31–40 of 60 posts
It looks promising! Minor point, a requirements.txt file or something would be convenient to get started quickly.
Once the book is released there will be a whole website and prebuilt environments and lots more to get started quickly. We didn't expect the draft to get this much attention, frankly!
> 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
Megszentségteleníthetetlenségeskedéseitekért for example.
> 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 techni…
Side note: IMHO, you are exaggerating the ability of Polish to form long compounds. Dissecting the "Bezbarwne zielone idee wściekle śpią" example from https://arxiv.org/pdf/1810.10222.pdf#page=3 reveals no words longer than 4 morphemes:
bez-BARW-n-e ZIEL-on-e IDE-e WŚCIEK-l-e ŚP-ią, where I put word roots in uppercase and bound morphemes in lowercase.
The longest sequences of morphemes (for a loose definition of morpheme) I can think of are conditional mood of verbs with double prefixes like po-wy-CHODZI-ł-y-by-ście. However, the sequences of bound morphemes in those forms, which may look complex to you, form a finite-state language that admits just a few sequences.
How does this compare to the video course? e.g. what are the differences?
Earlier quoted context omitted.
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 techni…
The term you are looking for may be "highly inflected". Side note: IMHO, you are exaggerating the ability of Polish to form long compounds. Dissecting the "Bezbarwne zielone idee wściekle śpią" example from https://arxiv.org/pdf/1810.10222.pdf#page=3 reveals no words longer than 4 morphemes: bez-BARW-n-e ZIEL-on-e IDE-e WŚCIEK-l-e ŚP-ią, where I put word roots in uppercase and bound morphemes in lowercase. The longes…
Maybe best to mention Turkish in the book!
Earlier quoted context omitted.
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.
Wait... so if you buy book then it seizes to be GPLed? This is quite confusing. For DL research, most code is MIT licenced and legal folks at many industrial labs would be quite hesitent to permit use of code from this repo with feels like legal minefield with different restrictions spread over multiple places including LICENSE, README, fastai website and perhaps printed book. I would highly recommand converting to o…
Earlier quoted context omitted.
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.
fastai is popular among practitioners as well as many researchers rather than just outsiders or outcasts. I've personally learned from it a lot and is amazing contribution. However, there is still a large population that is still unaware and it would be great to have a quick intro paragraph in readme so they know what all the fuzz is about.