erogol / QuoraDQBaseline

Baseline solution to Quora Duplicate Question dataset.

This is a solution to Quora Duplicate Question dataset and folow up to the blog post

Available Scripts & Related Codes:

• 1_spacy_glove.py (Computes accuracy on similar domain dataset) (python3 1_spacy_glove.py) Note:Runs with python3

• 2_tf_idf_vec.py (Computes accuracy on similar domain dataset) (python3 2_tf_idf_vec.py) Note:Runs with python3

• 3_word2vec_train.py (Computes accuracy on similar domain dataset) (python 3_word2vec_train.py) Note:Runs with python

• 4_tf_idf_vec_multidomain.py (Computes accuracy on multi-domain domain dataset) (python3 4_tf_idf_vec_multidomain.py) Note:Runs with python3