nlpxucan / MRFN

Tensorflow implementation for MRFN in Retrieval-based Chatbots

Multi-Representation Fusion Network (MRFN)

This is an implementation of [Multi-Representation Fusion Network for Multi-turn Response Selection in Retrieval-based Chatbots, WSDM 2019].

Requirements

• Ubuntu 16.04
• Tensorflow 1.4.0
• Python 2.7
• NumPy

Usage

To download and preprocess the data, run

# download ubuntu corpus and word/char dictionaries and pre-trained embeddings 
sh download.sh
# preprocess the data
python data_utils_record.py

All hyper parameters are stored in config.py. To train, run

python main.py --log_root=logs_ubuntu --batch_size=100

To evaluate the model, run

python evaluate.py --log_root=logs_ubuntu --batch_size=100