This repo collects and re-produces models related to domains of question answering and machine reading comprehension.

WikiQA, TrecQA, InsuranceQA

cd cQA
bash download.sh
python preprocess_wiki.py

This model is a simple complementation of a Siamese NN QA model with a pointwise way.

To this repo

python siamese.py --train

python siamese.py --test

This model is a simple complementation of a Siamese CNN QA model with a pointwise way.

To this repo

python siamese.py --train

python siamese.py --test

This model is a simple complementation of a Siamese RNN/LSTM/GRU QA model with a pointwise way.

To this repo

python siamese.py --train

python siamese.py --test

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.

Refer to 《APPLYING DEEP LEARNING TO ANSWER SELECTION:A STUDY AND AN OPEN TASK》

To this repo

python qacnn.py --train

python qacnn.py --test

Refer to 《A Decomposable Attention Model for Natural Language Inference》

To this repo

python decomp_att.py --train

python decomp_att.py --test

Refer to 《A COMPARE-AGGREGATE MODEL FOR MATCHING TEXT SEQUENCES》

To this repo

python seq_match_seq.py --train

python seq_match_seq.py --test

Refer to 《Bilateral Multi-Perspective Matching for Natural Language Sentence》

To this repo

python bimpm.py --train

python bimpm.py --test

CNN/Daily mail, CBT, SQuAD, MS MARCO, RACE

To be done

To be done

To be done

To be done

Refer to 《QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension》

To this repo

For more information, please visit http://skyhigh233.com/blog/2018/04/26/cqa-intro/.