Questions tagged [sequence-to-sequence]
The sequence-to-sequence tag has no usage guidance.
57
questions
1
vote
0answers
20 views
SymbolicException: Inputs to eager execution function cannot be Keras symbolic tensors
I am writing Encoder-Decoder architecture with Bahdanau Attention using tf.keras with TensorFlow 2.0. Below is my code This is working with TensorFlow 1.15 but getting the error in 2.0. you can check ...
1
vote
1answer
26 views
How can I feed BERT to neural machine translation?
I am trying to feed the input and target sentences to nmt model, I am trying to use BERT ...
0
votes
0answers
15 views
Weight matrices in transformers
I am trying to understand the transformer architecture.
I am aware that the encoder/decoder contains multiple stacked self attention layers. Further each layer contains multiple heads. For example ...
1
vote
1answer
19 views
Any good Implementations of Bi-LSTM bahdanau attention in Keras?
From past few weeks I'm trying to learn sequence to sequence machine translation modelling but I couldn't find any good examples/tutorials with bahdanau attention implemented. I did come across a ton ...
0
votes
0answers
8 views
Output of a seq2seq network
I've created a seq2seq lstm that uses word embeddings, following the tutorial in tutorial , but I'm having some problems understanding the output, which is along these lines:
...
1
vote
0answers
20 views
Improving Performance of LSTM for time series prediction
My data consists of two features and a set of time series data labeled as "bookings". I have 1056 data point in the times series, for which I have two features for each. The data size is 1056x3.
My ...
0
votes
0answers
42 views
Adapting Pytorch tutorial “NMT from Scratch…” for dynamic RNN
I have taken the code from the tutorial and attempted to modify it to include bi-directionality and any arbitrary numbers of layers for GRU.
Link to the tutorial which uses uni-directional, single ...
0
votes
0answers
18 views
two different attention methods for seq2seq
I see two different ways of applying attention in seq2seq:
(a) the context vector (the weighted sum of encoder hidden states) fed into the output softmax, as shown in the diagram below. The diagram ...
0
votes
0answers
43 views
Neural Network for text generation
I'm new into ML and NN and I would like to figure out what is the best way to solve this (initially little) problem.
Suppose i have a {number} in input and i want as output the phrase "The number in ...
0
votes
0answers
19 views
What's the meaning of having a UNK token for out of vocabulary words during decoding?
Adding a UNK token to the vocabulary is a conventional way to handle oov works in tasks of NLP. It is totally understandable to have it for encoding, but what's the ...
1
vote
0answers
8 views
How to create a seq2seq without specifying a fixed decoder length?
Based on the model presented in this answer:
...
0
votes
0answers
27 views
Scheduled Sampling in Keras
Im wondering how scheduled sampling (maybe together with curriculum learning) as described in this paper [https://arxiv.org/abs/1506.03099] could be implemented in keras.
Lets assume a simple ...
0
votes
1answer
22 views
How can I build a seq2seq model , which is topic aware
I have developed a chatbot, which is basically a seq2seq LSTM network. Which can generate text based on input text. But the problem I am having right now is it is not topic aware.
As an example :
...
0
votes
1answer
6 views
Confusion about Decoder labels for training seq-to-seq models
So in seq-to-seq models for say NMT, the decoder is a sequence model for the right-shifted intended output. My question is, during training, are the inputs and outputs of the decoder supposed to be ...
1
vote
0answers
89 views
Why isnt my seq2seq model reconising what the <END> tag is?
I am making a seq2seq chatbot with the help of this guide: https://medium.com/predict/creating-a-chatbot-from-scratch-using-keras-and-tensorflow-59e8fc76be79 . I set up the model and data processing ...
0
votes
0answers
11 views
Encoding numbers and words
I am fairly new to seq2seq models in nlp and just really learned about them. Anyway, in many of the examples, I have seen there has been to approaches to providing a model with data. One in which is ...
0
votes
0answers
62 views
Test case generation from user stories using NLP and NLG
I have an existing database with User stories (with multiple text fields like Description with Use cases, acceptance criteria etc) and corresponding test cases with steps for each test case.
I am ...
0
votes
0answers
24 views
Which algorithm to use for path to prescription?
I am working on a business problem in the commercial pharma industry. In the pharma industry, we have medical representatives (Reps) selling drugs to health care providers (HCPs). They frequently ...
0
votes
0answers
53 views
Error propagation in Time series forecast with many-to-many multi-steps RNN/LSTM
I am trying to do a many-to-many time series forecast, which features an encoder-decoder model to predict with variable input and fixed prediction period. In my case, I want to predict for the future ...
0
votes
0answers
15 views
Deep Learning - Predict the relative order of data
I am facing a problem in which i want to predict the order of data. I was searching for research papers, however i do not know how this problem is named in academia.
I encountered the following well ...
0
votes
1answer
33 views
Seq2Seq Model training: Encoder vs. Decoder
Can someone point me to an article which explains how the model training is done in Seq2Seq? I know "Teacher Forcing" is used but what I found so far hasn't been detailed enough. What I am most ...
1
vote
1answer
1k views
IndexError: list index out of range
I'm implementing a sequence-2-sequence model with RNN-VAE architecture, and I use an attention mechanism. I have problem in the decoder part.
I'm struggling with this error: IndexError: list index ...
0
votes
0answers
123 views
ValueError: Dimensions must be equal, but are 256 and 12 for 'attention_layer/MatMul_1' (op: 'MatMul') with input shapes: [?,256], [12,256]
I'm working on a sequence-to-sequence approach using LSTM and a VAE with an attention mechanism.
...
0
votes
0answers
427 views
ValueError: Cannot convert a partially known TensorShape to a Tensor: (?, 256)
I'm working on a sequence to sequence approach using LSTM and a VAE with an attention mechanism.
...
0
votes
0answers
19 views
Strategy for “forcing” number of labels in seq2seq predictions with Keras?
I'm trying to train a seq2seq model that for every timestep in a given timeseries sample will output 1 of 6 possible labels.
Furthermore, the training data is constructed in such a way that
Each ...
0
votes
0answers
33 views
What encoding to use for my musical vectors?
I'm trying to build a music recommendations system using an encoder-decoder sequence-to-sequence architecture using keras. My dataset comprises of playlists containing songs represented as a 13-...
2
votes
1answer
50 views
Working ofLSTM with multiple Units - NER
I am trying to understand working of LSTM networks and kind of not clear about how different neurons in a cell interact each other. I had a look at a similar question, but still not clear about few ...
0
votes
0answers
172 views
Seq2seq model that gets as input a sentence and outputs the same sentence
I tried to implement a model that takes as input sentences, which are hate_tweets and outputs exactly the same sentences. For this reason, I gave Input to the encoder and decoder exactly the same ...
0
votes
0answers
79 views
Using VAE with Sequence to Sequence Approach
In the code below, I'm using a VAE with a seq-to-seq approach for translation. At the beginning I sarted only by using a simple seq-to-seq approach which implements a RNN-AE, until this step I had not ...
1
vote
0answers
22 views
Adding context in a sequence to sequence problem
The encoder of a seq2seq model is meant to generate a conditioning context for the decoder, as mentioned here
A RNN layer (or stack thereof) acts as "encoder": it processes the input sequence and ...
3
votes
1answer
1k views
One-hot encode multi-class multi-label sequences
Suppose I want to build a timeseries where each timestep is represented by a categorical array: the encoded sequences look like [[2, 0, 5],[3, 1, 4],..] and each ...
1
vote
0answers
23 views
Initialising states in a multilayer sequence to sequence model
With a sequence to sequence model where the enocoder and decoder are both comprised of one layer each, the initial state of the decoder is initialised to use the final states of the encoder layer.
In ...
1
vote
0answers
78 views
What should the size of the decoder output be in a sequence to sequence model
In a sequence to sequence model, a lot of the tutorials I have read state that the decoder target length should be the same as the encoder input length (https://blog.keras.io/building-autoencoders-in-...
2
votes
1answer
5k views
How to determine feature importance in a neural network?
I have a neural network to solve a time series forecasting problem. It is a sequence-to-sequence neural network and currently it is trained on samples each with ten features. The performance of the ...
2
votes
0answers
479 views
Recommended model for univariate or multivariate multistep ahead time series forecasting
I have a dataset consisting of recurring and non-recurring expense transactions from bank accounts, as well as other features describing the bank account and each transation. I aggregate these ...
1
vote
1answer
1k views
Predicting next number in a sequence - data analysis
I am a machine learning newbie and I am working on a project where I'm given a sequence of integers all of which are in the range 0 to 70. My goal is to predict the next integer in the sequence given ...
2
votes
2answers
3k views
Does this encoder-decoder LSTM make sense for time series sequence to sequence?
TASK
given $\vec x = [x_{t=-3}, x_{t=-2}, x_{t=-1}, x_{t=0}]$
predict $\vec y = [x_{t=1}, x_{t=2}]$
Whith an LSTM encoder-decoder (seq2seq)
MODEL
NOTE: the ? symbol in the shape of the tensors ...
3
votes
0answers
1k views
Why does Position Embeddings work?
In the papers "Convolutional Sequence to Sequence Learning" and
"Attention Is All You Need", positions embeddings are simply added to the input words embeddings to give the model a sense of the order ...
1
vote
1answer
363 views
Give Variable Length input to LSTM
My input data consist of list of list. Both list have dynamic length for every example like below.
...
0
votes
1answer
41 views
What type of neural network could emulate a binary to HTML conversion tool?
I've got a problem, which I thought could be solved by using a neural network:
I've got a binary file and a tool that converts that file into a readable html file (probably a text file as well). How ...
1
vote
1answer
43 views
Can Sequence to sequence models be used to convert code from one programming language to another?
Is it possible to convert a code from one language to another using sequence to sequence programming. if not sequence to sequence, which algorithm can i use to do this?
3
votes
3answers
118 views
Predict output sequence one at a time with feedback
I would like to solve the following classification problem: Given an input sequence and zero or more initial terms of the true output, predict the next term in the output sequence.
For example, my ...
3
votes
2answers
311 views
Is this a problem for a Seq2Seq model?
I'm struggling to find a tutorial/example which covers using an seq2seq model for sequential inputs other then text/translation.
I have a multivariate dataset with n number of input variables each ...
2
votes
0answers
105 views
Encoder-Decoder Sequence-to-Sequence Model for Translations in Both Directions
Is it possible to use a pre-trained sequence to sequence encoder-decoder model which translates an input text in source language to an output in target language to do an inverse translation? That is, ...
1
vote
0answers
58 views
On-the-fly seq2seq: starting translation before the input sequence ends
By now anybody even remotely familiar with RNNs has been exposed to the famous figure representing variants of such networks:
However one type that is missing is one where there would be a partial ...
1
vote
0answers
232 views
Neural network outputting same result for all inputs
I'm building an encoder-decoder neural network in Keras for sequence generation. The specific task is to try and change the styles of the text.
Both my encoder and decoders are LSTMs with latent ...
2
votes
1answer
174 views
Keras: Softmax output into embedding layer
I'm trying to build an encoder-decoder network in Keras to generate a sentence of a particular style. As my problem is unsupervised i.e. I don't have the ground truths for the generated sentences, I ...
1
vote
2answers
153 views
What are the benefits and tradeoffs of a 1D conv vs a multi-input seq2seq LSTM model?
I have 6 sequences, s1,..,s6. Using all sequences I want to predict a binary vector q = [0,0,0,1,1,1,0,0,0,1,1,1,...], which is a mask of the activity of the 6 sequences.
I have looked at seq2seq ...
2
votes
1answer
138 views
Training Encoder-Decoder using Decoder Outputs
I am trying to build an encoder-decoder model for a text style transfer problem. The problem is I don't have parallel data between the two styles so I need to train the model in an unsupervised ...
0
votes
1answer
520 views
Do we really need `<unk>` tokens?
I am wondering, do we really need <unk> tokens?
Why do we limit our vocabulary?
Is it for speed? Accuracy?
If we disable all limitations, what do you ...
