Skip-Thought Vectors · HackerPapers discussions

Skip-Thought Vectors — mentioned by jkldotio

Wed, 23 Mar 2016 23:12:08 GMT

I don't speak with any authority on this. With word2vec you can do operations like king - man + woman and the nearest vector will be queen. Similarly capital cities will be in a similar relationship to their countries so if you take Rome - Italy + Spain you will be nearest to Madrid. That permits limited reasoning by analogy and there are some analogy benchmark tasks which those word models perform reasonably well on, effectively answering loads of questions like "Madrid is to Spain as Rome is to ____?". This model is more complex and seems to be using a series of techniques to "disentangle"…

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

Skip-Thought Vectors — mentioned by versteegen

Thu, 05 Nov 2015 13:39:17 GMT

Sure, Numenta seemed heavily focused on temporal sequences, but in "On Intelligence" Hawkins describes a more general picture. Prediction should be done not only on the past but on the context. The context includes other variables that also have to be predicted (e.g. predict the next word in a sentence based on a prediction of where this conversation is going) I think that predicting the next word in a sentence does actually get to the point of the issue, which is why the Hutter Prize [0] is defined the way it is. The human brain does: (1) operate sequentially on words (2) keeps an internal…

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

Skip-Thought Vectors — mentioned by cs702

Sat, 05 Sep 2015 19:10:27 GMT

I have shivers going down my spine at the idea of feeding, say, skip-thought vectors representing sentences[1] into stack-augmented recurrent neural nets as proposed in Facebook's paper[2], for all sorts of interesting tasks. -- [1] http://arxiv.org/pdf/1506.06726v1.pdf [2] http://arxiv.org/pdf/1503.01007.pdf

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

Skip-Thought Vectors — mentioned by cs702

Sun, 30 Aug 2015 13:45:39 GMT

This is not about word2vec, an algorithm for learning vector representations of words. This is about learning vector representations of thoughts (ideas, concepts, etc.) in an unsupervised manner. For reference, two months ago some of Hinton's colleagues at the University of Toronto published a paper describing an unsupervised algorithm for learning vector representations of sentences: http://arxiv.org/pdf/1506.06726v1.pdf Once trained, this algorithm is given a sentence and asked to find similar sentences in a corpus of half a million sentences, and it produces impressive results. For…

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

Skip-Thought Vectors — HN submission

Tue, 23 Jun 2015 04:56:54 GMT

Skip-Thought Vectors

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