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

Draft of the Fast.ai Book

github.com

Post reply on HN
Print view View original

11–20 of 60 posts

Re: Draft of the Fast.ai Book

#11

Post by mkl »

machiaweliczny wrote: post #9
mci wrote: post #4

> There are also "agglutinative languages", like Polish, which can add many morphemes together to create very long "words" which include a lot of separate pieces of information. [1] Polish does not work this way. Source: I am Polish. Perhaps jph00 meant Turkish. Issue filed. [1] https://github.com/fastai/fastbook/blob/master/10_nlp.ipynb

Doesn't German work this way?

Not really. "German grammar allows for the construction of long compounded noun phrases which are expressed as one word in written language. Compounding is not really the same as agglutination.": https://www.quora.com/Is-German-considered-a-true-agglutinat...

There are quite a lot of languages that do though: https://en.wikipedia.org/wiki/Agglutinative_language

Re: Draft of the Fast.ai Book

#12

Post by cube2222 »

I recommend everybody who didn’t check those out to do so.

Not really being interested in ML, but doing all the available most popular courses to keep up, I really liked how fastai doesn’t just teach you ready and known models, but also how to compose differentiable building blocks to design NN’s yourself.

Re: Draft of the Fast.ai Book

#14

Post by gumby »

mkl wrote: post #11
machiaweliczny wrote: post #9

Earlier quoted context omitted.

Doesn't German work this way?

Not really. "German grammar allows for the construction of long compounded noun phrases which are expressed as one word in written language. Compounding is not really the same as agglutination.": https://www.quora.com/Is-German-considered-a-true-agglutinat... There are quite a lot of languages that do though: https://en.wikipedia.org/wiki/Agglutinative_language

Not just in written language, although the difference between a “word” and “noun phrase” in spoken language is in the ear of the beholder.

But in a linguistic sense indeed, German is not at all an agglutinative language.

Re: Draft of the Fast.ai Book

#16

Post by sytelus »

Wow, Orielly lawyers are determined to screw this up. The thing is GPL v3 licensed which means I can’t copy any of the book code in my closed-source product or competitions or even MIT licensed code. The readme says I cannot make copies of this material but it’s ok to fork. Huh?

Re: Draft of the Fast.ai Book

#17

Post by sytelus »

pritovido wrote: post #3

It always amazes me how bad some technical people is at basic promotion: What is Fastai? Why do I need it? Something as basic as an elevator speech that introduces your product in your github page and book intro can mean 10x or 100x more sales. If you force people into having to search it for you, you have already lost most of them. For this author it is as you already know everything about Fastai, but if you did, yo…

You are downvoted by fanboys but you are exactly right. I am surrounded by researchers working in DL and I have say at least 40% of them have never heard of FastAI or Jeremy Howard. However folks who are active on Twitter, listening to popular podcasts, popular media, HN etc would be very familiar with name Jeremy Howard and what FastAI is and need no introduction. In research world, an astonishing number of good researchers have little to none online presence. They have little to no time other than keeping track of research papers in their sub-field. It also surprises me when authors sweat for months to churn out 100s of polished pages but couldn’t spend 15 minutes to write a paragraph of introduction in readme.MD.

Re: Draft of the Fast.ai Book

#18

Post by jph00 »

sytelus wrote: post #16

Wow, Orielly lawyers are determined to screw this up. The thing is GPL v3 licensed which means I can’t copy any of the book code in my closed-source product or competitions or even MIT licensed code. The readme says I cannot make copies of this material but it’s ok to fork. Huh?

No, the readme says you can make copies for personal use.

If you want to use code in the book under a non GPL license, then you could just buy the book when it comes out. That doesn't seem like an unreasonable burden.

PS: none of this is anything to do with O'Reilly or their lawyers.

Re: Draft of the Fast.ai Book

#19

Post by DrNuke »

sytelus wrote: post #17
pritovido wrote: post #3

It always amazes me how bad some technical people is at basic promotion: What is Fastai? Why do I need it? Something as basic as an elevator speech that introduces your product in your github page and book intro can mean 10x or 100x more sales. If you force people into having to search it for you, you have already lost most of them. For this author it is as you already know everything about Fastai, but if you did, yo…

You are downvoted by fanboys but you are exactly right. I am surrounded by researchers working in DL and I have say at least 40% of them have never heard of FastAI or Jeremy Howard. However folks who are active on Twitter, listening to popular podcasts, popular media, HN etc would be very familiar with name Jeremy Howard and what FastAI is and need no introduction. In research world, an astonishing number of good res…

Fast.ai really democratizes the bleeding edge research for the masses, though, that’s why it’s popular among outcasts and outsiders. In general, I would be more wary of people working within closed environments and organizations than people making all they do public and open to review.

Re: Draft of the Fast.ai Book

#20

Post by jph00 »

mci wrote: post #4

> There are also "agglutinative languages", like Polish, which can add many morphemes together to create very long "words" which include a lot of separate pieces of information. [1] Polish does not work this way. Source: I am Polish. Perhaps jph00 meant Turkish. Issue filed. [1] https://github.com/fastai/fastbook/blob/master/10_nlp.ipynb

Yes you're right, in our NLP course we used Turkish as our example.

But for the book I mentioned Polish due to this paper: https://arxiv.org/abs/1810.10222 . But as you say, now the word "agglutinative" isn't technically correct. I'm actually not sure what the right word is to describe languages that have lots of big compounds with no spaces. (Which is the key issue here, as to why we need subword tokenization techniques).

Post reply on HN