Statements：利用大型语言模型从表格中进行面向ESG KPI的通用信息抽取
Statements: Universal Information Extraction from Tables with Large Language Models for ESG KPIs
AI总结：
本文提出Statements数据结构和表格转statement的通用信息抽取任务，构建超10万标注表格的SemTabNet数据集，基于T5模型在ESG报告表格上实现82%的抽取相似度，显著优于基线。
摘要：
环境、社会和治理（ESG）关键绩效指标（KPI）用于评估组织在气候变化、温室气体排放、水资源消耗、废弃物管理、人权、多样性和政策等问题上的表现。ESG报告通过表格传达这些有价值的定量信息。不幸的是，由于表格结构和内容的高度可变性，提取这些信息十分困难。我们提出了Statements，一种新颖的领域无关数据结构，用于抽取定量事实及相关信息。我们提出将表格转换为statements，作为一项新的有监督深度学习通用信息抽取任务。我们引入了SemTabNet——一个包含超过10万张标注表格的数据集。通过研究一系列基于T5的Statement抽取模型，我们最好的模型生成的statements与真实标注的相似度达到82%（基线为21%）。我们通过将该模型应用于来自ESG报告的2700多张表格，展示了statements的优势。statements的同质化特性使得能够对大规模ESG报告集合中的广泛信息进行探索性数据分析。
英文摘要：
Environment, Social, and Governance (ESG) KPIs assess an organization's performance on issues such as climate change, greenhouse gas emissions, water consumption, waste management, human rights, diversity, and policies. ESG reports convey this valuable quantitative information through tables. Unfortunately, extracting this information is difficult due to high variability in the table structure as well as content. We propose Statements, a novel domain agnostic data structure for extracting quantitative facts and related information. We propose translating tables to statements as a new supervised deep-learning universal information extraction task. We introduce SemTabNet - a dataset of over 100K annotated tables. Investigating a family of T5-based Statement Extraction Models, our best model generates statements which are 82% similar to the ground-truth (compared to baseline of 21%). We demonstrate the advantages of statements by applying our model to over 2700 tables from ESG reports. The homogeneous nature of statements permits exploratory data analysis on expansive information found in large collections of ESG reports.
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。
