Update README.md
Browse files
README.md
CHANGED
@@ -1,8 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
# DeBERTa for aspect-based sentiment analysis
|
2 |
The `deberta-v3-base-absa` model for aspect-based sentiment analysis, trained with English datasets from [ABSADatasets](https://github.com/yangheng95/ABSADatasets).
|
3 |
|
4 |
## Training Model
|
5 |
-
This model is trained based on the
|
6 |
To track state-of-the-art models, please see [PyASBA](https://github.com/yangheng95/PyABSA).
|
7 |
|
8 |
## Usage
|
@@ -17,7 +38,7 @@ outputs = model(**inputs)
|
|
17 |
```
|
18 |
|
19 |
## Example in PyASBA
|
20 |
-
An [example](https://github.com/yangheng95/PyABSA/blob/release/demos/aspect_polarity_classification/train_apc_multilingual.py) for using
|
21 |
|
22 |
## Datasets
|
23 |
This model is fine-tuned with 180k examples for the ABSA dataset (including augmented data). Training dataset files:
|
@@ -84,4 +105,3 @@ If you use this model in your research, please cite our paper:
|
|
84 |
bibsource = {dblp computer science bibliography, https://dblp.org}
|
85 |
}
|
86 |
```
|
87 |
-
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
tags:
|
5 |
+
- aspect-based-sentiment-analysis
|
6 |
+
- lcf-bert
|
7 |
+
license: mit
|
8 |
+
datasets:
|
9 |
+
- laptop14 (w/ augmentation)
|
10 |
+
- restaurant14 (w/ augmentation)
|
11 |
+
- restaurant16 (w/ augmentation)
|
12 |
+
- ACL-Twitter (w/ augmentation)
|
13 |
+
- MAMS (w/ augmentation)
|
14 |
+
- Television (w/ augmentation)
|
15 |
+
- TShirt (w/ augmentation)
|
16 |
+
- Yelp (w/ augmentation)
|
17 |
+
metrics:
|
18 |
+
- accuracy
|
19 |
+
- macro-f1
|
20 |
+
---
|
21 |
+
|
22 |
# DeBERTa for aspect-based sentiment analysis
|
23 |
The `deberta-v3-base-absa` model for aspect-based sentiment analysis, trained with English datasets from [ABSADatasets](https://github.com/yangheng95/ABSADatasets).
|
24 |
|
25 |
## Training Model
|
26 |
+
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).
|
27 |
To track state-of-the-art models, please see [PyASBA](https://github.com/yangheng95/PyABSA).
|
28 |
|
29 |
## Usage
|
|
|
38 |
```
|
39 |
|
40 |
## Example in PyASBA
|
41 |
+
An [example](https://github.com/yangheng95/PyABSA/blob/release/demos/aspect_polarity_classification/train_apc_multilingual.py) for using FAST-LCF-BERT in PyASBA
|
42 |
|
43 |
## Datasets
|
44 |
This model is fine-tuned with 180k examples for the ABSA dataset (including augmented data). Training dataset files:
|
|
|
105 |
bibsource = {dblp computer science bibliography, https://dblp.org}
|
106 |
}
|
107 |
```
|
|