Papers with attention-based transformer language models
Frequency Balanced Datasets Lead to Better Language Models (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing evidence that high-frequency tokens in pretraining data might bias learning, causing undesired effects, is not clear. |
| Approach: | They propose a sampling algorithm that iteratively assesses token frequencies and removes sentences that contain still high-frequency tokens, resulting in a balanced dataset. |
| Outcome: | The proposed method reduces the amount of pre-training data required for training attention-based transformer language models by up to three times. |