arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2305.14232cs.CLcs.DLcs.IRcs.LG
收藏

用于科学文献理解的多任务对比学习模型预训练

Pre-training Multi-task Contrastive Learning Models for Scientific Literature Understanding

University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Microsoft Research(微软研究院);Microsoft Search, Assistant and Intelligence(微软搜索、助理与智能部门)

Yu Zhang, Hao Cheng, Zhihong Shen, Xiaodong Liu, Ye-Yi Wang, Jianfeng Gao

AI总结:

提出多任务对比学习框架SciMult,通过任务感知专门化和指令微调技术,在多个科学文献理解任务间共享知识并避免干扰,实验证明其优于现有最先进的科学预训练语言模型。

摘要:

科学文献理解任务因其加速科学发现的潜力而备受关注。预训练语言模型(LMs)在这些任务中表现出有效性,尤其是通过对比学习进行微调时。然而,联合利用多个异构任务(例如,极多标签论文分类、引用预测和文献搜索)的预训练数据在很大程度上仍未被探索。为了填补这一空白,我们提出了一个多任务对比学习框架SciMult,重点关注促进不同科学文献理解任务之间的通用知识共享,同时防止任务特定技能相互干扰。具体而言,我们探索了两种技术——任务感知专门化和指令微调。前者采用带有任务感知子层的混合专家Transformer架构;后者将任务特定指令前置到输入文本中,以产生任务感知输出。在全面的基准数据集集合上的大量实验验证了我们任务感知专门化策略的有效性,其中我们优于最先进的科学预训练LMs。代码、数据集和预训练模型可在https://scimult.github.io/找到。

英文摘要:

Scientific literature understanding tasks have gained significant attention due to their potential to accelerate scientific discovery. Pre-trained language models (LMs) have shown effectiveness in these tasks, especially when tuned via contrastive learning. However, jointly utilizing pre-training data across multiple heterogeneous tasks (e.g., extreme multi-label paper classification, citation prediction, and literature search) remains largely unexplored. To bridge this gap, we propose a multi-task contrastive learning framework, SciMult, with a focus on facilitating common knowledge sharing across different scientific literature understanding tasks while preventing task-specific skills from interfering with each other. To be specific, we explore two techniques -- task-aware specialization and instruction tuning. The former adopts a Mixture-of-Experts Transformer architecture with task-aware sub-layers; the latter prepends task-specific instructions to the input text so as to produce task-aware outputs. Extensive experiments on a comprehensive collection of benchmark datasets verify the effectiveness of our task-aware specialization strategy, where we outperform state-of-the-art scientific pre-trained LMs. Code, datasets, and pre-trained models can be found at https://scimult.github.io/.

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。

↑