Globally Normalized Transition-Based Neural Networks · HackerPapers discussions

Globally Normalized Transition-Based Neural Networks — mentioned by supercarrot

Wed, 15 Jun 2016 16:14:21 GMT

Still, beam search can be simulated and improved by running decision processes in parallel. For example, instead of learning the sequence labeling as a sequence of n decisions (where n is the length of the sequence) you can learn sequence labeling as a sequence of 3n+1 decisions where you make 3 decisions for each sequence element and after 3n decision pick one out of three decision streams that minimizes loss using an extra decision. (when inference is done then the classifier will, hopefully, pick the stream that minimizes test loss). This simulates a beam search and can be done during…

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

Globally Normalized Transition-Based Neural Networks — mentioned by vagabondvector

Mon, 16 May 2016 19:38:35 GMT

http://arxiv.org/abs/1603.06042 this is the paper. the idea is based on the incredible incremental perceptron coupled with beam search for having different hypotheses at the same time trying to find a policy which will build them and select the best one http://dl.acm.org/citation.cfm?id=1218970 The approach to structured prediction that was the fastest at the time was that incremental perceptron and the implementation extremely simple. Some other approaches includes conditional random fields, hidden markov models, maximum margin markov networks, maximum entropy markov model and the approach…

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

Globally Normalized Transition-Based Neural Networks — mentioned by the_decider

Thu, 12 May 2016 20:50:18 GMT

According to their paper (http://arxiv.org/pdf/1603.06042v1.pdf), the technique can also be applied to sentence compression. It would be cool if Google publishes that example code/training-data as well.

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

Globally Normalized Transition-Based Neural Networks — mentioned by xigency

Thu, 12 May 2016 19:53:15 GMT

Evidence that this is the most accurate parser is here; the previous approach mentioned is a March 2016 paper, "Globally Normalized Transition-Based Neural Networks," http://arxiv.org/abs/1603.06042 "On a standard benchmark consisting of randomly drawn English newswire sentences (the 20 year old Penn Treebank), Parsey McParseface recovers individual dependencies between words with over 94% accuracy, beating our own previous state-of-the-art results, which were already better than any previous approach." From the original paper, "Our model achieves state-of-the-art accuracy on all of these…

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