4
$\begingroup$

Hi fellow computer scientists,

I just began my journey to the world of ML and NLP so please bear with me. I'm hoping to find some guidance here. I would be very grateful if anyone could point me in the right direction (reading materials, lectures, specific algorithms, tools, etc.) for solving the following list of problems:

  1. Spell checking, grammar checking, proofreading with ML
  2. Text generation on a given topic with ML
  3. "Artistic Style Transfer" for articles (if it is even possible), i.e. "transfer" Shakespeare's writing style onto a given text.

I've done some learning already but neither of this helps:

  1. ML lectures by Andrew Ng
  2. Hacker's guide to Machine learning
  3. Udacity's Introduction to Deep Learning
Improve this question
$\endgroup$
  • 2
    $\begingroup$ A reference request like yours is too broad for Stack Exchange -- you ask for a survey of a whole research area! You need to narrow your focus considerably before a question of reasonable scope appears. Try talking to your advisor(s), search with Google Scholar and check out this guide to better (re)searches on Academia. $\endgroup$ – David Richerby Nov 22 '16 at 10:41
  • 2
    $\begingroup$ It looks to me like you're asking at least 3 different questions here (since you have at least 3 different tasks you're asking about). This site format tends not to work so well when asking multiple questions in the same post. Instead, I'd recommend that you stick asking only one question per question. Also, you should tell us what research you've done (for each topic). $\endgroup$ – D.W.♦ Nov 22 '16 at 17:41
  • $\begingroup$ @D.W. I didn't know if these questions are even related or not. As I stated in the very first sentence I'm a beginner. Now, when I know that these three questions all have different approaches/solutions I know where to dig and all my further questions on this site will be more concrete. Thank you for your patience. $\endgroup$ – vooD Nov 23 '16 at 2:36
  • 1
    $\begingroup$ If you don't know whether they're related or not, a good default would be to assume that they don't belong together in the same post. Instead, I'd recommend that you ask about one of them that you're interested in. (If you're interested in multiple, you can always ask multiple separate questions.) Anyway, I'm glad the answers were helpful! $\endgroup$ – D.W.♦ Nov 23 '16 at 3:32
3
$\begingroup$

As far as I can see, your reading list lacks specific NLP introductions. A really good starting point is Dan Jurafsky and Chris Manning's Coursera course (for example here https://www.youtube.com/watch?v=nfoudtpBV68 ). This specifically covers spell checking in one of the first videos.

In general, spell checking is a rather easy task, while (convincing) text generation is a lot harder. Grammar checking should be easy in theory but I'm not sure about that. Concerning proofreading, I'm not completely sure what you mean by that. Does this extend over spell and grammar checking, in your point of view?

Artistic style transfer is possible although I'm not sure what the current state of the art. You could be more luckily diving into stylometry (https://en.wikipedia.org/wiki/Stylometry) there.

A really good NLP text book to start with is Jurafsky and Martin: Speech and Language Processing (specifically covering generation). 1st edition is publicly available as pdf (just google). But there is also a 2nd edition and they are currently working on a 3rd (the chapters they are done writing are freely available as well).

Improve this answer
$\endgroup$
3
$\begingroup$
  1. Spell checking, grammar checking, proofreading with ML

Norvig: How to Write a Spelling Corrector

  1. "Artistic Style Transfer" for articles (if it is even possible), i.e. "transfer" Shakespeare's writing style onto a given text.

Yes, it is possible. Recurrent neural networks can do this. See The Unreasonable Effectiveness of Recurrent Neural Networks for a nice explanation how this works and Creativity in Machine Learning for a very high-level introduction.

If you want a general introduction to neural networks, I recommend

Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436–444, 2015. [Online]. Available: http://www.nature.com/nature/journal/v521/n7553/abs/nature14539.html

Improve this answer
$\endgroup$

Not the answer you're looking for? Browse other questions tagged or ask your own question.