面向半结构化网页文章的基于大语言模型赋能的高通量生物医学关系抽取
High-throughput Biomedical Relation Extraction for Semi-Structured Web Articles Empowered by Large Language Models
AI总结：
本文提出一种基于大语言模型的高通量生物医学关系抽取方法，将任务表述为二分类问题，结合外部语料库与世界知识进行事实验证，并针对半结构化网页文章优化实体匹配与文本检索，最终从三个网站提取超24万个三元组，性能媲美GPT-4。
摘要：
目的：开发一个高通量生物医学关系抽取系统，以可扩展和可证据化的方式利用大语言模型（LLMs）的阅读理解能力和生物医学世界知识。方法：我们将关系抽取任务表述为LLMs的二分类问题。具体而言，LLMs基于外部语料库及其世界知识做出决策，并给出判断理由以进行事实验证。该方法专为半结构化网页文章量身定制，其中我们将主标题指定为尾实体并将其显式纳入上下文，同时基于生物医学词典匹配潜在的头实体。此外，冗长的内容被切分为文本块，进行嵌入，并使用额外的嵌入模型进行检索。结果：使用开源LLM，我们从三个知名生物医学网站提取了248659个关系三元组，涵盖三种不同的关系类型。为了评估用于生物医学关系抽取的基础流水线的有效性，我们构建了一个由医学专家标注的基准数据集。评估结果表明，该流水线表现出与GPT-4相当的性能。案例研究进一步阐明了当代LLMs在半结构化网页文章生物医学关系抽取中面临的挑战。结论：所提出的方法已证明其在利用LLMs优势进行高通量生物医学关系抽取方面的有效性。其适应性显而易见，因为它可以无缝扩展到各种半结构化生物医学网站，从而轻松促进各类生物医学关系的抽取。
英文摘要：
Objective: To develop a high-throughput biomedical relation extraction system that takes advantage of the large language models'(LLMs) reading comprehension ability and biomedical world knowledge in a scalable and evidential manner. Methods: We formulate the relation extraction task as binary classifications for large language models. Specifically, LLMs make the decision based on the external corpus and its world knowledge, giving the reason for the judgment for factual verification. This method is tailored for semi-structured web articles, wherein we designate the main title as the tail entity and explicitly incorporate it into the context, and the potential head entities are matched based on a biomedical thesaurus. Moreover, lengthy contents are sliced into text chunks, embedded, and retrieved with additional embedding models. Results: Using an open-source LLM, we extracted 248659 relation triplets of three distinct relation types from three reputable biomedical websites. To assess the efficacy of the basic pipeline employed for biomedical relation extraction, we curated a benchmark dataset annotated by a medical expert. Evaluation results indicate that the pipeline exhibits performance comparable to that of GPT-4. Case studies further illuminate challenges faced by contemporary LLMs in the context of biomedical relation extraction for semi-structured web articles. Conclusion: The proposed method has demonstrated its effectiveness in leveraging the strengths of LLMs for high-throughput biomedical relation extraction. Its adaptability is evident, as it can be seamlessly extended to diverse semi-structured biomedical websites, facilitating the extraction of various types of biomedical relations with ease.
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。
