Wandering around

It's very often that in natural language processing, you will have to re-format your data to take as inputs to different systems. In this case, these simple linux commands will help you do it much quicker without having to write a script. 1. Merging two files to one file with two column Input f1 looks like this: 1 2 3 4 Input f2 looks like this: a b c d Output f3 will look like this: 1  a 2  b 3  c 4  d Command: paste f1 f2 > f3  The delimiter by default is a tab. You can also define it (for example, separated by a comma) as follows: paste -d ',' f1 f2 > f3 2.  Create a line number to each line of a text file Assume that you want to create an index to each line in a text file, i.e. inserting a line number and then a tab before the content of each line: Input f1: a b c d Output f2: 1  a 2  b 3  c 4  d Command: nl f1 > f2 3. Joining two files with a common field Input f1: 1   aaa 2   bbb 3   ccc 4   ddd Input f

In Machine Learning, we often hear the problems of underfitting, overfitting, or bias and variance. What are they and how to "diagnose" the problem of your models? Underfitting / high bias Symptom: Your training error is high Problem: Your model is not able to capture the underlying structures/relationships in your training data Solution: Make your model more powerful (e.g., bigger nets, longer training time, more iterations) Overfitting / high variance Symptom: Errors on your development set are much higher than your training errors Problem: Your model is "too fit" to the training data Solution: Use more training data (or data augmentation - e.g., flip/rotate images to have more training samples), add regularization to the model (or some techniques like drop-out, early stopping, etc.)

If you are working on Deep Learning or Machine Learning in general, you have heard of these three functions quite frequently. We know that they can all be used as activation functions in neural networks. But what are these functions and why do people use for example ReLU in this part, sigmoid in another part and so on? Here is a friendly introduction to these functions and a brief explanation of when to use which. Sigmoid function Output from 0 to 1 Exponential computation (hence, slow) Is usually used for binary classification (when output is 0 or 1) Almost never used (e.g., tanh is a better option) Tanh function A rescaled logistic sigmoid function (center at 0) Exponential computation Works better than sigmoid ReLU function (Rectified Linear Unit) and its variants Faster to compute Often used as default for activation function in hidden layers ReLU is a simple model which gives 0 value to all W*x + b < 0. The importance is that it introduces to ou

In the previous post , we have seen the 3 word2vec models: skip-gram, CBOW and GloVe. Now let's have a look at negative sampling and what it is used to make training skip-gram faster. The idea is originated from this paper: " Distributed Representations of Words and Phrases and their Compositionality ” (Mikolov et al. 2013) In the previous example , we have seen that if we have a vocabulary of size 10K, and we want to train word vectors of size 300. Then the number of parameters we have to estimate in each layer is 10Kx300. This number is big and makes training prone to over-fitting and gives too much focus on words that appear often, and less focus on rare words. Subsampling of frequent words So the idea of subsampling is that: we try to maximize the probability that "real outside word" appears, and minimize the probability that "random words" appear around center word. Real outside words are words that characterize the meaning of the center word, wh

In this post, we are going to talk about word embedding (or word vector), which is how we represent words in NLP. Word embedding is used in many higher-level applications such as sentiment analysis, Q&A, etc. Let's have a look at the most currently widely used models. One-hot vector is a vector of size V, with V is the vocabulary size. It has value 1 in one position (represents the value of this word "appears") and 0 in all other positions. [0, 0, ... 1, .., 0] This is usually used as the input of a word2vec model. It is just operating as a lookup table. So this one-hot encoding treats words as independent units. In fact, we want to find the "similarity" between words for many other higher-level tasks such as document classification, Q&A, etc. The idea is: To capture the meaning of a word, we look at the words that frequently appear close-by this word. Let's have a look at some state-of-the-art architectures that give us the results of word ve

Step 1: Generate keys in your local computer ssh-keygen -t rsa Step 2: Copy your public key (which you have just generated in the previous step) to the server you want to connect to cat ~/.ssh/id_rsa.pub | ssh username @ server.example "mkdir -p ~/.ssh && chmod 700 ~/.ssh && cat >> ~/.ssh/authorized_keys" Done! Now you can login to the server from your computer through SSH Keys (no need to enter password each time) Optional (for server administrators): disable ROOT login through password for security once you have setup logging in with SSH keys successfully.