Update README.md
Browse files
README.md
CHANGED
|
@@ -68,27 +68,23 @@ print(generated_text)
|
|
| 68 |
| [`sega-small-chinese`]() | xM | Chinese |
|
| 69 |
|
| 70 |
|
| 71 |
-
##
|
| 72 |
-
|
| 73 |
-
|
| 74 |
-
|
| 75 |
-
|
| 76 |
-
|
| 77 |
-
|
| 78 |
-
|
| 79 |
-
|
| 80 |
-
|
| 81 |
-
|
| 82 |
-
|
| 83 |
-
|
| 84 |
-
|
| 85 |
-
|
| 86 |
-
|
| 87 |
-
|
| 88 |
-
|
| 89 |
-
### Pretraining
|
| 90 |
-
|
| 91 |
-
## Evaluation results
|
| 92 |
|
| 93 |
|
| 94 |
|
|
|
|
| 68 |
| [`sega-small-chinese`]() | xM | Chinese |
|
| 69 |
|
| 70 |
|
| 71 |
+
## Data Augmentation for Text Classification Tasks:
|
| 72 |
+
- Setting: Low-resource setting, where only n={50,100,200,500,1000} labeled samples are available for training. The below results are the average of all training sizes.
|
| 73 |
+
- Datasets: [HuffPost](https://huggingface.co/datasets/khalidalt/HuffPost), [BBC](https://huggingface.co/datasets/SetFit/bbc-news), [SST2](https://huggingface.co/datasets/glue), [IMDB](https://huggingface.co/datasets/imdb), [Yahoo](https://huggingface.co/datasets/yahoo_answers_topics), [20NG](https://huggingface.co/datasets/newsgroup).
|
| 74 |
+
- Base classifier: [DistilBERT](https://huggingface.co/distilbert-base-cased)
|
| 75 |
+
|
| 76 |
+
| Method | HuffPost | BBC | SST2 | IMDB | Yahoo | 20NG | avg. |
|
| 77 |
+
|---------|:------------------:|:------------------:|:----------------------:|:----------------------:|:----------:|:----------:|:----------:|
|
| 78 |
+
| | ID / OOD (BBC) | ID / OOD (Huff) | ID / OOD (IMDB) | ID / OOD (SST2) | | | |
|
| 79 |
+
| none | 79.17 / 62.32 | **96.16** / 62.00 | 76.67 / 73.16 | 77.87 / 74.43 | 45.77 | 46.67 | 69.42 |
|
| 80 |
+
| EDA | 79.63 / 67.48 | 95.11 / 58.92 | 75.52 / 69.46 | 77.88 / 75.88 | 45.10 | 46.15 | 69.11 |
|
| 81 |
+
| STA | 80.74 / 69.31 | 95.64 / 64.82 | 77.80 / 73.66 | 77.88 / 74.77 | 46.96 | 47.27 | 70.88 |
|
| 82 |
+
| Back | 80.48 / 67.75 | 95.28 / 63.10 | 76.96 / 72.23 | 78.35 / 75.96 | 46.10 | 46.61 | 70.28 |
|
| 83 |
+
| MLM | 80.04 / 66.80 | 96.07 / 65.39 | 76.61/ 73.11 | 75.73 / 73.70 | 45.35 | 46.53 | 69.93 |
|
| 84 |
+
| C-MLM | 79.96 / 65.10 | 96.13 / **67.80** | 76.91 / 71.83 | 77.31 / 75.02 | 45.29 | 46.36 | 70.17 |
|
| 85 |
+
| LAMBADA | 81.03 / 68.89 | 93.75 / 52.79 | 77.87 / 74.54 | 77.49 / 74.33 | 50.66 | 47.72 | 69.91 |
|
| 86 |
+
| **SEGA (Ours)** | 81.43 / 74.87 | 95.61 / 67.79 | 77.87 / 72.94 | **79.51** / **76.75** | 49.43 | 50.47 | 72.67 |
|
| 87 |
+
| **SEGA-f (Ours)** | **81.82** / **76.18** | 95.78 / 67.79 | **80.59** / **80.32** | 79.37 / 76.61 | **50.12** | **50.81** | **73.94** |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 88 |
|
| 89 |
|
| 90 |
|