User alvas

70 votes

11 answers

40k views

What is dimensionality reduction? What is the difference between feature selection and extraction?

asked May 18, 2014 at 6:26

62 votes

6 answers

32k views

Latent Dirichlet Allocation vs Hierarchical Dirichlet Process

asked May 18, 2014 at 6:10

25 votes

2 answers

35k views

What does the alpha and beta hyperparameters contribute to in Latent Dirichlet allocation?

asked May 23, 2014 at 6:25

22 votes

4 answers

17k views

Dimensionality and Manifold

asked May 5, 2015 at 17:48

16 votes

5 answers

25k views

Number of epochs in Gensim Word2Vec implementation

asked Jan 17, 2016 at 13:14

15 votes

1 answer

11k views

Why do we need to add START <s> + END </s> symbols when using Recurrent Neural Nets for Sequence-to-Sequence Models?

asked Jan 23, 2018 at 9:39

14 votes

2 answers

7k views

What to do when testing data has less features than training data?

asked Nov 18, 2015 at 9:12

10 votes

1 answer

2k views

What is generative and discriminative model? How are they used in Natural Language Processing?

asked May 18, 2014 at 6:17

6 votes

3 answers

659 views

Which tribe does Probabilistic Graphical Models fall under?

asked Jul 26, 2016 at 4:21

5 votes

1 answer

10k views

How/What to initialize the hidden states in RNN sequence-to-sequence models?

asked Jan 30, 2018 at 6:30

4 votes

2 answers

355 views

How to get phrase tables from word alignments?

asked May 31, 2014 at 14:28

3 votes

5 answers

2k views

Are there any python based data visualization toolkits?

asked Jun 9, 2014 at 8:34

3 votes

3 answers

181 views

A good way to organize/store a lot of datasets

asked Jul 2, 2021 at 13:11

2 votes

0 answers

1k views

What is zero-shot vs one-short vs few-shot learning?

asked Apr 2 at 6:27

2 votes

2 answers

1k views

Dynamic batching and padding batches for NLP in deep learning libraries

asked Apr 7 at 12:05

2 votes

0 answers

34 views

How to estimate the lambda e to reweighing translation probabilities of entries in a dictionary

asked Jan 19, 2016 at 14:21

1 vote

0 answers

90 views

Minimum Error Rate Training using Powell Search for Machine Translation

asked Dec 9, 2015 at 11:29

1 vote

1 answer

3k views

How to visualize multi-instance multiclass classification?

asked Jun 12, 2017 at 6:06

1 vote

0 answers

102 views

What does NIST information weights refer to?

asked Sep 28, 2017 at 3:00

1 vote

1 answer

252 views

How to better represent three sets of categorical data?

asked Oct 24, 2017 at 1:29

0 votes

2 answers

148 views

What does the Ip mean in the Bayesian Ridge Regression formula?

asked Jul 28, 2015 at 8:53

0 votes

0 answers

17 views

How to best visualize feature-label combinations as a tree/chart/table?

asked Jul 27 at 10:42

0 votes

0 answers

33 views

How should data from closed down sites or companies be licensed?

asked Apr 2 at 5:32

0 votes

1 answer

203 views

PMI between lemma vs surface

asked Aug 8, 2018 at 6:55

Stack Exchange Network

24 Questions

What is dimensionality reduction? What is the difference between feature selection and extraction?

Latent Dirichlet Allocation vs Hierarchical Dirichlet Process

What does the alpha and beta hyperparameters contribute to in Latent Dirichlet allocation?

Dimensionality and Manifold

Number of epochs in Gensim Word2Vec implementation

Why do we need to add START <s> + END </s> symbols when using Recurrent Neural Nets for Sequence-to-Sequence Models?

What to do when testing data has less features than training data?

What is generative and discriminative model? How are they used in Natural Language Processing?

Which tribe does Probabilistic Graphical Models fall under?

How/What to initialize the hidden states in RNN sequence-to-sequence models?

How to get phrase tables from word alignments?

Are there any python based data visualization toolkits?

A good way to organize/store a lot of datasets

What is zero-shot vs one-short vs few-shot learning?

Dynamic batching and padding batches for NLP in deep learning libraries

How to estimate the lambda e to reweighing translation probabilities of entries in a dictionary

Minimum Error Rate Training using Powell Search for Machine Translation

How to visualize multi-instance multiclass classification?

What does NIST information weights refer to?

How to better represent three sets of categorical data?

What does the Ip mean in the Bayesian Ridge Regression formula?

How to best visualize feature-label combinations as a tree/chart/table?

How should data from closed down sites or companies be licensed?

PMI between lemma vs surface