Text Understanding from Scratch · HackerPapers discussions

Text Understanding from Scratch — mentioned by theschreon

Mon, 30 Apr 2018 17:27:16 GMT

"Search is all well and good when we are counting words, which is what data analytics and machine learning are really all about." There are machine learning models which go far beyond counting words, for example see https://arxiv.org/abs/1502.01710

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

Text Understanding from Scratch — HN submission

Fri, 17 Feb 2017 19:38:12 GMT

Text Understanding from Scratch (2015)

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

Text Understanding from Scratch — mentioned by eegilbert

Sun, 05 Jun 2016 14:07:06 GMT

One example is this recent paper on learning (somewhat) high-level attributes of text from character streams alone (i.e., without telling the convolutional networks that things like words and punctuation exist). https://arxiv.org/abs/1502.01710

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

Text Understanding from Scratch — HN submission

Thu, 02 Jun 2016 07:25:35 GMT

Text understanding from scratch

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

Text Understanding from Scratch — mentioned by Xeoncross

Wed, 01 Jun 2016 22:37:14 GMT

Is this the paper they said they based this on: "Text Understanding from Scratch": http://arxiv.org/abs/1502.01710 Here is example code for text classification from character-level using convolutional networks in Torch 7 https://github.com/zhangxiangxiao/Crepe

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

Text Understanding from Scratch — mentioned by p1esk

Tue, 27 Oct 2015 03:01:53 GMT

Here's one by Lecun: http://arxiv.org/abs/1502.01710

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

Text Understanding from Scratch — mentioned by JadeNB

Fri, 13 Mar 2015 13:21:02 GMT

My usual plea for abstracts over PDFs: http://arxiv.org/abs/1502.01710 .

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

Text Understanding from Scratch — HN submission

Fri, 13 Mar 2015 01:15:37 GMT

Text Understanding from Scratch [pdf]

53 points; 5 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Text Understanding from Scratch — mentioned by agibsonccc

Wed, 11 Mar 2015 22:24:17 GMT

Word2vec is usually the standard neural word embeddings implementation. There are other algorithms as well such as glove[1], document embeddings[2] and backpropagation based methods[3]. Facebook just came out with a paper recently that beat word2vec as well[4]. Neural word embeddings are a neat way of representing concepts. I see a great future for automated feature engineering with text (joining audio and images) in deep learning. [1]: http://nlp.stanford.edu/pubs/glove.pdf [2]: http://cs.stanford.edu/~quocle/paragraph_vector.pdf…

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

Text Understanding from Scratch — HN submission

Fri, 06 Feb 2015 20:08:31 GMT

Text Understanding from Scratch Using Temporal Convolutional Networks

61 points; 9 discussion replies on HN. Paper and source history. A submission is not an endorsement.