Update README.md
Browse files
README.md
CHANGED
@@ -19,6 +19,8 @@ metrics:
|
|
19 |
- macro-f1
|
20 |
|
21 |
---
|
|
|
|
|
22 |
|
23 |
# DeBERTa for aspect-based sentiment analysis
|
24 |
The `deberta-v3-base-absa` model for aspect-based sentiment analysis, trained with English datasets from [ABSADatasets](https://github.com/yangheng95/ABSADatasets).
|
@@ -39,9 +41,9 @@ outputs = model(**inputs)
|
|
39 |
```
|
40 |
|
41 |
## Example in PyASBA
|
42 |
-
An [example](https://github.com/yangheng95/PyABSA/blob/release/demos/aspect_polarity_classification/train_apc_multilingual.py) for using FAST-LCF-BERT in PyASBA
|
43 |
|
44 |
-
## Datasets
|
45 |
This model is fine-tuned with 180k examples for the ABSA dataset (including augmented data). Training dataset files:
|
46 |
```
|
47 |
loading: integrated_datasets/apc_datasets/SemEval/laptop14/Laptops_Train.xml.seg
|
19 |
- macro-f1
|
20 |
|
21 |
---
|
22 |
+
# Note
|
23 |
+
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!)
|
24 |
|
25 |
# DeBERTa for aspect-based sentiment analysis
|
26 |
The `deberta-v3-base-absa` model for aspect-based sentiment analysis, trained with English datasets from [ABSADatasets](https://github.com/yangheng95/ABSADatasets).
|
41 |
```
|
42 |
|
43 |
## Example in PyASBA
|
44 |
+
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.
|
45 |
|
46 |
+
## Datasets
|
47 |
This model is fine-tuned with 180k examples for the ABSA dataset (including augmented data). Training dataset files:
|
48 |
```
|
49 |
loading: integrated_datasets/apc_datasets/SemEval/laptop14/Laptops_Train.xml.seg
|