Data Science Stack Exchange Community Digest

Top new questions this week:

Is there a reference dataset for contextual similarity?

I’m doing some experiments with word embeddings to try to capture context-aware similarity, so that for example the word pair apple – hardware, are very dissimilar in the context of a fruit store, but …

nlp word-embeddings similarity semantic-similarity

asked by Jorgemar Score of 3 answered by Erwan Score of 2

unbalanced data on train set and test set

I already have 2 datasets. One to use for training and one for testing. Both datasets are unbalanced (with similar percentages), with around 90% of label 1 . Will it be useful to balance the data if …

machine-learning training sentiment-analysis oversampling

asked by mikeman Score of 2 answered by justinlk Score of 0

Is it valid changing the classification treshold of neural networks for improving the classification performance?

I’m dealing with text classification using BERT pre-trained model with a multiclass imbalanced dataset. When we use a 0.5 default classification threshold we obtain a f1 measure of around 0.7. But we …

machine-learning classification bert text-classification

asked by Zaratruta Score of 1 answered by lpounng Score of 2

How does BERT work for Aspect-Based sentiment analysis?

I have recently used a package to perform Aspect-Based Sentiment Analysis (ABSA) through a BERT model. Briefly, the model takes two inputs: words that constitute the aspects a sentence on which we …

deep-learning nlp bert sentiment-analysis

asked by Alberto De Benedittis Score of 1

Greatest hits from previous weeks:

How to draw Deep learning network architecture diagrams?

I have built my model. Now I want to draw the network architecture diagram for my research paper. Example is shown below:

machine-learning neural-network deep-learning svm software-recommendation

asked by Muhammad Ali Score of 189 answered by Pablo Rivas Score of 134

What is the difference between Gradient Descent and Stochastic Gradient Descent?

What is the difference between Gradient Descent and Stochastic Gradient Descent? I am not very familiar with these, can you describe the difference with a short example?

machine-learning neural-network deep-learning gradient-descent

asked by Developer Score of 75 answered by Sociopath Score of 83

How can I check the correlation between features and target variable?

I am trying to build a Regression model and I am looking for a way to check whether there’s any correlation between features and target variables? This is my …

machine-learning scikit-learn regression linear-regression

asked by user_6396 Score of 31 answered by JahKnows Score of 24

When to use GRU over LSTM?

The key difference between a GRU and an LSTM is that a GRU has two gates (reset and update gates) whereas an LSTM has three gates (namely input, output and forget gates). Why do we make use of GRU …

neural-network deep-learning lstm gru

asked by Sayali Sonawane Score of 174 answered by Abhishek Jaiswal Score of 115

How to disable GPU with TensorFlow?

Using tensorflow-gpu 2.0.0rc0. I want to choose whether it uses the GPU or the CPU.

tensorflow gpu

asked by Florin Andrei Score of 36 answered by Florin Andrei Score of 63

Should a model be re-trained if new observations are available?

So, I have not been able to find any literature on this subject but it seems like something worth giving a thought: What are the best practices in model training and optimization if new observations …

machine-learning predictive-modeling optimization training

asked by yad Score of 60 answered by Hima Varsha Score of 30

How to use the output of GridSearch?

I’m currently working with Python and Scikit learn for classification purposes, and doing some reading around GridSearch I thought this was a great way for optimising my estimator parameters to get …

machine-learning cross-validation

asked by Dan Carter Score of 36 answered by Dan Carter Score of 44

Can you answer these questions?

In WGAN paper, why does clipping weights approximate Lipschitz function?

In Wasserstein GAN, it’s explained that maximizing a certain formula over a set of K-Lipschitz functions approximates the 1-Wasserstein distance and they model the functions as NNs. That much I …

neural-network gan mathematics distance

asked by znb Score of 1

A French version of Rebel

Is there an end-to-end trained transformer like Rebel for french data? Rebel can extract entities and relations from text, yet as far as I know, it works only with english texts. Is there any other …

nlp transformer knowledge-base knowledge-graph

asked by Eshrak Score of 1