Recent advances in NLP demonstrate the effectiveness of training large-scale language models and transferring them to downstream tasks. Can fine-tuning these models on tasks other than language modeling further improve performance? In this paper, we conduct an extensive study of the transferability between 33 NLP tasks across three broad classes of problems (text classification, question answering, and sequence labeling). Our results show that transfer learning is more beneficial than previously thought, especially when target task data is scarce, and can improve performance even when the source task is small or differs substantially from the target task (e.g., part-of-speech tagging transfers well to the DROP QA dataset). We also develop task embeddings that can be used to predict the most transferable source tasks for a given target task, and we validate their effectiveness in experiments controlled for source and target data size. Overall, our experiments reveal that factors such as source data size, task and domain similarity, and task complexity all play a role in determining transferability.

本文旨在探究将自然语言处理大规模语言模型fine-tuning应用于其他任务是否有效，通过在三大问题领域（文本分类、问题回答、序列标注）的33个NLP任务上的数据验证，结果显示transfer learning在数据稀缺情况下更为有效，在源任务数据较少或与目标任务差异较大的情况下仍能提高性能，同时提出了可以预测给定目标任务最具可转移性源任务的任务嵌入，并验证其在数据大小、源和目标之间的有效性。最终的结果显示源数据大小、任务和领域的相似性和任务的复杂性在决定转移性方面起着关键作用。

探索和预测NLP任务的可转移性