Tag Archives: NLP

Understanding Convolutional Neural Networks for NLP

From http://www.wildml.com/2015/11/understanding-convolutional-neural-networks-for-nlp/

When we hear about Convolutional Neural Network (CNNs), we typically think of Computer Vision. CNNs were responsible for major breakthroughs in Image Classification and are the core of most Computer Vision systems today, from Facebook’s automated photo tagging to self-driving cars.

More recently we’ve also started to apply CNNs to problems in Natural Language Processing and gotten some interesting results. In this post I’ll try to summarize what CNNs are, and how they’re used in NLP. The intuitions behind CNNs are somewhat easier to understand for the Computer Vision use case, so I’ll start there, and then slowly move towards NLP.
Continue reading

Opinion phrases

Opinion phrases was published on September 02, 2014 and last modified onSeptember 02, 2014 by Vlad Sandulescu.

Website  and  Github: 

In Predicting what user reviews are about with LDA and gensim I played with extracting topics from short reviews and given a new review, tried to predict the most probable topic(s) it can be associated with. LDA relies on a bag-of-words model, which is a very popular document representation approach. The model disregards any syntactic dependencies between the words, i.e. any grammar, as well as word order in the documents. For a deeper read about the assumptions made by the LDA model, try to digest Blei’s paper…if you dare!

Continue reading

Predicting what user reviews are about with LDA and gensim

Predicting what user reviews are about with LDA and gensim was published onSeptember 09, 2014 and last modified on September 09, 2014 by Vlad Sandulescu.



I was rather impressed with the impressions and feedback I received for my Opinion phrases prototype – code repository here. So yesterday, I have decided to rewrite my previous post on topic prediction for short reviews using Latent Dirichlet Analysis and its implementation in gensim.
I have previously worked with topic modeling for my MSc thesis but there I used the Semilar toolkit and a looot of C# code. Having read many articles about gensim, I was itchy to actually try it out. Continue reading

Deep Learning + NLP (PFIの勉強会)

  1. Deep Learning とは?
    • Neural Network (input, hidden, output) の拡張: hidden layers >= 2(階層を増やす)
    • Hidden layers:
      • Deep Brief Network
      • Convolutional Neural Network (image recognition)
      • Stacked Auto Encoder
      • Recursive NN
      • Recurrence NN
    • 画像認識精度アップ、音声認識、薬物の活性の推測
      Continue reading