa Suleyman, Phil Blunsom

Abstract

Teaching machines to read natural language documents remains an elusive challenge. Machine reading systems can be tested on their ability to answer questions posed on the contents of documents that they have seen, but until now large scale training and test datasets have been missing for this type of evaluation. In this work we define a new methodology that resolves this bottleneck and provides large scale supervised reading comprehension data. This allows us to develop a class of attention based deep neural networks that learn to read real documents and answer complex questions with minimal prior knowledge of language structure.

arXiv comments
Appears in: Advances in Neural Information Processing Systems 28 (NIPS 2015). 14 pages, 13 figures
Journal reference
DOI
Subjects
cs.CLComputation and Language cs.AIArtificial Intelligence cs.NENeural and Evolutionary Computing

On Hacker News

Linked by 4 identifiable commenters in 5 comments across 5 threads, from Jun 2015 to May 2016. Found in 5 HN submissions from Jun 2015 to Mar 2016. Open submission discussions.

Comments linking this paper, per year.

Discussed in comments5 threads

  1. IBM is not doing "cognitive computing" with Watson 1 comment

    • It's true that we (as in everyone working on these problems - not just IBM) don't have this working. Two points, though: 1) This is probably the most active area of research in machine learning/AI at the moment. The same type of progress that was made in image understanding 2…

      nlView on HNParent context

  2. Go, Marvin Minsky, and the Chasm That AI Hasn’t yet Crossed 1 comment

    • No doubt there is plenty of hype. From where I sit though, a lot of it is justified (Not the general intelligence stuff of course). Choosing problems for their theatrical effect, rather than utility. Writing articles and research papers as if they're marketing pamphlets.…

      nlView on HNParent context

  3. Teaching Machines to Read and Comprehend [pdf] 1 comment

    • non pdf links to arxiv abstracts: Teaching Machines to Read and Comprehend by Hermann, Kočiský, Grefenstette, Espeholt, Kay, Suleyman, & Blunsom http://arxiv.org/abs/1506.03340 and (same group) Reasoning about Entailment with Neural Attention http://arxiv.org/abs/1509.06664…

      deepnetView on HNParent context

  4. DeepMind's machine-reading question/answer dataset 1 comment
  5. DeepMind uses the Daily Mail as a huge training corpus for text comprehension 1 comment

    • The original Deepmind paper [1] is based on a really smart idea. Algorithmic development relies on measuring the performance of any proposed algorithm. For reading comprehension, performance is evaluated using Q&A about the corpus. Its difficult to find a large corpus with a…

      paulsutterView on HNParent context

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.