HansiZeng/text-semantic-matching

Pytorch implementations of several text semantic matching models. The repository currently contains ESIM, CAFE, RE2

Python

text-semantic-matching

The repository contains several Pytorch model implementations for text semantic matching. The implemented models are as followed,

ESIM Enhanced LSTM for Natural Language Inference
CAFE Compare, Compress and Propagate: Enhancing Neural Architectures with Alignment Factorization for Natural Language Inference
RE2 Simple and Effective Text Matching with Richer Alignment Features

Data Preparation

cd setup
bash setup_snli.sh

Run Model

python train.py --model="esim" # run ESIM model
or
python train.py --model="cafe" # run CAFE model
or
python train.py --model="re2" # run RE2 model

Performance

We report the performance of ESIM, CAFE, RE2 in the SNLI dataset

Models	Accuracy
ESIM	88.325
CAFE	87.320
RE2	88.458