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.

The Amazing Power of Word Vectors (2016)

127 pointsby SamuelKillinabout 8 years ago

6 comments

iconvalleysilabout 8 years ago
More interesting information from a DOD research lab that resulted in vectors <a href="https:&#x2F;&#x2F;www.kaggle.com&#x2F;c&#x2F;word2vec-nlp-tutorial&#x2F;discussion&#x2F;12349" rel="nofollow">https:&#x2F;&#x2F;www.kaggle.com&#x2F;c&#x2F;word2vec-nlp-tutorial&#x2F;discussion&#x2F;12...</a>
评论 #13782448 未加载
j_sabout 8 years ago
Recently HN featured a podcast interview with &quot;one of the creators of Word2Vec and fastText&quot;, documenting some of his professional history.<p><a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=13630678" rel="nofollow">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=13630678</a>
Bioeyeabout 8 years ago
This is an awesome explanation of those papers! Does anyone have any cool examples of word2vec being used in a project? I&#x27;d be interested in seeing what people could make with it.
评论 #13782438 未加载
ideonexusabout 8 years ago
For anyone looking for a simple javascript explorable explanation of this you can quickly download and run in a browser, I just found the following GitHub Project.<p>Demo:<p><a href="http:&#x2F;&#x2F;turbomaze.github.io&#x2F;word2vecjson&#x2F;" rel="nofollow">http:&#x2F;&#x2F;turbomaze.github.io&#x2F;word2vecjson&#x2F;</a><p>Code:<p><a href="https:&#x2F;&#x2F;github.com&#x2F;turbomaze&#x2F;word2vecjson" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;turbomaze&#x2F;word2vecjson</a><p>The code looks pretty straightforward so I look forward to exploring this playground of a new and fascinating concept.
评论 #13783610 未加载
vonnikabout 8 years ago
Word vectors are great. We&#x27;ve also written about them at length.[0] But any one interested in word vectors should also be looking at newer ways of applying neural nets to text. Specifically, convolutional nets with pooling for time are producing great results for clustering and classification.<p>[0] <a href="https:&#x2F;&#x2F;deeplearning4j.org&#x2F;&#x2F;word2vec" rel="nofollow">https:&#x2F;&#x2F;deeplearning4j.org&#x2F;&#x2F;word2vec</a>
mustafabisic1about 8 years ago
You nailed it with the &quot;German + airlines&quot; example. Up until that point it was tough to read for a newbie like me. Great blog post