Convolutional Neural Networks for Sentence Classification · HackerPapers discussions

Convolutional Neural Networks for Sentence Classification — mentioned by bomb199

Fri, 02 Mar 2018 17:39:06 GMT

Thanks for this, I'll have to take a look at FastText. I've been using word2vec before turning it into a matrix and running it through a CNN. I based it off of Yoon Kim's[0] work. I haven't had much luck though on my 92-class problem. Maybe Fast Text will work better, although I think there are a lot of improvements my model can have still. [0] https://arxiv.org/abs/1408.5882

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

Convolutional Neural Networks for Sentence Classification — mentioned by ovi256

Fri, 02 Mar 2018 15:14:31 GMT

A few remarks: In the "Doing bad digital humanities with color vectors", if you consider colors as 3D vectors, which they do, you'll see that summing enough uniformly sampled vectors always gives medium browns, because that's the color in the middle of the colorspace. Instead, you should model colors in a polar space and sum vectors in that space. This will prevent going inside the sphere and losing color saturation. It's explained quite well here in the Interpolation section: http://www.inference.vc/high-dimensional-gaussian-distributi... If you want to understand contemporary use of words…

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

Convolutional Neural Networks for Sentence Classification — mentioned by drraid0

Wed, 08 Nov 2017 18:45:17 GMT

Yes I have. Convolutional Nets work well for simpler cases. See [Yoon Kim 2014](https://arxiv.org/abs/1408.5882). FYI "Tagging" in NLP is more used for labelling individual words (verbs, nouns, pronouns, etc). "Classification" is a better keyword here.

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

Convolutional Neural Networks for Sentence Classification — mentioned by bernatfp

Mon, 26 Oct 2015 23:44:20 GMT

Surprising there is no mention of any CNN based methods for NLP. A different approach that seems to provide results on par with the state of the art in some NLP tasks [1]. [1] http://arxiv.org/abs/1408.5882

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