Stack Overflow
Stack Overflow

Questions tagged [seq2seq]

Seq2Seq is a sequence to sequence learning add-on for the python deep learning library.

318 questions
0
votes
1 answer

Word2Vec with POS not producing expected results?

I am trying to gauge the impact of part of speech information with Word2Vec embeddings but am not obtaining expected results. I expected POS included word2vec embeddings to perform better in a machine translation task but it is actually performing…
Andrew Xia
  • 365
  • 1
  • 11
0
votes
1 answer

Getting ValueError: setting an array element with a sequence when passing gensim.word2vec to feed_dict

I am creating a seq2seq model with tensorflow(not Keras) and the input /output are sentences. Something like a chatbot or translator. But when I run for epoch in range(total_epoch): _, loss = sess.run([optimizer, cost], …
that_random_guy
  • 25
  • 1
  • 2
0
votes
1 answer

How to load a Seq2Seq Model and use it?

I have built a basic Chatbot using Seq2Seq model. The bot works great when I run the code in sequence in my notebook - i.e Build the model --> Train the model --> Test the model. I now want to save the model after training, load the model and then…
Sunil
  • 1
  • 1
0
votes
1 answer

Is it okay to compare Test BLEU score between NMT models while using a slightly modified standard test sets?

I am using tst2013.en found here, as my test sets to get the Test BLEU score to compare to other previous models. However, I have to filter out some sentences that are longer than 100 words otherwise I won't have the resource to run the model. But…
Minh Ung
  • 13
  • 5
0
votes
1 answer

How to use BLEU score to compare your model to existing models?

So I am using the BLEU score metric to compare my NMT model's performance with existing models. However, I'm wondering how many settings do I have to match with the other models. Settings like dev sets, test sets and hyperparameters I think are…
Minh Ung
  • 13
  • 5
0
votes
1 answer

How do I use Pytorch's "tanslation with a seq2seq" using my own inputs?

I am following the guide here Currently this is the model: SOS_token = 0 EOS_token = 1 class Lang: def __init__(self, name): self.name = name self.word2index = {} self.word2count = {} self.index2word = {0:…
new_one
  • 105
  • 1
  • 11
0
votes
1 answer

Tensorflow seq2seq regression model

I have simple seq2seq model for predicting stock prices.I have create an encoder of lstm cells and decoder which will predict the next 5 timesteps values.But it throws error: ValueError: Dimensions must be equal, but are 517 and 562 for…
Marios Nikolaou
  • 1,326
  • 1
  • 13
  • 24
0
votes
1 answer

keras lstm-seq2seq-chatbot. Training not working and predict someting wrong. I get the same reply whatever i input

I have built a chatbot based seq2seq.The coupus i used is movie dialogs from https://github.com/Conchylicultor/DeepQA/tree/master/data/cornell About 20000 corpus i used to train my model. After 300 epochs, the loss is about 0.02.But finally when i…
Constantinechiae
  • 21
  • 4
0
votes
1 answer

Dimensions for Keras RNN encoder-decoder architecture output

I've been unable to figure out the dimensions for an RNN encoder-decoder architecture. I understand how LSTMs work, but I am struggling to implement this one in Keras. After looking at the documentation and reading Q&As, it looks like the dimensions…
Jake
  • 61
  • 1
  • 4
0
votes
2 answers

How to control the author’s point of view in natural language generation models?

I am new to Natural Language Generation and I am currently in the experimentation phase. The motivating use-case is to generate one-sentence captions for images, but my question/problem is not unique to my current NLG use-case alone. The first…
Charles Walsh
  • 1
0
votes
1 answer

Seq2Seq in Keras for prediction the next element of a sequence of vectors

Excuse me. I am a beginner in neural networks. I have to use seq2seq model in Keras for prediction the next element x[N] of a sequence of vectors x[0], x[1], ..., x[N-1]. This sequence of vectors has variable length, that is, N is not fixed number.…
acshi610
  • 1
0
votes
1 answer

Bleu Score in Model Evaluation Metric

In many seq2seq implementations, I saw that they use accuracy metric in compiling the model and Bleu score only in predictions. Why they don't use Bleu score in training to be more efficient? if I understand correctly!
userInThisWorld
  • 1,361
  • 4
  • 18
  • 35
0
votes
0 answers

how to use seq2seq to decode concatenated string

Am trying to decode a concatenated String like below ... SQCB7A750BATWE SQ CB 7 A 750 B A T WE PT05A1219PY023 PT 05 A 12 19 P Y 023 PT55A1019PX02 PT 55 A 10 19 P X 02 PT33SE2215SW023 PT 33 SE 22 15 S W 023 PT05A2216PW023(LC) PT 05 A…
Exorcismus
  • 2,243
  • 1
  • 35
  • 68
0
votes
0 answers

decompose text into multi-class

am looking for a machine learning algorithm which serves as String decoder (Multi-label classifier). for example , decompose an email xyz@qwe.abc.com into different classes with/out…
Exorcismus
  • 2,243
  • 1
  • 35
  • 68
0
votes
1 answer

Is there a way to control the output length of a sequence to sequence text summarization model?

Is there a way to control the number of words or characters that a seq2seq model for text summarization produces? Examples: "My dog is the fastest dog in the world. He loves cuddling as well." 1 output: My dog is fast and loves cuddling. 2 output:…
Любомир Борисов
  • 49
  • 1
  • 1
  • 7
1 2 3
…
21 22