Teaching Machines to Read and Comprehend · HackerPapers discussions

Teaching Machines to Read and Comprehend — mentioned by nl

Mon, 23 May 2016 05:37:38 GMT

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 years ago using deep learning techniques is now being seen in NLP. See for example[1]. 2) It isn't at all clear that "making connections" of the type he talks about is needed to generate the types on insights that he claims. For example, the work StitchFix is doing combining analogy reasoning on words along with other…

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

Teaching Machines to Read and Comprehend — HN submission

Sat, 05 Mar 2016 20:07:34 GMT

Teaching Machines to Read and Comprehend

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

Teaching Machines to Read and Comprehend — mentioned by nl

Wed, 03 Feb 2016 10:54:05 GMT

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. Claiming that incremental improvements are paradigm shifts. Treating arbitrary achievements as if they were commonly agreed upon milestones all along. I'm not sure what to say to this. There are no "commonly agreed upon milestones". The closest things are the academic benchmarks/shared tasks that you seem to be critical of. I…

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

Teaching Machines to Read and Comprehend — mentioned by deepnet

Wed, 09 Dec 2015 21:33:59 GMT

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 Learning to Transduce with Unbounded Memory http://arxiv.org/abs/1506.02516

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

Teaching Machines to Read and Comprehend — mentioned by andrewtbham

Fri, 02 Oct 2015 18:40:27 GMT

Link to the original paper. http://arxiv.org/abs/1506.03340

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

Teaching Machines to Read and Comprehend — HN submission

Thu, 06 Aug 2015 22:41:21 GMT

Google DeepMind: Teaching Machines to Read and Comprehend [pdf]

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

Teaching Machines to Read and Comprehend — mentioned by paulsutter

Tue, 23 Jun 2015 05:28:55 GMT

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 comprehensive set of questions about the content. Deepmind is cleverly converting the Daily Mail article summaries into questions by removing a proper noun. For example: Question: Producer X will not press charges against Jeremy Clarkson, his lawyer says. Answer: Oisin Tymon They are using the Daily Mail corpus to develop…

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

Teaching Machines to Read and Comprehend — HN submission

Thu, 11 Jun 2015 23:20:03 GMT

Google Deepmind – Teaching Machines to Read and Comprehend [pdf]

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

Teaching Machines to Read and Comprehend — HN submission

Thu, 11 Jun 2015 05:59:52 GMT

Teaching Machines to Read and Comprehend – Deepmind [pdf]

4 points; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.

Teaching Machines to Read and Comprehend — HN submission

Thu, 11 Jun 2015 02:42:56 GMT

DeepMind: Teaching Machines to Read and Comprehend

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