Hi,
I recently started to deal with neural networks. I read about recurrent neural networks and convolutional neural networks. Is there anyone who can tell me which one (or the combination of both) is better suited for a question-answering system (more concretely for text classification)? Does someone have experience in this field or even publications?
Thanks a lot for your help.
- S
Dear Sara,
As far i know, CNN is a good classification model such as image or signal processing and RNN is good for prediction such as time series problems. But, RNN can be applied for classification too.
Question-answering is like predicting the suitable answer. So, RNN would be better.
Best Regards,
Dear Prof. D'Onofrio,
I just read your question and thought the following reference might be interesting for you:
https://cs224d.stanford.edu/reports/StrohMathur.pdf
As suggested in the previous answer by Prof. Mirrashid, it makes use of deep learning in question-answering.
Yours sincerely,
Rainer
Refer this IEEE article:
Natural language neural network and its application to question-answering system
Conference Paper Natural language neural network and its application to quest...
- Badges
- Science topic