How to Get into Natural Language Processing
blog.ycombinator.com
How to Get into Natural Language Processing
1–10 of 80 posts
Re: How to Get into Natural Language Processing
#2How? just get started working on a fun problem. A good place to start is keyword extraction. You don't need a PhD or expensive tools. All you need is some free time and willingness to read some cool stuff.
Copy a few articles into text files and get working on implementing some of these methods until you have enough of an understanding to construct your own methods for the fun of it.
Here's some good reading material:
https://www.facebook.com/notes/facebook-engineering/under-th...
https://www.researchgate.net/profile/Stuart_Rose/publication...
http://cdn.intechopen.com/pdfs/5338.pdf
https://arxiv.org/pdf/1603.03827v1.pdf
https://www.quora.com/Sentiment-Analysis-What-are-the-good-w...
http://hrcak.srce.hr/file/207669
http://nlp.stanford.edu/fsnlp/promo/colloc.pdf
https://arxiv.org/ftp/cs/papers/0410/0410062.pdf
http://delivery.acm.org/10.1145/1120000/1119383/p216-hulth.p...
Edit: Don't get deterred by the math formulas in these papers. They look far more complicated than they actually are.
Re: How to Get into Natural Language Processing
#3Fun problem: Write a parser for the English language.
See it fail at tweets :)
Re: How to Get into Natural Language Processing
#4I think "Paths" is a terrific idea. There have been times where I've wanted to do a "first principles" look at a topic but don't want to go back through my HN upvotes. "Paths" allows for a curated and practical advice-driven jumping off point. Looking forward to more content. Best of luck with it!
Re: How to Get into Natural Language Processing
#5How? just get started working on a fun problem. A good place to start is keyword extraction. You don't need a PhD or expensive tools. All you need is some free time and willingness to read some cool stuff. Copy a few articles into text files and get working on implementing some of these methods until you have enough of an understanding to construct your own methods for the fun of it. Here's some good reading material…
Another fun thing is to paste article text into some API, like the Watson demo, so you can see what kinds of things are possible:
https://alchemy-language-demo.mybluemix.net/
I played around with this a bit to develop https://www.findlectures.com, so knowing what works/doesn't work there I'm developing some NLP scripts to support my use cases.
Re: How to Get into Natural Language Processing
#6There are a ton of libraries and tools available for NLP, so I feel that side is relatively mature.
What I want are more tools for Natural Language Generation. Can anyone recommend some good ones? (beyond what's on Wikipedia)
Re: How to Get into Natural Language Processing
#7How? just get started working on a fun problem. A good place to start is keyword extraction. You don't need a PhD or expensive tools. All you need is some free time and willingness to read some cool stuff. Copy a few articles into text files and get working on implementing some of these methods until you have enough of an understanding to construct your own methods for the fun of it. Here's some good reading material…
Thank you very much for the reading material
Re: How to Get into Natural Language Processing
#8One of the best places to start is reading this patent from Berkeley Lab/DOE which word2vec was based on https://www.google.com/patents/US7987191
Re: How to Get into Natural Language Processing
#9I think "Paths" is a terrific idea. There have been times where I've wanted to do a "first principles" look at a topic but don't want to go back through my HN upvotes. "Paths" allows for a curated and practical advice-driven jumping off point. Looking forward to more content. Best of luck with it!
So glad that you enjoyed the post! What are other topics that you've wanted to hear about?
Re: How to Get into Natural Language Processing
#10There are a ton of libraries and tools available for NLP, so I feel that side is relatively mature. What I want are more tools for Natural Language Generation. Can anyone recommend some good ones? (beyond what's on Wikipedia)
+ this. It's actually much harder than folks think; most solutions are still rules and sentence fragments that you string append. Automated Insights and Narrative Science are both doing interesting work, but more is needed here.
(...though I don't agree that NLP is mature, just more mature than this. Lots of room to improve NLP as well!)