Oxford Deep NLP – An advanced course on natural language processing • Hacker News Board

Re: Oxford Deep NLP – An advanced course on natural language processing

#31

Post by mcintyre1994 » Tue, Feb 07, 2017, 2:02 PM UTC

axplusb wrote: post #25

jkbschwarz wrote: post #16

Im taking this course at Oxford and they have been working through the practicals 1-3 (further ones will be posted) For anyone considering working through this outside of Oxford: I think the practicals are the real gems here and should be doable without the practical lab sessions that you get when attending the course. With that being said, they use a dataset a bit closer to a real world assignment. Therefore, it req…

Regarding practicals: is there anything more than the overview slides ?

The org : https://github.com/oxford-cs-deepnlp-2017

That contains repos for practicals, eg. Practical 1: https://github.com/oxford-cs-deepnlp-2017/practical1

Re: Oxford Deep NLP – An advanced course on natural language processing

#32

Post by jdemler » Tue, Feb 07, 2017, 2:34 PM UTC

seycombi wrote: post #5

YOUTUBE-DL will download the lectures https://rg3.github.io/youtube-dl/

Thank you. I just wanted to complain about the need for the adobe flash player.

Re: Oxford Deep NLP – An advanced course on natural language processing

#33

Post by Fede_V » Tue, Feb 07, 2017, 2:40 PM UTC

If you want more advanced materials, both Kyunghyun Cho and Yoav Goldberg posted excellent notes: https://arxiv.org/abs/1511.07916 and https://arxiv.org/abs/1510.00726

Re: Oxford Deep NLP – An advanced course on natural language processing

#34

Post by hmate9 » Tue, Feb 07, 2017, 2:53 PM UTC

I am currently taking this course at Oxford and definitely recommend following this.

We will be using TED talks as our dataset, to create Question Answering, text completion, generating entire TED talks ourselves etc. Definitely very interesting and it is being taught by leading researchers in the field!

Re: Oxford Deep NLP – An advanced course on natural language processing

#35

Post by roystonvassey » Tue, Feb 07, 2017, 3:12 PM UTC

Began this course earlier today and I think they appear to be pulling off the right combo of first principles foundation and tough problem sets, like cs224n (Karpathys CNN class). Other NLP courses that I've taken so far have gone over my head.

Re: Oxford Deep NLP – An advanced course on natural language processing

#36

Post by snissn » Tue, Feb 07, 2017, 3:25 PM UTC

jkbschwarz wrote: post #16

Im taking this course at Oxford and they have been working through the practicals 1-3 (further ones will be posted) For anyone considering working through this outside of Oxford: I think the practicals are the real gems here and should be doable without the practical lab sessions that you get when attending the course. With that being said, they use a dataset a bit closer to a real world assignment. Therefore, it req…

Would you be able to post your own solutions for the non sense spewing ted bot? I'd like to jump into hacking on something that already works while also working through the theory from the lectures

Re: Oxford Deep NLP – An advanced course on natural language processing

#37

Post by cr0sh » Tue, Feb 07, 2017, 3:42 PM UTC

RegW wrote: post #22

"Prerequisites: This not meant to be an introduction to Machine Learning course. Hopefully you've all got some knowledge to machine learning, otherwise you may find this a bit opaque. So at least you should understand/have taken courses in linear algebra, calculus, probability, ... we are not going to do anything particularly challenging in those areas, but ideas from those areas will be useful." around 7 mins 30secs…

Those sound like standard pre-reqs for any ML course - it should probably be a standard disclaimer on every course except for intros (even there, though, you'll want the linear algebra and probability knowledge - at least the bare basics). I can only imagine the number of people who jump into such courses and get in over their head very quickly...

Re: Oxford Deep NLP – An advanced course on natural language processing

#38

Post by circuithunter » Tue, Feb 07, 2017, 3:49 PM UTC

option_greek wrote: post #17

What are the practical uses of language modelling RNNs ? (apart from writing grammar/syntax checkers)

Machine translation is a big one. See the recent NY Times feature [1] and the arxiv paper [2]. Automated image captioning is another (used extensively by Facebook).

[1] https://www.nytimes.com/2016/12/14/magazine/the-great-ai-awa...

[2] https://arxiv.org/abs/1609.08144

Re: Oxford Deep NLP – An advanced course on natural language processing

#39

Post by demonshalo » Tue, Feb 07, 2017, 3:51 PM UTC

here is what I don't understand about deep NLP (please keep in mind that I just began exploring this field):

I am currently working on an algorithm that uses elementary text cues in combination with large data-table lookups to determine things like relevant keywords of news articles scraped from various sites. I have given my results to hundreds of people independently to provide me with some feedback regarding the quality. Here is the current breakdown:

80% of the cases I get perfect score.

10% of the cases I get acceptable score.

10% of the cases needs improvement.

My questions here are:

1. if deep nlp can only provide us with the same level of efficiency/accuracy, then why the hell would we use it?

2. if deep nlp can provide us with more efficiency than what is stated above then wouldn't it be safe to assume that is UNREASONABLY efficient?

3. why are most people using deep nlp or ML in general right off the bat. Theoretically, it would be far more interesting to construct a model where the result of a statistical/linguistically parsing is fed to some sot of ML algo in order to tackle that 10% of bad cases.

Re: Oxford Deep NLP – An advanced course on natural language processing

#40

Post by stephancoral » Tue, Feb 07, 2017, 4:03 PM UTC

greeneggs wrote: post #28

matt4711 wrote: post #23

Earlier quoted context omitted.

Say you want to translate a sentence from language A to language B. You have a system that generates 10 possible translations in language B. Now you use a language model of language B to figure out which is the best translation by asking the language model which of the translations has the highest probability of being generated by the model.

Is there any way to "translate" between writing styles of the same language? I'm thinking something analogous to the Van Gogh-ify image-processing techniques using deep convolutional networks. Even very simple transformations, e.g., adding alliteration/assonance or adding rhymes everywhere, might be fun.

Look into Google's SyntaxNet - https://research.googleblog.com/2016/05/announcing-syntaxnet...

Should help you break down sentences into their semantic parts. The transformations are then made by walking the syntax tree and modifying the tagged parts of speech as you see fit.