mirror of
https://github.com/wassname/Castor.git
synced 2026-10-07 11:13:23 +08:00
Michael Tu
4470983504
* Add TrecQA dataset and modularize MP-CNN infra * Stylistic improvements * Fix and warn about trec_eval path issue * Update README for MP-CNN * Update incorrect map/mrr * MP-CNN: address code review comments * Create common Castor pair Dataset class * Move map and mrr computation to Castor utils * Make map mrr utility trec_eval path more general
Castor
PyTorch deep learning models.
- SM model: Similarity between question and candidate answers.
Setting up PyTorch
You need Python 3.6 to use the models in this repository.
As per pytorch.org,
"Anaconda is our recommended package manager"
conda install pytorch torchvision -c soumith
Other pytorch installation modalities (e.g. via pip) can be seen at pytorch.org.
We also recommend gensim. We use some gensim modules to cache word embeddings.
conda install gensim
PyTorch has good support for GPU computations. CUDA installation guide for linux can be found here
NOTE: Install CUDA libraries before installing conda and pytorch.
data for models
Sourcing and pre-processing of input data for each model is described in respective model/README.md's
Baselines
- IDF Baseline: IDF overlap between question and candidate answers.
Tutorials
SM Model tutorial: sm_cnn/tutorial.ipynb - notebook that walks through SM CNN model, good for beginnners.