Source code, datasets and experimental results for submission "Deep Entity Matching with Adversarial Active Learning".
- Python 3.8
- Python libraries: see requirements.txt
- Dataset and pre-trained word embeddings: please use
download.sh
to download
Datasets (from DeepMatcher)
We evaluate DAEM on seven benchmark datasets.
File | Description |
---|---|
daem | Code of DAEM |
scripts/entity_matching.py | Code to reproduce the deep entity matching experiment and ablation study |
scripts/adversarial_active_learning.py | Code to reproduce the active entity matching experiment |
scripts/inter_attribute_completion.py | Code to reproduce the inter-attribute completion experiment |
scripts/adversarial_learning.py | Code to reproduce the adversarial learning experiment |
scripts/entity_signature.py | Code to reproduce the entity signature experiment |
scripts/dynamic_blocking.py | Code to reproduce the dynamic blocking experiment |