This repo collects and re-produces models related to domains of question answering and machine reading comprehension
WikiQA, TrecQA, InsuranceQA
run preprocess_wiki.ipynb
This model is a simple complementation of a Siamese NN QA model with a pointwise way.
python siamese.py --train --model NN
python siamese.py --test --model NN
This model is a simple complementation of a Siamese CNN QA model with a pointwise way.
python siamese.py --train --model CNN
python siamese.py --test --model CNN
This model is a simple complementation of a Siamese RNN/LSTM/GRU QA model with a pointwise way.
python siamese.py --train --model RNN
python siamese.py --test --model RNN
All these three models above are based on the vanilla siamese structure. You can easily combine these basic deep learning module cells together and build your own models.
Given a question, a positive answer and a negative answer, this pairwise model can rank two answers with higher ranking in terms of the right answer.
python qacnn.py --train
python qacnn.py --test
To be done
CNN/Daily mail, CBT
To be done
To be done
To be done
SQuAD, MS MARCO
To be done
RACE dataset
For more information, please visit http://skyhigh233.com/blog/2018/04/26/cqa-intro/.