arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2404.05415cs.CLcs.AI
收藏

使用大型语言模型进行关系抽取:以穴位定位为例

Relation Extraction Using Large Language Models: A Case Study on Acupuncture Point Locations

The University of Texas Health Science Center at Houston(德克萨斯大学休斯顿健康科学中心);Yale University(耶鲁大学);Mayo Clinic(妙佑医疗国际);China Academy of Chinese Medical Sciences(中国中医科学院);The University of Texas MD Anderson Cancer Center(德克萨斯大学MD安德森癌症中心)

Yiming Li, Xueqing Peng, Jianfu Li, Xu Zuo, Suyuan Peng, Donghong Pei, Cui Tao, Hua Xu, Na Hong

AI总结:

本文以 WHO 标准的 361 个穴位、3,174 个定位关系为语料,比较 GPT 与 LSTM、BioBERT 的关系抽取性能,发现微调 GPT-3.5 表现最佳,微平均 F1 达 0.92。

摘要:

在针灸治疗中,穴位的准确定位对其疗效至关重要。大型语言模型(LLM)——例如 Generative Pre-trained Transformers(GPT)——所具备的先进语言理解能力,为从文本知识源中抽取与穴位定位相关的关系提供了重要机遇。本研究旨在比较 GPT 与传统深度学习模型(Long Short-Term Memory(LSTM)和用于生物医学文本挖掘的 Bidirectional Encoder Representations from Transformers(BioBERT))在抽取穴位相关定位关系方面的性能,并评估预训练和微调对 GPT 性能的影响。我们采用世界卫生组织《西太平洋地区针灸穴位定位标准》(WHO Standard)作为语料库,其中包含 361 个穴位的描述。研究标注了穴位之间的五类关系(“direction_of”“distance_of”“part_of”“near_acupoint”和“located_near”),共计 3,174 个关系实例。研究比较了五个模型:BioBERT、LSTM、预训练 GPT-3.5、微调 GPT-3.5 以及预训练 GPT-4。性能指标包括微平均精确匹配精确率、召回率和 F1 分数。结果表明,微调 GPT-3.5 在所有关系类型上的 F1 分数均持续优于其他模型。总体而言,它取得了 0.92 的最高微平均 F1 分数。本研究强调了 GPT 等 LLM 在抽取穴位定位相关关系方面的有效性,对准确建模针灸知识以及推动针灸培训和实践中的标准化实施具有意义。研究结果还有助于推进传统医学与补充医学中的信息学应用,展示了 LLM 在自然语言处理中的潜力。

英文摘要:

In acupuncture therapy, the accurate location of acupoints is essential for its effectiveness. The advanced language understanding capabilities of large language models (LLMs) like Generative Pre-trained Transformers (GPT) present a significant opportunity for extracting relations related to acupoint locations from textual knowledge sources. This study aims to compare the performance of GPT with traditional deep learning models (Long Short-Term Memory (LSTM) and Bidirectional Encoder Representations from Transformers for Biomedical Text Mining (BioBERT)) in extracting acupoint-related location relations and assess the impact of pretraining and fine-tuning on GPT's performance. We utilized the World Health Organization Standard Acupuncture Point Locations in the Western Pacific Region (WHO Standard) as our corpus, which consists of descriptions of 361 acupoints. Five types of relations ('direction_of,' 'distance_of,' 'part_of,' 'near_acupoint,' and 'located_near') (n= 3,174) between acupoints were annotated. Five models were compared: BioBERT, LSTM, pre-trained GPT-3.5, fine-tuned GPT-3.5, as well as pre-trained GPT-4. Performance metrics included micro-average exact match precision, recall, and F1 scores. Our results demonstrate that fine-tuned GPT-3.5 consistently outperformed other models in F1 scores across all relation types. Overall, it achieved the highest micro-average F1 score of 0.92. This study underscores the effectiveness of LLMs like GPT in extracting relations related to acupoint locations, with implications for accurately modeling acupuncture knowledge and promoting standard implementation in acupuncture training and practice. The findings also contribute to advancing informatics applications in traditional and complementary medicine, showcasing the potential of LLMs in natural language processing.

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。

↑