https://github.com/tshu-w/ember
Code and data for the paper "Bridging the Gap between Reality and Ideality of Entity Matching: A Revisiting and Benchmark Re-Construction" (IJCAI 2022)
https://github.com/tshu-w/ember
benchmark entity-matching entity-resolution ijcai2022
Last synced: 7 days ago
JSON representation
Code and data for the paper "Bridging the Gap between Reality and Ideality of Entity Matching: A Revisiting and Benchmark Re-Construction" (IJCAI 2022)
- Host: GitHub
- URL: https://github.com/tshu-w/ember
- Owner: tshu-w
- Created: 2021-07-28T11:34:49.000Z (over 4 years ago)
- Default Branch: main
- Last Pushed: 2025-07-22T08:19:09.000Z (6 months ago)
- Last Synced: 2025-10-13T03:34:34.440Z (3 months ago)
- Topics: benchmark, entity-matching, entity-resolution, ijcai2022
- Language: Python
- Homepage: https://tshu-w.github.io/ember/
- Size: 29.8 MB
- Stars: 6
- Watchers: 1
- Forks: 2
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- Citation: CITATION.bib
Awesome Lists containing this project
README
Bridging the Gap between Reality and Ideality of Entity Matching:
A Revisiting and Benchmark Re-Construction
## Description
Code and data for the paper:
*Bridging the Gap between Reality and Ideality of Entity Matching: A Revisiting and Benchmark Re-Construction*
## Data
Details of the released data can be found in the [REAME](./data/ali/README.md) of the data.
## How to run
First, install dependencies
```console
# clone project
git clone https://github.com/tshu-w/EMBer
cd EMBer
# [SUGGESTED] use conda environment
conda env create -n ember -f environment.yaml
conda activate ember
# [ALTERNATIVE] install requirements directly
pip install -r requirements.txt
```
Next, to obtain the main results of the paper:
```console
bash scripts/download_images.sh
python scripts/run_ali.py --gpus 0 1 2 3
python scripts/test_ali.py --gpus 0 1 2 3
python scripts/run_dm_ali.py --gpus 0 1 2 3
python scripts/test_dm_ali.py --gpus 0 1 2 3
python scripts/print_results results/test -k test/f1 test/prc test/rec
```
You can also run experiments with the `run` script.
```console
# fit with the TextMatcher config
./run fit --config configs/ali_tm.yaml
# or specific command line arguments
./run fit --model TextMatcher --data AliDataModule --data.batch_size 32 --trainer.gpus 0,
# evaluate with the checkpoint
./run test --config configs/ali_tm.yaml --ckpt_path ckpt_path
# get the script help
./run --help
./run fit --help
```
## Citation
```
@inproceedings{ijcai2022p0552,
title = {Bridging the Gap between Reality and Ideality of Entity Matching: A Revisiting and Benchmark Re-Construction},
author = {Wang, Tianshu and Lin, Hongyu and Fu, Cheng and Han, Xianpei and Sun, Le and Xiong, Feiyu and Chen, Hui and Lu, Minlong and Zhu, Xiuwen},
booktitle = {Proceedings of the Thirty-First International Joint Conference on
Artificial Intelligence, {IJCAI-22}},
publisher = {International Joint Conferences on Artificial Intelligence Organization},
editor = {Lud De Raedt},
pages = {3978--3984},
year = {2022},
month = {7},
note = {Main Track},
doi = {10.24963/ijcai.2022/552},
url = {https://doi.org/10.24963/ijcai.2022/552},
}
```