Hi, there! Please star this repo if it helps you! Each Star helps PyABSA go further, many thanks.
PyABSA is a free and open-soruce tool for everyone, but please do not forget to attach the author information and project address in your work.
| Overview | HuggingfaceHub | ABDADatasets | ABSA Models | Colab Tutorials | Troubleshooting(常见问题解决)
- (Gradio) Aspect term extraction & sentiment classification (English, Chinese, Arabic, Dutch, French, Russian, Spanish, Turkish, etc.)
- (Prototype) Aspect term extraction & sentiment classification (English, Chinese, Arabic, Dutch, French, Russian, Spanish, Turkish, etc.)
- 方面术语提取和情感分类 (中文, etc.)
- Aspect-based sentiment classification (Multilingual) (English, Chinese, etc.)
This repository is based on our papers for ABSA research. Here are the papers that you can cite or refer to for your implementations:
Aspect sentiment polarity classification models
- Back to Reality: Leveraging Pattern-driven Modeling to Enable Affordable Sentiment Dependency Learning (e.g., Fast-LSA, 2020)
- Learning for target-dependent sentiment based on local context-aware embedding (e.g., LCA-Net, 2020)
- LCF: A Local Context Focus Mechanism for Aspect-Based Sentiment Classification (e.g., LCF-BERT, 2019)
Aspect sentiment polarity classification & Aspect term extraction models
If you are looking for the original proposal of local context focus, here are some introduction at here.
Aspect-term extraction
Models | Laptop14 (APC-Acc) | Laptop14 (ATE-F1) | Restaurant14 (APC-Acc) | Restaurant14 (ATE-F1) |
---|---|---|---|---|
FAST-LCF-ATEPC (BERT) | 80.72 | 85.75 | 86.40 | 89.29 |
FAST-LCF-ATEPC (DeBERTa) | 83.65 | 89.03 | 90.52 | 91.77 |
FAST-LCF-ATEPC (DeBERTa-Large) | 85.06 | 87.76 | 90.70 | 92.50 |
Aspect-based sentiment analysis
Models | Laptop14 (Acc) | Restaurant14 (acc) | Models | Laptop14 (Acc) | Restaurant14 (acc) |
---|---|---|---|---|---|
FAST-LSA-P(DeBERTa) | 84.33 | 89.91 | FAST-LSA-P(DeBERTa-Large) | 86.00 | 90.33 |
FAST-LSA-T(DeBERTa) | 84.80 | 89.91 | FAST-LSA-T(DeBERTa-Large) | 86.31 | 90.86 |
FAST-LSA-S(DeBERTa) | 84.17 | 89.64 | FAST-LSA-S(DeBERTa-Large) | 86.21 | 89.38 |
pyabsa | package root (including all interfaces) |
pyabsa.functional | recommend interface entry |
pyabsa.functional.checkpoint | checkpoint manager entry, inference model entry |
pyabsa.functional.dataset | datasets entry |
pyabsa.functional.config | predefined config manager |
pyabsa.functional.trainer | training module, every trainer return a inference model |
To use PyABSA, install the latest version from pip or source code:
pip install -U pyabsa
git clone https://github.com/yangheng95/PyABSA --depth=1
cd PyABSA
python setup.py install
My case:
!git clone https://github.com/leticiarubalcabadg/PyABSA --depth=1
%cd PyABSA
!python setup.py build
!python setup.py install
- Train a model of aspect term extraction
from pyabsa.functional import ATEPCModelList
from pyabsa.functional import Trainer, ATEPCTrainer
from pyabsa.functional import ABSADatasetList
from pyabsa.functional import ATEPCConfigManager
atepc_config = ATEPCConfigManager.get_atepc_config_english()
atepc_config.pretrained_bert = 'microsoft/deberta-v3-base'
atepc_config.model = ATEPCModelList.FAST_LCF_ATEPC
dataset_path = ABSADatasetList.Restaurant14
# or your local dataset: dataset_path = 'your local dataset path'
aspect_extractor = ATEPCTrainer(config=atepc_config,
dataset=dataset_path,
from_checkpoint='', # set checkpoint to train on the checkpoint.
checkpoint_save_mode=1,
auto_device=True
).load_trained_model()
- Inference Example of aspect term extraction
from pyabsa.functional import ABSADatasetList
from pyabsa.functional import ATEPCCheckpointManager
examples = ['But the staff was so nice to us .',
'But the staff was so horrible to us .',
r'Not only was the food outstanding , but the little ` perks \' were great .',
'It took half an hour to get our check , which was perfect since we could sit , have drinks and talk !',
'It was pleasantly uncrowded , the service was delightful , the garden adorable , '
'the food -LRB- from appetizers to entrees -RRB- was delectable .',
'How pretentious and inappropriate for MJ Grill to claim that it provides power lunch and dinners !'
]
inference_source = ABSADatasetList.Restaurant14
aspect_extractor = ATEPCCheckpointManager.get_aspect_extractor(checkpoint='multilingual2')
atepc_result = aspect_extractor.extract_aspect(inference_source=inference_source,
save_result=True,
print_result=True, # print the result
pred_sentiment=True, # Predict the sentiment of extracted aspect terms
)
- Get available checkpoints from Google Drive
PyABSA will check the latest available checkpoints before and load the latest checkpoint from Google Drive. To view available checkpoints, you can use the following code and load the checkpoint by name:
from pyabsa import available_checkpoints
# The results of available_checkpoints() depend on the PyABSA version
checkpoint_map = available_checkpoints() # show available checkpoints of PyABSA of current version
If you can not access to Google Drive, you can download our checkpoints and load the unzipped checkpoint manually.
We expect that you can help us improve this project, and your contributions are welcome. You can make a contribution in many ways, including:
- Share your custom dataset in PyABSA and ABSADatasets
- Integrates your models in PyABSA. (You can share your models whether it is or not based on PyABSA. if you are interested, we will help you)
- Raise a bug report while you use PyABSA or review the code (PyABSA is a individual project driven by enthusiasm so your help is needed)
- Give us some advice about feature design/refactor (You can advise to improve some feature)
- Correct/Rewrite some error-messages or code comment (The comments are not written by native english speaker, you can help us improve documents)
- Create an example script in a particular situation (Such as specify a SpaCy model, pretrained-bert type, some hyperparameters)
- Star this repository to keep it active
This work is built from LC-ABSA/LCF-ABSA and LCF-ATEPC, and other impressive works such as PyTorch-ABSA and LCFS-BERT.