DKE-Research 在 SemEval-2024 任务 2 中的研究:结合生成模型数据增强与生物医学知识提升推理鲁棒性
DKE-Research at SemEval-2024 Task 2: Incorporating Data Augmentation with Generative Models and Biomedical Knowledge to Enhance Inference Robustness
AI总结:
针对临床试验生物医学自然语言推理中预训练模型偏差问题,提出结合语义扰动、领域词汇替换、数值推理任务的多任务数据增强方法,搭配DeBERTa架构,在NLI4CT 2024基准取得显著提升,消融验证各模块有效性,最终在32支队伍中获忠实度第12、一致性第8。
摘要:
安全可靠的自然语言推理对从临床试验报告中提取洞见至关重要,但由于大型预训练语言模型存在偏差,该任务面临挑战。本文提出一种新颖的数据增强技术,用于提升临床试验场景下生物医学自然语言推理的模型鲁棒性。我们通过语义扰动和领域特定词汇替换生成合成样本,并新增一项数值与定量推理任务,以此引入更多多样性并减少捷径学习。我们的方法结合多任务学习与 DeBERTa 架构,在 NLI4CT 2024 基准上相比原始语言模型取得了显著性能提升。消融研究验证了每种增强方法对提升鲁棒性的贡献。我们的最佳性能模型在32名参与者中,忠实度排名第12,一致性排名第8。
英文摘要:
Safe and reliable natural language inference is critical for extracting insights from clinical trial reports but poses challenges due to biases in large pre-trained language models. This paper presents a novel data augmentation technique to improve model robustness for biomedical natural language inference in clinical trials. By generating synthetic examples through semantic perturbations and domain-specific vocabulary replacement and adding a new task for numerical and quantitative reasoning, we introduce greater diversity and reduce shortcut learning. Our approach, combined with multi-task learning and the DeBERTa architecture, achieved significant performance gains on the NLI4CT 2024 benchmark compared to the original language models. Ablation studies validate the contribution of each augmentation method in improving robustness. Our best-performing model ranked 12th in terms of faithfulness and 8th in terms of consistency, respectively, out of the 32 participants.
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。