A Convolutional Neural Network for Modelling Sentences (2014) [pdf]
1–10 of 25 posts
Re: A Convolutional Neural Network for Modelling Sentences (2014) [pdf]
#2Inviting a discussion on the topic.
Re: A Convolutional Neural Network for Modelling Sentences (2014) [pdf]
#3Would like to actually see these CNN's first hand but if I'm not missing something on a first quick pass, the amazing results of 2013-2014 are continuing. Major gating barriers that have stymied AGI's are disappearing. This result is cool on its own. But, what really excites is how this provides a key foundational building block for even cooler ideas. When you have sentence structure, it naturally lends itself to many unsupervised NLP and learning tasks. Just wow!
Re: A Convolutional Neural Network for Modelling Sentences (2014) [pdf]
#4I see Thomas Mikolov, the creator of Google's Word2Vec (https://www.kaggle.com/c/word2vec-nlp-tutorial/forums/t/1234...) is referenced in the paper.
Re: A Convolutional Neural Network for Modelling Sentences (2014) [pdf]
#5I see Thomas Mikolov, the creator of Google's Word2Vec ( https://www.kaggle.com/c/word2vec-nlp-tutorial/forums/t/1234... ) is referenced in the paper.
Word2Vec is getting referenced a lot these days, but that doesn't mean much about the referencing paper. This approach is pretty unique in trying to apply CNNs (which are very successful in image recognition) to NLP. But it's not yet clear to me whether these are just tricks or are they really onto some key insight.
Re: A Convolutional Neural Network for Modelling Sentences (2014) [pdf]
#6How do you guys understand this stuff!?
The topic absolutely fascinated me, but after reading the paper... I just feel dumb. Are there any good resources I could use to better understand machine learning papers such as this? I mean I can't even comprehend the implications this paper could have? Is anyone opening to doing some mentoring?
Gbachik@gmail.com
Re: A Convolutional Neural Network for Modelling Sentences (2014) [pdf]
#7How do you guys understand this stuff!? The topic absolutely fascinated me, but after reading the paper... I just feel dumb. Are there any good resources I could use to better understand machine learning papers such as this? I mean I can't even comprehend the implications this paper could have? Is anyone opening to doing some mentoring? Gbachik@gmail.com
You just need to learn some background. I recommend this hands-on resource: http://karpathy.github.io/neuralnets/
Re: A Convolutional Neural Network for Modelling Sentences (2014) [pdf]
#8How do you guys understand this stuff!? The topic absolutely fascinated me, but after reading the paper... I just feel dumb. Are there any good resources I could use to better understand machine learning papers such as this? I mean I can't even comprehend the implications this paper could have? Is anyone opening to doing some mentoring? Gbachik@gmail.com
You can start with:
http://deeplearning.net/tutorial/
And this book (work in progress):
Re: A Convolutional Neural Network for Modelling Sentences (2014) [pdf]
#9The progress here is getting spooky, including the success of such networks for captioning arbitrary images and translating between natural languages. I read that one researcher predicts live narration of video within 5 years.
A cold-splash-in-the-face intro for laypeople can be found in the TEDx talk of Jeremy Howard (founder of Kaggle):
The wonderful and terrifying implications of computers that can learn – https://www.youtube.com/watch?v=xx310zM3tLs
For cutting-edge research, it seems the "NIPS" conference each December is where many of the new results appear:
Re: A Convolutional Neural Network for Modelling Sentences (2014) [pdf]
#10I see Thomas Mikolov, the creator of Google's Word2Vec ( https://www.kaggle.com/c/word2vec-nlp-tutorial/forums/t/1234... ) is referenced in the paper.
Notably, Mikolev is now at Facebook.
My hunch (as a total outsider) is that anything Google publishes is about 2 years behind their current best practices.