|
---
|
|
language:
|
|
- en
|
|
tags:
|
|
- aspect-based-sentiment-analysis
|
|
- lcf-bert
|
|
license: mit
|
|
datasets:
|
|
- laptop14 (w/ augmentation)
|
|
- restaurant14 (w/ augmentation)
|
|
- restaurant16 (w/ augmentation)
|
|
- ACL-Twitter (w/ augmentation)
|
|
- MAMS (w/ augmentation)
|
|
- Television (w/ augmentation)
|
|
- TShirt (w/ augmentation)
|
|
- Yelp (w/ augmentation)
|
|
metrics:
|
|
- accuracy
|
|
- macro-f1
|
|
|
|
---
|
|
# Note
|
|
This model is training with 180k+ ABSA samples, see [ABSADatasets](https://github.com/yangheng95/ABSADatasets). Yet the test sets are not included in pre-training, so you can use this model for training and benchmarking on common ABSA datasets, e.g., Laptop14, Rest14 datasets. (Except for the Rest15 dataset!)
|
|
|
|
# DeBERTa for aspect-based sentiment analysis
|
|
The `deberta-v3-base-absa` model for aspect-based sentiment analysis, trained with English datasets from [ABSADatasets](https://github.com/yangheng95/ABSADatasets).
|
|
|
|
## Training Model
|
|
This model is trained based on the FAST-LCF-BERT model with `microsoft/deberta-v3-base`, which comes from [PyABSA](https://github.com/yangheng95/PyABSA).
|
|
To track state-of-the-art models, please see [PyASBA](https://github.com/yangheng95/PyABSA).
|
|
|
|
## Usage
|
|
```python3
|
|
from transformers import AutoTokenizer, AutoModel
|
|
|
|
tokenizer = AutoTokenizer.from_pretrained("yangheng/deberta-v3-base-absa")
|
|
model = AutoModel.from_pretrained("yangheng/deberta-v3-base-absa")
|
|
|
|
inputs = tokenizer("good product especially video and audio quality fantastic.", return_tensors="pt")
|
|
outputs = model(**inputs)
|
|
```
|
|
|
|
## Example in PyASBA
|
|
An [example](https://github.com/yangheng95/PyABSA/blob/release/demos/aspect_polarity_classification/train_apc_multilingual.py) for using FAST-LCF-BERT in PyASBA datasets.
|
|
|
|
## Datasets
|
|
This model is fine-tuned with 180k examples for the ABSA dataset (including augmented data). Training dataset files:
|
|
```
|
|
loading: integrated_datasets/apc_datasets/SemEval/laptop14/Laptops_Train.xml.seg
|
|
loading: integrated_datasets/apc_datasets/SemEval/laptop14/0.cross_boost.fast_lcf_bert_Laptop14_deberta-v3-base.train.augment
|
|
loading: integrated_datasets/apc_datasets/SemEval/laptop14/1.cross_boost.fast_lcf_bert_Laptop14_deberta-v3-base.train.augment
|
|
loading: integrated_datasets/apc_datasets/SemEval/laptop14/2.cross_boost.fast_lcf_bert_Laptop14_deberta-v3-base.train.augment
|
|
loading: integrated_datasets/apc_datasets/SemEval/laptop14/3.cross_boost.fast_lcf_bert_Laptop14_deberta-v3-base.train.augment
|
|
loading: integrated_datasets/apc_datasets/SemEval/restaurant14/Restaurants_Train.xml.seg
|
|
loading: integrated_datasets/apc_datasets/SemEval/restaurant14/0.cross_boost.fast_lcf_bert_Restaurant14_deberta-v3-base.train.augment
|
|
loading: integrated_datasets/apc_datasets/SemEval/restaurant14/1.cross_boost.fast_lcf_bert_Restaurant14_deberta-v3-base.train.augment
|
|
loading: integrated_datasets/apc_datasets/SemEval/restaurant14/2.cross_boost.fast_lcf_bert_Restaurant14_deberta-v3-base.train.augment
|
|
loading: integrated_datasets/apc_datasets/SemEval/restaurant14/3.cross_boost.fast_lcf_bert_Restaurant14_deberta-v3-base.train.augment
|
|
loading: integrated_datasets/apc_datasets/SemEval/restaurant16/restaurant_train.raw
|
|
loading: integrated_datasets/apc_datasets/SemEval/restaurant16/0.cross_boost.fast_lcf_bert_Restaurant16_deberta-v3-base.train.augment
|
|
loading: integrated_datasets/apc_datasets/SemEval/restaurant16/1.cross_boost.fast_lcf_bert_Restaurant16_deberta-v3-base.train.augment
|
|
loading: integrated_datasets/apc_datasets/SemEval/restaurant16/2.cross_boost.fast_lcf_bert_Restaurant16_deberta-v3-base.train.augment
|
|
loading: integrated_datasets/apc_datasets/SemEval/restaurant16/3.cross_boost.fast_lcf_bert_Restaurant16_deberta-v3-base.train.augment
|
|
loading: integrated_datasets/apc_datasets/ACL_Twitter/acl-14-short-data/train.raw
|
|
loading: integrated_datasets/apc_datasets/ACL_Twitter/acl-14-short-data/0.cross_boost.fast_lcf_bert_Twitter_deberta-v3-base.train.augment
|
|
loading: integrated_datasets/apc_datasets/ACL_Twitter/acl-14-short-data/1.cross_boost.fast_lcf_bert_Twitter_deberta-v3-base.train.augment
|
|
loading: integrated_datasets/apc_datasets/ACL_Twitter/acl-14-short-data/2.cross_boost.fast_lcf_bert_Twitter_deberta-v3-base.train.augment
|
|
loading: integrated_datasets/apc_datasets/ACL_Twitter/acl-14-short-data/3.cross_boost.fast_lcf_bert_Twitter_deberta-v3-base.train.augment
|
|
loading: integrated_datasets/apc_datasets/MAMS/train.xml.dat
|
|
loading: integrated_datasets/apc_datasets/MAMS/0.cross_boost.fast_lcf_bert_MAMS_deberta-v3-base.train.augment
|
|
loading: integrated_datasets/apc_datasets/MAMS/1.cross_boost.fast_lcf_bert_MAMS_deberta-v3-base.train.augment
|
|
loading: integrated_datasets/apc_datasets/MAMS/2.cross_boost.fast_lcf_bert_MAMS_deberta-v3-base.train.augment
|
|
loading: integrated_datasets/apc_datasets/MAMS/3.cross_boost.fast_lcf_bert_MAMS_deberta-v3-base.train.augment
|
|
loading: integrated_datasets/apc_datasets/Television/Television_Train.xml.seg
|
|
loading: integrated_datasets/apc_datasets/Television/0.cross_boost.fast_lcf_bert_Television_deberta-v3-base.train.augment
|
|
loading: integrated_datasets/apc_datasets/Television/1.cross_boost.fast_lcf_bert_Television_deberta-v3-base.train.augment
|
|
loading: integrated_datasets/apc_datasets/Television/2.cross_boost.fast_lcf_bert_Television_deberta-v3-base.train.augment
|
|
loading: integrated_datasets/apc_datasets/Television/3.cross_boost.fast_lcf_bert_Television_deberta-v3-base.train.augment
|
|
loading: integrated_datasets/apc_datasets/TShirt/Menstshirt_Train.xml.seg
|
|
loading: integrated_datasets/apc_datasets/TShirt/0.cross_boost.fast_lcf_bert_TShirt_deberta-v3-base.train.augment
|
|
loading: integrated_datasets/apc_datasets/TShirt/1.cross_boost.fast_lcf_bert_TShirt_deberta-v3-base.train.augment
|
|
loading: integrated_datasets/apc_datasets/TShirt/2.cross_boost.fast_lcf_bert_TShirt_deberta-v3-base.train.augment
|
|
loading: integrated_datasets/apc_datasets/TShirt/3.cross_boost.fast_lcf_bert_TShirt_deberta-v3-base.train.augment
|
|
loading: integrated_datasets/apc_datasets/Yelp/yelp.train.txt
|
|
loading: integrated_datasets/apc_datasets/Yelp/0.cross_boost.fast_lcf_bert_Yelp_deberta-v3-base.train.augment
|
|
loading: integrated_datasets/apc_datasets/Yelp/1.cross_boost.fast_lcf_bert_Yelp_deberta-v3-base.train.augment
|
|
loading: integrated_datasets/apc_datasets/Yelp/2.cross_boost.fast_lcf_bert_Yelp_deberta-v3-base.train.augment
|
|
loading: integrated_datasets/apc_datasets/Yelp/3.cross_boost.fast_lcf_bert_Yelp_deberta-v3-base.train.augment
|
|
|
|
```
|
|
If you use this model in your research, please cite our paper:
|
|
```
|
|
@article{YangZMT21,
|
|
author = {Heng Yang and
|
|
Biqing Zeng and
|
|
Mayi Xu and
|
|
Tianxing Wang},
|
|
title = {Back to Reality: Leveraging Pattern-driven Modeling to Enable Affordable
|
|
Sentiment Dependency Learning},
|
|
journal = {CoRR},
|
|
volume = {abs/2110.08604},
|
|
year = {2021},
|
|
url = {https://arxiv.org/abs/2110.08604},
|
|
eprinttype = {arXiv},
|
|
eprint = {2110.08604},
|
|
timestamp = {Fri, 22 Oct 2021 13:33:09 +0200},
|
|
biburl = {https://dblp.org/rec/journals/corr/abs-2110-08604.bib},
|
|
bibsource = {dblp computer science bibliography, https://dblp.org}
|
|
}
|
|
```
|
|
|
