Jindřich's user avatar
Jindřich's user avatar
Jindřich's user avatar
Jindřich
  • Member for 4 years, 10 months
  • Last seen more than a month ago
10 votes

Overfitting with text classification using Transformers

8 votes
Accepted

Does BERT use GLoVE?

5 votes

How are Q, K, and V Vectors Trained in a Transformer Self-Attention?

5 votes

BERT vs GPT architectural, conceptual and implemetational differences

4 votes

What are good toy problems for testing Transformer architectures?

3 votes

Transformer seq2seq model and loading embeddings from XLM-RoBERTa

3 votes

What is the advantage of positional encoding over one hot encoding in a transformer model?

3 votes
Accepted

Transformer masking during training or inference?

3 votes

How to interpret the value of categorical cross entropy?

3 votes

Why is it convolutional 1D is sometimes better and faster that LSTM at classification and predicting tasks?

3 votes
Accepted

Optimal batch size and number of epoch for BERT

2 votes

What does Embeddings Array Represent in BERT's Feature Extraction?

2 votes
Accepted

BERT minimal batch size

2 votes
Accepted

use the same gradient to maximize one part of the model and minimize another part of the same model

2 votes
Accepted

Smart sentence segmentation not splitting on abbreviations

2 votes
Accepted

Context Based Embeddings vs character based embeddings vs word based embeddings

2 votes

SpaCy string store

2 votes
Accepted

Does BERT need supervised data only when fine-tuning?

2 votes
Accepted

What are the differences between bert embedding and flair embedding

2 votes

How does T5 model work on input and target data while transfer learning?

2 votes

What happens when the length of input is shorter than length of output in transformer architecture?

2 votes
Accepted

Attention mechanism in Tensorflow 2

2 votes

What are the elements in a BERT word embedding?

2 votes

Splitting into multiple heads -- multihead self attention

2 votes

Transformer-based architectures for regression tasks

1 vote
Accepted

What are the merges and vocab files used for in BERT-based models?

1 vote

Next sentence prediction in RoBERTa

1 vote
Accepted

How to use unigram and bigram as an feature on SVM or logistic regression

1 vote

Is there any way to calculate a relevance score between a title and the content of a text?

1 vote
Accepted

How to understand Inconsistent and ambiguous dimensions of matrices used in the Attention layer?