3
votes
How to create a language translator from scratch?
Google translate itself uses Deep learning to translate sentences which can be seen here.
You can translate sentences across languages for which you need two things :
A large dataset which has pairs ...
- 2,140
3
votes
Why is the F-measure preferred for classification tasks?
The Fı-score is preferred to simple classification accuracy in order to counter the problem of imbalanced datasets; if the thing you are looking for occurs only rarely anyway then a naive classifier ...
- 328
2
votes
How does T5 model work on input and target data while transfer learning?
T5 is in fact a sequence-to-sequence model, it has an encoder that generates some hidden states representing the input and a decoder that generates the output. When you fine-tune the model you can ...
- 1,661
1
vote
Accepted
What is the difference between batch_encode_plus() and encode_plus()
See also the huggingface documentation, but as the name suggests batch_encode_plus tokenizes a batch of (pairs of) sequences ...
- 7,087
1
vote
Generate sentences from keywords by adding formal word
I am also fairly new to this, but am working on the same type of problem where I have to predict the sentence based on previous data. Like you want giving X value predict y value.
So, basically you ...
- 111
1
vote
Generate new sentences based on keywords
This is area of NLG . You can use template based text generation techniques, wherein you have defined structure of output text and fill in required blank areas based on keywords. This technique is ...
- 884
Only top scored, non community-wiki answers of a minimum length are eligible