Questions tagged [seq2seq]
For questions related to sequence-to-sequence (seq2seq) machine learning models/architectures, used e.g. in machine translation.
18
questions
1
vote
0
answers
30
views
How to Train a Decoder for Pre-trained BERT Transformer-Encoder?
Context:
I am currently working on an encoder-decoder sequence to sequence model that uses a sequence of word embeddings as input and output, and then reduces the dimensionality of the word embeddings....
- 11
0
votes
0
answers
64
views
Why are separate, bigger Encoder-Decoder architectures used instead of Bidirectional RNNs/Transformers for Seq2Seq tasks?
Whether with RNNs or Transformers, Encoder-Decoder networks are used for Sequence to Sequence (Seq2Seq) tasks, like Machine Translation.
Why are separate, bigger Encoder-Decoder networks used for this ...
- 286
1
vote
0
answers
29
views
When training a seq2seq model is it better to train using the models outputs or expected outputs?
When training any seq2seq model you have a target and a source. The source may be a sentence ...
- 1,266
1
vote
1
answer
42
views
Does Seq2Seq decoder take a special vector or the weights of the last encoder cell as an output?
I'm reading Sequence to Sequence Learning with Neural Networks and there's a thing that I couldn't quite grasp.
Paper says the encoder outputs a vector to be fed to the decoder. More precisely
Our ...
- 145
1
vote
2
answers
255
views
Is seq2seq the best model when input/output sequences have fixed length?
I understand that seq2seq models are perfectly suitable when the input and/or the output have variable lengths. However, if we know exactly the input/output sequence lengths of the neural network. Is ...
- 11
1
vote
0
answers
110
views
What is the best way to generate German paraphrases?
What is the best method to generate German paraphrases? The state-of-the-art are seq2seq transformer models, like T5, but they only work for English sentences. I found the multilingual MT5 model, but ...
- 11
3
votes
1
answer
71
views
Can Reinforcement Learning be used to generate sequences?
Can we use reinforcement learning for sequence-to-sequence tasks? If yes, whether or not this is a good choice, how could this be done?
2
votes
0
answers
27
views
Are there any successful applications of transformers of small size (<10k weights)?
In the problems of NLP and sequence modeling, the Transformer architectures based on the self-attention mechanism (proposed in Attention Is All You Need) have achieved impressive results and now are ...
- 1,894
1
vote
0
answers
29
views
Training seq2seq translation model with one source and multiple target
So basically I'm training a sequence to sequence model that translates English sentences to Arabic sentences. I'm using the data provided by Anki @ manythings. I realized that some of the sentences in ...
- 11
0
votes
1
answer
362
views
Seq2Seq model produces repeating words
My framework is an encoder-decoder (LSTM-to-LSTM) model, similar to this post. The model basically reads a sentence and generate another sentence. But, the thing is, after a few epochs training, the ...
3
votes
0
answers
64
views
What is the difference between zero-padding and character-padding in Recurrent Neural Networks?
For RNN's to work efficiently, we vectorize the operations, which results in an input matrix of shape
(m, max_seq_len)
where m ...
- 31
4
votes
1
answer
974
views
What's the difference between content-based attention and dot-product attention?
I'm following this blog post which enumerates the various types of attention.
It mentions content-based attention where the alignment scoring function for the $j$th encoder hidden state with respect ...
- 1,169
2
votes
1
answer
336
views
How is Google Translate able to convert texts of different lengths?
According to my experience with Tensorflow and many other frameworks, neural networks have to have a fixed shape for any output, but how does Google translate convert texts of different lengths?
- 49
1
vote
0
answers
125
views
SeqGAN - Policy gradient objective function interpretation
Could someone clear my doubt on the loss function used in SeqGAN paper . The paper uses policy gradient method to train the generator which is a recurrent neural network here.
Have I interpreted the ...
- 111
2
votes
0
answers
860
views
What is the time complexity of the forward pass and back-propagation of the sequence-to-sequence model with and without attention?
I keep looking through the literature, but can't seem to find any information regarding the time complexity of the forward pass and back-propagation of the sequence-to-sequence RNN encoder-decoder ...
- 53
1
vote
1
answer
605
views
Do Seq2Seq models and the Bidirectional RNN do the same thing?
It seems to me that Seq2Seq models and Bidirectional RNNs try to do the same thing. Is that true?
Also, when would you recommend one setup over another?
- 51
9
votes
4
answers
13k
views
What exactly is a hidden state in an LSTM and RNN?
I'm working on a project, where we use an encoder-decoder architecture. We decided to use an LSTM for both the encoder and decoder due to its hidden states. In my specific case, the hidden state of ...
- 627
1
vote
1
answer
88
views
Why feeding the correct output as input during training of seq2seq models?
I've read about seq2seq for time-series and it seemed really promising, but, when I went to implement it, all the tutorials I've found use the correct output as input to the decoder phase during ...
