eznlp
is a PyTorch
-based package for neural natural language processing, currently supporting the following tasks:
- Text Classification (Experimental Results)
- Named Entity Recognition (Experimental Results)
- Sequence Tagging
- Span Classification
- Boundary Selection
- Relation Extraction (Experimental Results)
- Attribute Extraction
- Machine Translation
- Image Captioning
This repository also maintains the code of our papers:
- Check this link for "Boundary Smoothing for Named Entity Recognition" accepted to ACL 2022 main conference.
$ pip install eznlp
$ python setup.py sdist
$ pip install dist/eznlp-<version>.tar.gz
$ python scripts/text_classification.py --dataset <dataset> [options]
$ python scripts/entity_recognition.py --dataset <dataset> [options]
$ python scripts/relation_extraction.py --dataset <dataset> [options]
$ python scripts/attribute_extraction.py --dataset <dataset> [options]
If you find our code useful, please cite the following papers:
@inproceedings{zhu2022boundary,
title={Boundary Smoothing for Named Entity Recognition},
author={Zhu, Enwei and Li, Jinpeng},
booktitle={Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics},
year={2022},
publisher={Association for Computational Linguistics},
}
@article{zhu2021framework,
title={A Unified Framework of Medical Information Annotation and Extraction for {Chinese} Clinical Text},
author={Zhu, Enwei and Sheng, Qilin and Yang, Huanwan and Li, Jinpeng},
journal={Working Paper},
year={2021}
}
- Unify the data interchange format as a dict, i.e.,
entry
- Reorganize
JsonIO
- Memory optimization for large dataset for training PLM
- More relation extraction models
- Multihot classification
- Unify the aggregation interface of pooling and attention
- Radical-level features
- Data augmentation
- Loss increases in later training phases -> LR finder?