Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/white127/QA-deep-learning
tensorflow and theano cnn code for insurance QA(question Answer matching)
https://github.com/white127/QA-deep-learning
Last synced: 4 months ago
JSON representation
tensorflow and theano cnn code for insurance QA(question Answer matching)
- Host: GitHub
- URL: https://github.com/white127/QA-deep-learning
- Owner: white127
- Created: 2016-06-02T01:00:34.000Z (over 8 years ago)
- Default Branch: master
- Last Pushed: 2018-09-07T03:40:34.000Z (over 6 years ago)
- Last Synced: 2024-08-01T16:41:46.619Z (7 months ago)
- Language: Python
- Size: 13.8 MB
- Stars: 532
- Watchers: 38
- Forks: 285
- Open Issues: 25
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
Insurance-QA deeplearning model
======
This is a repo for Q&A Mathing, includes some deep learning models, such as CNN、RNN.
1. CNN. Basic CNN model from 《Applying Deep Learning To Answer Selection: A Study And An Open Task》
2. RNN. RNN seems the best model on Insurance-QA dataset.
3. SWEM. SWEM is the fastest, and has good effect on other datasets, such as WikiQA ..., but is seems not so good on Insurance-QA dataset. I think that, SWEM is more suitable for Q&Q matching, not Q&A matching.
It's hard to say which model is the best in other datasets, you have to choose the most suitable model for you.
More models are on the way, pay attention to the updates.
## Requirements
1. tensorflow 1.4.0
2. python3.5
## Performance
margin loss version
Model/Score | Ins_qa_top1_precision | quora_best_prec
------------ | ------------- | -------------
CNN | 62% | None
LSTM+CNN | 68% | None
SWEM | <55% | None
logloss version
Model/Score | Insqa_top1_precision | quora_best_prec
------------ | ------------- | -------------
CNN | None | 79.60%
LSTM+CNN | None | None
SWEM | <40% | 82.69%
## Running
Change configuration to your own environment, just like data pathes
vim config.py
Data processing
python3 gen.py
Run CNN model
cd ./cnn/tensorflow && python3 insqa_train.py
It will take few hours(thousands of epoches) to train this model on a single GPU.
## Downloads
1. You can get Insurance-QA data from here https://github.com/shuzi/insuranceQA
2. You can get Quora data from here http://qim.ec.quoracdn.net/quora_duplicate_questions.tsv
## Links
1. CNN and RNN textual classification repo https://github.com/white127/TextClassification_CNN_RNN
2. 《Applying Deep Learning To Answer Selection: A Study And An Open Task》