Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Natural Language Processing Demystified (Part One)

nlpdemystified.org

Post reply on HN
Print view View original

11–20 of 45 posts

Re: Show HN: Natural Language Processing Demystified (Part One)

#11

Post by photonemitter »

philophyse wrote: post #8
jll29 wrote: post #3

NLP researcher here. It'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 & notebooks, standalone tools). But what saddens me is too many people are trying to dive into NLP without trying to understand language & linguistics first. For example, you can run a part of speech (POS) tagger in thre…

In your opinion, would George Yule's The Study of Language be a good introduction to linguistics? Or is there any other book that you would recommend to someone who has little knowledge of the field, but a lot of interest?

Jumping in on this; I’ve found jurafsky/martin a good place to start. Covers a lot of ground and is a pretty good read as well.

https://web.stanford.edu/~jurafsky/slp3/

Re: Show HN: Natural Language Processing Demystified (Part One)

#12

Post by scarface74 »

mywaifuismeta wrote: post #9
jll29 wrote: post #3

NLP researcher here. It'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 & notebooks, standalone tools). But what saddens me is too many people are trying to dive into NLP without trying to understand language & linguistics first. For example, you can run a part of speech (POS) tagger in thre…

I'm generally not a fan of these kind of high-level tutorials that tell you "use X library to get Y result" - it's just not good for learning. But any content that tries to sell you on learning ML/NLP/etc in a few weeks is just that. I understand people want to make money by targeting a large audience, but it makes me sad when I see (the vast vast majority) of practitioners not having any understanding about ML (or N…

Everything eventually gets boiled down to libraries. The purpose of technology is to get things done. I could say the same that it makes me sad that today’s developers use high level languages without ever knowing assembly. A chip designer could say that assembly language developers are saddened that the assembly language programmer never had to learn how processors are created.

Re: Show HN: Natural Language Processing Demystified (Part One)

#14

Post by gattilorenz »

LunaSea wrote: post #10
jll29 wrote: post #3

NLP researcher here. It'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 & notebooks, standalone tools). But what saddens me is too many people are trying to dive into NLP without trying to understand language & linguistics first. For example, you can run a part of speech (POS) tagger in thre…

Is this still true in an era where most NLP problems use language models as a solution?

I think so. First of all, knowing some linguistics will teach you terms and concepts (e.g. parse tree, phrase, morpheme, phoneme, etc) that will both help you find relevant literature and avoid reinventing terms for stuff that is widely known (so others will more readily find your work).

Language models are currently the best solution for many problems, but it's hard to predict how we will move forward from here. Maybe the inclusion of linguistic information, or linguistic-inspired knowledge, or whatever, will be the key to having better results, or saving training time/resources. With no linguistics background, I imagine it's hard to get ideas going in that direction (and test if it's actually a good direction)

Re: Show HN: Natural Language Processing Demystified (Part One)

#15

Post by ninjin »

photonemitter wrote: post #11
philophyse wrote: post #8

Earlier quoted context omitted.

In your opinion, would George Yule's The Study of Language be a good introduction to linguistics? Or is there any other book that you would recommend to someone who has little knowledge of the field, but a lot of interest?

Jumping in on this; I’ve found jurafsky/martin a good place to start. Covers a lot of ground and is a pretty good read as well. https://web.stanford.edu/~jurafsky/slp3/

As a somewhat established researcher in the field, I second Jurasky and Martin. It is peerless and what I recommend to anyone joining my team if they think their background NLP knowledge is a bit on the weak side.

Re: Show HN: Natural Language Processing Demystified (Part One)

#16

Post by mirker »

scarface74 wrote: post #12
mywaifuismeta wrote: post #9

Earlier quoted context omitted.

I'm generally not a fan of these kind of high-level tutorials that tell you "use X library to get Y result" - it's just not good for learning. But any content that tries to sell you on learning ML/NLP/etc in a few weeks is just that. I understand people want to make money by targeting a large audience, but it makes me sad when I see (the vast vast majority) of practitioners not having any understanding about ML (or N…

Everything eventually gets boiled down to libraries. The purpose of technology is to get things done. I could say the same that it makes me sad that today’s developers use high level languages without ever knowing assembly. A chip designer could say that assembly language developers are saddened that the assembly language programmer never had to learn how processors are created.

It’s fine when the library is a tight abstraction. Unfortunately, ML libraries are leaky.

Example: take a classification model and change the output dimensions without understanding the model.

Re: Show HN: Natural Language Processing Demystified (Part One)

#17

Post by mothcamp »

PainfullyNormal wrote: post #4
jll29 wrote: post #3

NLP researcher here. It'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 & notebooks, standalone tools). But what saddens me is too many people are trying to dive into NLP without trying to understand language & linguistics first. For example, you can run a part of speech (POS) tagger in thre…

> I recommend people spend a bit of time to read an(y) introduction to linguistics textbook Do you have a favorite you can recommend?

In addition to Jurafsky and Martin (https://web.stanford.edu/~jurafsky/slp3/), I also like Emily Bender's book: https://www.goodreads.com/book/show/18128399-linguistic-fund...

Bender's book is NOT an end-to-end text though imo. It's more a central jumping off point. So you can read about a concept and if it sounds interesting, search more about it.

Re: Show HN: Natural Language Processing Demystified (Part One)

#19

Post by irln »

mothcamp wrote: post #2

Hi HN: 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's mainstream models and frameworks. 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. In part one, we cover text pre…

The interface is great. Did you create the front-end/back-end from scratch?

Re: Show HN: Natural Language Processing Demystified (Part One)

#20

Post by rmellow »

PainfullyNormal wrote: post #4
jll29 wrote: post #3

NLP researcher here. It'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 & notebooks, standalone tools). But what saddens me is too many people are trying to dive into NLP without trying to understand language & linguistics first. For example, you can run a part of speech (POS) tagger in thre…

> I recommend people spend a bit of time to read an(y) introduction to linguistics textbook Do you have a favorite you can recommend?

In addition to Jurafsky and Martin, I recommend Foundations of Statistical NLP by Manning and Schutze: https://nlp.stanford.edu/fsnlp/promo/
Post reply on HN