TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Abstractions my Deep Learning word2vec model made

125 pointsby aliostadalmost 10 years ago

11 comments

fcholletalmost 10 years ago
The &quot;deep&quot; in deep learning refers to hierarchical layers of representations (to note: you can do &quot;deep learning&quot; without neural networks).<p>Word embeddings using skipgram or CBOW are a shallow method (single-layer representation). Remarkably, in order to stay interpretable, word embeddings <i>have</i> to be shallow. If you distributed the predictive task (eg. skip-gram) over several layers, the resulting geometric spaces would be much less interpretable.<p>So: this is not deep learning, and this not being deep learning is in fact the core feature.
评论 #9716105 未加载
评论 #9716174 未加载
评论 #9716237 未加载
评论 #9715953 未加载
lelfalmost 10 years ago
&gt; <i>word2vec is a Deep Learning technique first described by Tomas Mikolov only 2 years ago but due to its simplicity of algorithm and yet surprising robustness of the results, it has been widely implemented and adopted.</i><p>… And patented <a href="http:&#x2F;&#x2F;www.freepatentsonline.com&#x2F;9037464.html" rel="nofollow">http:&#x2F;&#x2F;www.freepatentsonline.com&#x2F;9037464.html</a>
评论 #9716167 未加载
评论 #9715931 未加载
lqdc13almost 10 years ago
I thought Word 2 Vec isn&#x27;t &quot;Deep Learning&quot; as both CBOW and skip-gram are &quot;shallow&quot; neural models.
评论 #9715754 未加载
bdamosalmost 10 years ago
How did you select words to compare? Did you have to try many poor combinations before selecting a &quot;good&quot; set?
评论 #9715873 未加载
评论 #9715900 未加载
eatonphilalmost 10 years ago
I am not getting the &quot;Obama + Russia - USA = Putin&quot; piece nor the &quot;King + Woman - Man&quot; bit either. Nothing particularly meaningful came up on a search for the latter. Could someone explain?
评论 #9716507 未加载
tshadwellalmost 10 years ago
When I see things like this, it makes me wonder how much data forms each of these vectors; if a single article were to say things about Obama, or humans and animals, would it produce these results?
thisjepisjealmost 10 years ago
Anyone tried this with the corpus of HN commentary?
评论 #9716128 未加载
platzalmost 10 years ago
reminds me of how Chinese words are made up of individual characters that have semantic meaning themselves.
评论 #9715549 未加载
fauigerzigerkalmost 10 years ago
I wonder if Obama + 2017 == Obama - President
评论 #9716504 未加载
评论 #9717230 未加载
datacogalmost 10 years ago
OP:<p>Do you have some more results to share coming from your model?
SilasXalmost 10 years ago
So that&#x27;s the result? That you can find sorta clever vector equations in the results like &quot;Obama + Russia - USA = Putin&quot;?
评论 #9715506 未加载
评论 #9715959 未加载