Update README.md
Browse files
README.md
CHANGED
|
@@ -77,7 +77,7 @@ predictions = trainer_hf.predict(encoded_dataset["validation"])
|
|
| 77 |
acc_val = metric.compute(predictions=np.argmax(predictions.predictions,axis=1).tolist(), references=predictions.label_ids)['accuracy']
|
| 78 |
```
|
| 79 |
Finally, with the classification above model, you can follow the steps below to generate the news ranking.
|
| 80 |
-
- For each news article in the [google_news_en
|
| 81 |
- Employing pair encoders, rank the news articles that occupy the second position in each pair, determining their relevance to the first article.
|
| 82 |
- Organize each list generated by the encoders based on the probabilities obtained for the relevance class.
|
| 83 |
|
|
@@ -87,7 +87,7 @@ More information needed
|
|
| 87 |
|
| 88 |
## Training, evaluation and test data
|
| 89 |
|
| 90 |
-
The training data is sourced from the *train* split in [usa_news_en
|
| 91 |
|
| 92 |
## Training procedure
|
| 93 |
|
|
|
|
| 77 |
acc_val = metric.compute(predictions=np.argmax(predictions.predictions,axis=1).tolist(), references=predictions.label_ids)['accuracy']
|
| 78 |
```
|
| 79 |
Finally, with the classification above model, you can follow the steps below to generate the news ranking.
|
| 80 |
+
- For each news article in the [google_news_en dataset](https://huggingface.co/datasets/cmunhozc/google_news_en) dataset positioned as the first element in a pair, retrieve all corresponding pairs from the dataset.
|
| 81 |
- Employing pair encoders, rank the news articles that occupy the second position in each pair, determining their relevance to the first article.
|
| 82 |
- Organize each list generated by the encoders based on the probabilities obtained for the relevance class.
|
| 83 |
|
|
|
|
| 87 |
|
| 88 |
## Training, evaluation and test data
|
| 89 |
|
| 90 |
+
The training data is sourced from the *train* split in [usa_news_en dataset](https://huggingface.co/datasets/cmunhozc/usa_news_en), and a similar procedure is applied for the *validation* set. In the case of testing, the initial segment for the text classification model is derived from the *test_1* and *test_2* splits. As for the ranking model, the test dataset from [google_news_en dataset](https://huggingface.co/datasets/cmunhozc/google_news_en) is utilized
|
| 91 |
|
| 92 |
## Training procedure
|
| 93 |
|