News for hackers. Stuff that matters.
Re:Why Deep Learning Cannot Be Applied to Natural Languages ... by sprobertson on Monday January 02, 2017 @01:27PM (#13303185)
And bases the argument on a single feed forward network, nothing about RNNs which most good NN NLP results are based on.
Re:Why Deep Learning Cannot Be Applied to Natural Languages ... by habeanf on Monday January 02, 2017 @01:34PM (#13303247)
Google's SyntaxNet (as of Andor et al 2016) achieves state-of-the-art accuracy for dependency parsing without RNNs.