用大模型零样本构建可增量更新的知识图谱，无需后期处理。
iText2KG: Incremental Knowledge Graphs Construction Using Large Language Models
- 基于四个模块的零样本流程，支持跨领域增量构建
- 在论文、网页、简历三类数据上优于基线方法
- 无需预设实体类型，适合多场景快速部署
现有数据大多为非结构化文本，难以高效获取有价值信息。自动构建知识图谱（KG）是实现数据结构化与有效检索的关键，有助于洞察、推理与分析。传统自然语言处理方法如命名实体识别和关系抽取受限于预定义实体类型及有监督学习需求。当前研究虽利用大语言模型的零样本或少样本能力，但仍存在未解决的语义重复实体与关系问题，导致图谱不一致，需大量后处理，且多数方法依赖特定主题。本文提出 iText2KG，一种无需后处理、支持增量与主题无关的知识图谱构建方法。该即插即用的零样本方法适用于广泛场景，包含四个模块：文档提炼器、增量实体抽取器、增量关系抽取器、图整合与可视化模块。实验表明，iText2KG 在将科学论文、网站内容、简历转换为知识图谱三种场景中均显著优于基线方法。
原文摘要 · Abstract (English)
Most available data is unstructured, making it challenging to access valuable information. Automatically building Knowledge Graphs (KGs) is crucial for structuring data and making it accessible, allowing users to search for information effectively. KGs also facilitate insights, inference, and reasoning. Traditional NLP methods, such as named entity recognition and relation extraction, are key in information retrieval but face limitations, including the use of predefined entity types and the need for supervised learning. Current research leverages large language models' capabilities, such as zero- or few-shot learning. However, unresolved and semantically duplicated entities and relations still pose challenges, leading to inconsistent graphs and requiring extensive post-processing. Additionally, most approaches are topic-dependent. In this paper, we propose iText2KG, a method for incremental, topic-independent KG construction without post-processing. This plug-and-play, zero-shot method is applicable across a wide range of KG construction scenarios and comprises four modules: Document Distiller, Incremental Entity Extractor, Incremental Relation Extractor, and Graph Integrator and Visualization. Our method demonstrates superior performance compared to baseline methods across three scenarios: converting scientific papers to graphs, websites to graphs, and CVs to graphs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。