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.

Show HN: Natural Language Processing Demystified (Part One)

166 pointsby mothcampabout 3 years ago
Hi HN:<p>I published part one of my free NLP course. The course is intended to help anyone who knows Python and a bit of math go from the very basics all the way to today&#x27;s mainstream models and frameworks.<p>I strive to balance theory and practice and so every module consists of detailed explanations and slides along with a Colab notebook (in most modules) putting the theory into practice.<p>In part one, we cover text preprocessing, how to turn text into numbers, and multiple ways to classify and search text using &quot;classical&quot; approaches. And along the way, we&#x27;ll pick up useful bits on how to use tools such as spaCy and scikit-learn.<p>No registration required: <a href="https:&#x2F;&#x2F;www.nlpdemystified.org&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.nlpdemystified.org&#x2F;</a>

4 comments

jll29about 3 years ago
NLP researcher here. It&#x27;s great to see many offerings for courses and tutorials, and NLP has made a lot of progress, in terms of both its science as well as its re-usable software artifacts (ibraries &amp; notebooks, standalone tools).<p>But what saddens me is too many people are trying to dive into NLP without trying to understand language &amp; linguistics first. For example, you can run a part of speech (POS) tagger in three lines of Python, but you will still not know much about what parts of speech are, which languages have which ones, what function they have in linguistic theory or practical applications.<p>What are the advantages of using the C7 tagset over the C5 or PENN tagsets?<p>Why is AT sometimes called DET?<p>etc.<p>I recommend people spend a bit of time to read an(y) introduction to linguistics textbook before diving into NLP, then the second investment will be worth so much more.
评论 #31421735 未加载
评论 #31421586 未加载
评论 #31427217 未加载
评论 #31423537 未加载
评论 #31421679 未加载
评论 #31455941 未加载
评论 #31421752 未加载
评论 #31421597 未加载
评论 #31433468 未加载
评论 #31421588 未加载
评论 #31427158 未加载
评论 #31421572 未加载
mothcampabout 3 years ago
Hi HN:<p>I published part one of my free NLP course. The course is intended to help anyone who knows Python and a bit of math go from the very basics all the way to today&#x27;s mainstream models and frameworks.<p>I strive to balance theory and practice and so every module consists of detailed explanations and slides along with a Colab notebook (in most modules) putting the theory into practice.<p>In part one, we cover text preprocessing, how to turn text into numbers, and multiple ways to classify and search text using &quot;classical&quot; approaches. And along the way, we&#x27;ll pick up useful bits on how to use tools such as spaCy and scikit-learn.<p>No registration required: <a href="https:&#x2F;&#x2F;www.nlpdemystified.org&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.nlpdemystified.org&#x2F;</a>
评论 #31423042 未加载
jasfiabout 3 years ago
I&#x27;m working on extracting facts from sentences, see <a href="https:&#x2F;&#x2F;lxagi.com" rel="nofollow">https:&#x2F;&#x2F;lxagi.com</a>.<p>Which are the toughest NLP problems you know of that aren&#x27;t being solved satisfactorily?
评论 #31425471 未加载
评论 #31426060 未加载
评论 #31424323 未加载
Utkarsh_Moodabout 3 years ago
Looks great, thanks for this!