News for hackers. Stuff that matters.
Re:Getting Started in Natural Language Processing by stochastic_monk on Friday June 08, 2018 @03:41PM (#17269036)
The state of the art is primarily hybrid models which use deep neural networks in combination with classical parsing algorithms. For example, the Stack LSTM method uses a form of arc-std with an LSTM and a stack of sorts.
Re:Getting Started in Natural Language Processing by riku_iki on Friday June 08, 2018 @04:43PM (#17269515)
And on which problem this approach achieved state of art results?
Re:Getting Started in Natural Language Processing by stochastic_monk on Friday June 08, 2018 @04:48PM (#17269553)
Dependency Parsing [1].

[1] https://arxiv.org/abs/1505.08075

Re:Getting Started in Natural Language Processing by riku_iki on Friday June 08, 2018 @05:02PM (#17269650)
I checked this paper briefly, and couldn't find any "classical parsing algorithms" there. Maybe you could point me on what do you mean?..

Also why do you think it is state of art? Is it in top results in any recent benchmarks (e.g. http://universaldependencies.org/conll17/results.html)?

Re:Getting Started in Natural Language Processing by stochastic_monk on Friday June 08, 2018 @05:32PM (#17269888)
Arc-standard [1] is the classical algorithm in question. See section 3.2 of Dyer's paper: "Our parser is based on the arc-standard transition inventory (Nivre, 2004), given in Figure 3".

Perhaps it's not still state of the art, but I don't see dependency parsing as a task in that suite of benchmarks, and NLP isn't my primary field, so I'm not up-to-date on the whether or not another method has outperformed it in the last three years. (I would be surprised if one hadn't.) At the time it was, and regardless, I don't doubt that the current state of the art similarly uses neural networks only as a subset of the complete method.

[1] https://www.aclweb.org/anthology/W04-0308

Edit: I can't seem to reply to the post below me. There isn't an entry CMU/Pittsburgh in your benchmark. The paper refers to the Stanford Dependency [SD] and Penn Chinese Treebank 5 [CTB5], and reports 90.9/85.7, respectively, for LAS scores. I'm not sure if any of the treebanks listed correspond to these, but these numbers do seem in line to at least be competitive regardless of which treebank is used.

Re:Getting Started in Natural Language Processing by riku_iki on Friday June 08, 2018 @05:57PM (#17270061)
> But I don't see dependency parsing as a task in that suite of benchmarks

That site is dedicated for dependency parsing task, scorecard represents results of various teams/models.