Data Science Stack Exchange is a question and answer site for Data science professionals, Machine Learning specialists, and those interested in learning more about the field. It only takes a minute to sign up.

Sign up to join this community

Anybody can ask a question

Anybody can answer

The best answers are voted up and rise to the top

Explore our Questions

Ask Question

more tags

Active 4 Bountied Hot Week Month

1

vote

1

answer

17

views

What is the difference between BERT architecture and vanilla Transformer architecture

nlp bert transformer encoder

answered 53 mins ago Allohvk 131

0

votes

0

answers

9

views

Using bert (or fitbert) for predicting masked words from word candidates

nlp word-embeddings bert

asked 12 hours ago Bilinual 1

0

votes

1

answer

20

views

Why does gpu speed up inference?

nlp cnn gpu

modified 18 hours ago desertnaut 1,176

2

votes

1

answer

59

views

How to compute unseen bi-grams in a corpus (for Good-Turing Smoothing)

nlp

modified yesterday Community♦ 1

3

votes

1

answer

204

views

What are the rules when extracting SVO triples from preprocessed text?

python nlp text-mining feature-extraction

answered yesterday Brian Spiering 10k

11

votes

1

answer

371

views

ngram and RNN prediction rate wrt word index

neural-network nlp statistics rnn ngrams

modified yesterday Community♦ 1

7

votes

2

answers

7k

views

Increasing SpaCy max NLP limit

python nlp

modified yesterday Davide Fiocco 415

0

votes

1

answer

54

views

When one model is superior in real world use?

neural-network keras nlp

modified 2 days ago Community♦ 1

1

vote

1

answer

128

views

The memorisation capacity of an LSTM (real numbers)

nlp lstm

modified 2 days ago Community♦ 1

0

votes

0

answers

11

views

k-means for customer review analysis

python nlp k-means sentiment-analysis

asked 2 days ago Pari Ganjoo 25

2

votes

1

answer

85

views

Automatic topic labelling for topic modelling

machine-learning nlp topic-model python-3.x

modified Nov 26 at 22:06 Community♦ 1

2

votes

2

answers

76

views

In sequence models, is it possible to have training batches with different timesteps each to reduce the required padding per input sequence?

keras tensorflow nlp sequence mini-batch-gradient-descent

modified Nov 26 at 20:00 ncasas 8,151

12

votes

3

answers

542

views

How does attention mechanism learn?

neural-network deep-learning nlp attention-mechanism

modified Nov 26 at 18:27 Allohvk 131

0

votes

1

answer

49

views

What model is recommended: I am using text features in a regression and want to interpret coefficients

machine-learning nlp regression model-selection

modified Nov 26 at 3:07 Community♦ 1

Browse more Questions

Data Science Stack Exchange works best with JavaScript enabled