mirror of https://github.com/wassname/Castor.git synced 2026-09-25 13:10:11 +08:00

T

Matt Crane 945b1fa6c0 Fix vocab caching issue (#29 )

With the line as-was the vocab cache was stored as b'the' rather than the, meaning that word2vec wasn't found for terms causing massive performance loss (AP 0.71 cf 0.77).

2017-06-19 13:02:36 -04:00

idf_baseline

Corpus idf (#23 )

2017-05-07 22:28:35 -04:00

kim_cnn

Kim cnn (#21 )

2017-04-24 15:53:36 -04:00

simple_qa_rnn

Relation prediction model from Simple QA paper (#20 )

2017-04-20 13:29:32 -04:00

sm_cnn

Fix vocab caching issue (#29 )

2017-06-19 13:02:36 -04:00

.gitignore

GPU Support for SM Model (#26 )

2017-06-02 08:47:13 -04:00

baseline_results.tsv

Ext feats bug fix (#19 )

2017-04-18 12:32:43 -04:00

README.md

Corpus idf (#23 )

2017-05-07 22:28:35 -04:00

setup.py

renaming sm_model; faster bridge (#18 ) (#22 )

2017-05-03 17:24:47 -04:00

README.md

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.