/Semantic-Hashing-Models

source code of baselines for paper "Refining BERT Embeddings for Document Hashing via Mutual Information Maximization"

Primary LanguagePythonMIT LicenseMIT

Semantic Hashing models

This repo contains six well-known semantic hashing models: VDSH, NASH, BMSH, WISH, AMMI, and corrSH.

Datasets

Please download the data from here and move them into the ./data/ directory.

How to Run

Unsupervised document hashing on 20Newsgroups using 64 bits

python main.py ng64 data/ng20.tfidf.mat --train --cuda