DS4DH 团队在 #SMM4H 2023 中的研究：基于 Sentence Transformers 与倒数排名融合的零样本药物不良事件归一化
DS4DH at #SMM4H 2023: Zero-Shot Adverse Drug Events Normalization using Sentence Transformers and Reciprocal-Rank Fusion
AI总结：
本研究针对SMM4H 2023共享任务5的Twitter药物不良事件归一化需求，提出BERT微调实体识别结合Sentence Transformers与倒数排名融合的零样本归一化两阶段方法，取得任务最优性能，验证了该方法的有效性与应用潜力。
摘要：
本文概述了由数字健康数据科学（Data Science for Digital Health，DS4DH）团队为2023年健康应用社交媒体挖掘（Social Media Mining for Health Applications，SMM4H）共享任务5开发的药物不良事件归一化系统的性能评估结果。共享任务5的目标是将Twitter中的药物不良事件提及内容，归一化到《监管活动医学词典》（Medical Dictionary for Regulatory Activities）术语的标准概念。我们的系统采用两阶段方法：首先通过BERT微调进行实体识别，随后利用Sentence Transformers和倒数排名融合实现零样本归一化。该方法取得了44.9%的精确率、40.5%的召回率以及42.6%的F1值，其性能比共享任务5的中位性能高出10%，且在所有参赛队伍中表现最佳。这些结果证实了我们方法的有效性，以及其在社交媒体文本挖掘领域中应用于药物不良事件归一化的潜力。
英文摘要：
This paper outlines the performance evaluation of a system for adverse drug event normalization, developed by the Data Science for Digital Health (DS4DH) group for the Social Media Mining for Health Applications (SMM4H) 2023 shared task 5. Shared task 5 targeted the normalization of adverse drug event mentions in Twitter to standard concepts of the Medical Dictionary for Regulatory Activities terminology. Our system hinges on a two-stage approach: BERT fine-tuning for entity recognition, followed by zero-shot normalization using sentence transformers and reciprocal-rank fusion. The approach yielded a precision of 44.9%, recall of 40.5%, and an F1-score of 42.6%. It outperformed the median performance in shared task 5 by 10% and demonstrated the highest performance among all participants. These results substantiate the effectiveness of our approach and its potential application for adverse drug event normalization in the realm of social media text mining.
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。
