arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2204.07600cs.CL
收藏

In-BoXBART:获取生物医学多任务学习的指令

In-BoXBART: Get Instructions into Biomedical Multi-Task Learning

Arizona State University(亚利桑那州立大学);Mayo Clinic(梅奥诊所)

Mihir Parmar, Swaroop Mishra, Mirali Purohit, Man Luo, M. Hassan Murad, Chitta Baral

摘要:

单任务模型已被证明在解决特定任务方面至关重要;然而,它们在现实世界的应用中存在局限性,其中需要多任务处理并且显示域转移。最近,教学提示已经显示出显着的改善对多任务的概括,然而,教学提示和多任务学习(MTL)的效果还没有系统地研究在生物医学领域。基于此,本文探讨了生物医学MTL教学提示的影响。我们介绍了BoX,这是一个针对生物医学NLP的32个指令任务的集合,涵盖了(X)个不同的类别。使用这个元数据集,我们提出了一个统一的模型,称为In-BoXBART,它可以联合学习BoX的所有任务,而无需任何特定于任务的模块。据我们所知,这是第一次尝试在生物医学领域提出一个统一的模型,并使用指令来实现跨几个生物医学任务的泛化。实验结果表明,所提出的模型:1)平均优于单任务基线约3%和多任务(无指令)基线约18%,以及2)与单任务基线相比,在少样本学习(即,平均每个任务32个实例)。我们的分析表明,在BoX中的所有任务都有很大的改进空间,这意味着未来研究方向的范围。

英文摘要:

Single-task models have proven pivotal in solving specific tasks; however, they have limitations in real-world applications where multi-tasking is necessary and domain shifts are exhibited. Recently, instructional prompts have shown significant improvement towards multi-task generalization; however, the effect of instructional prompts and Multi-Task Learning (MTL) has not been systematically studied in the biomedical domain. Motivated by this, this paper explores the impact of instructional prompts for biomedical MTL. We introduce the BoX, a collection of 32 instruction tasks for Biomedical NLP across (X) various categories. Using this meta-dataset, we propose a unified model termed In-BoXBART, that can jointly learn all tasks of the BoX without any task-specific modules. To the best of our knowledge, this is the first attempt to propose a unified model in the biomedical domain and use instructions to achieve generalization across several biomedical tasks. Experimental results indicate that the proposed model: 1) outperforms the single-task baseline by ~3% and multi-task (without instruction) baseline by ~18% on an average, and 2) shows ~23% improvement compared to the single-task baseline in few-shot learning (i.e., 32 instances per task) on an average. Our analysis indicates that there is significant room for improvement across tasks in the BoX, implying the scope for future research direction.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑