Distributed Representations of Sentences and Documents · HackerPapers discussions

Distributed Representations of Sentences and Documents — mentioned by hiddencost

Thu, 06 Aug 2026 13:11:10 GMT

You're looking for this paper: https://arxiv.org/abs/1405.4053

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

Distributed Representations of Sentences and Documents — mentioned by gojomo

Mon, 18 Dec 2023 23:47:32 GMT

As another small hint of Mikolov-vs-Le divergence: they're the coauthors of the 'Paragraph Vector' paper (https://arxiv.org/abs/1405.4053) applying a slightly-modified version of word2vec to vectorize longer texts, still in a very shallow way. (This technique often goes by the name 'doc2vec', but other things also sometimes get called that, too.) There are some results in that paper, supposedly from exactly the technique described on an open dataset, that no one has ever been able to reproduce – & you can see the effort has frustrated a lot of people, over the years, in different forums. When…

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

Distributed Representations of Sentences and Documents — HN submission

Thu, 10 Jan 2019 14:55:05 GMT

Distributed Representations of Sentences and Documents

5 points; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.

Distributed Representations of Sentences and Documents — mentioned by aglionby

Fri, 02 Mar 2018 19:35:46 GMT

Doc2vec is the name of the gensim implementation of this paper [0]. Briefly, it creates document embeddings (document being anything on the level of phrases, to sentences, to paragraphs and beyond) on the basis of either predicting a word given the context words (distributed memory -- DM), or predicting the context words given a word (distributed bag of words -- DBOW). [0] https://arxiv.org/abs/1405.4053

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

Distributed Representations of Sentences and Documents — HN submission

Mon, 12 Dec 2016 23:34:57 GMT

Distributed Representations of Sentences and Documents (2014) [pdf]

68 points; 13 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Distributed Representations of Sentences and Documents — 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.

Distributed Representations of Sentences and Documents — mentioned by gojomo

Tue, 25 Aug 2015 09:38:48 GMT

The gensim library now offers the 'Paragraph Vector' [1] approach to create vectors for longer ranges of text. It's available in a class named Doc2Vec – but I don't think that's what is being used here. The Paragraph Vector approach can give interesting results for document-similarity, including similarity after certain 'algebraic'-like additions/subtractions of other topics/word-concepts. [2] [1] http://arxiv.org/abs/1405.4053 [2] http://arxiv.org/abs/1507.07998

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

Distributed Representations of Sentences and Documents — mentioned by Tobu

Sat, 22 Aug 2015 01:03:58 GMT

Such a fluffy article. Here is what he's publishing: http://arxiv.org/find/cs/1/au:+Hinton_G/0/1/0/all/0/1 This seems to be a good introduction to the topic: http://arxiv.org/pdf/1310.4546v1.pdf This is about paragraph vectors: http://arxiv.org/abs/1507.07998 http://arxiv.org/abs/1405.4053

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

Distributed Representations of Sentences and Documents — mentioned by sanxiyn

Mon, 08 Dec 2014 03:42:32 GMT

> Page 60-70 talks about paragraph embedding. I haven't seen this published before. Paragraph embedding was published this year as "Distributed Representations of Sentences and Documents". http://arxiv.org/abs/1405.4053

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

Distributed Representations of Sentences and Documents — HN submission

Tue, 27 May 2014 06:33:15 GMT

Distributed Representations of Sentences and Documents

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