Towards a Better Understanding of Predict and Count Models · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/1511.02024/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTTowards a Better Understanding of Predict and Count Models — mentioned by cschmidthttps://news.ycombinator.com/item?id=13774364urn:hackerpapers:mention:1511.02024:13774364Thu, 02 Mar 2017 14:54:44 GMT<p>The paper you link is about word2vec, which has taken quite a while to understand. This paper shows word2vec is a particular factorization of the word-context matrix. Neural Word Embedding as Implicit Matrix Factorization https://papers.nips.cc/paper/5477-neural-word-embedding-as-i... Which is some of the story. I found this paper also interesting. Towards a Better Understanding of Predict and Count Models https://arxiv.org/abs/1511.02024</p><p><a href="https://hackerpaper.kaipfister.de/p/1511.02024/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.LG