3 accepted papers
This empirical study analyzes how the choice of pre-training corpus affects the quality of learned transformer representations. We focus specifically on the representation quality achieved through pre-training alone. Our experiments demonstrate that pre-training on a small, specialized corpus can pr
Most current state-of-the-art approaches for text classification are based on fine-tuning the representations computed by large language models (LLMs). This strategy has led to significant improvements in classification performance and contributed to a reduction of the amount of labeled data require…
Textual representations based on pre-trained language models are key, especially in few-shot learning scenarios. What makes a representation good for text classification? Is it due to the geometric properties of the space or because it is well aligned with the task? We hypothesize the second claim.…