allanchen95 / CODE

AAAI'22-"CODE: Contrastive Pre-training with Adversarial Fine-tuning for Zero-shot Expert Linking."

Expert-Linking

Pytorch implementation of the paper "COAD: Contrastive Pre-training with Adversarial Fine-tuning for Zero-shot Expert Linking."

This is a simple online demo: https://newsminer.net/ExpertLinking/

Chinese Expert Linking Code

Requirements

• Ubuntu 16.04
• Python 3.6
• Pytorch 1.1.0
• GPU 32G

How to run

1. Downloading the dataset to correspanding code files;

• AMiner;
• News, passwd: s0k2;
• LinkedIn, passwd: df2j

2. Changing the data-file-path;
3. Running the main function.

Note: We will carefully reorganize the github page after paper-reviewing.