期刊
EXPERIMENTAL IR MEETS MULTILINGUALITY, MULTIMODALITY, AND INTERACTION (CLEF 2022)
卷 13390, 期 -, 页码 105-117出版社
SPRINGER INTERNATIONAL PUBLISHING AG
DOI: 10.1007/978-3-031-13643-6_8
关键词
Document Understanding; Survey; Benchmarks; Datasets
This paper explores the problem of information extraction from semi-structured documents, highlighting the practical needs missing in common definitions and proposing the Key Information Localization and Extraction (KILE) and Line Item Recognition (LIR) problems. Due to the legal protection of content in semi-structured business documents, there is a lack of relevant datasets and benchmarks.
Information extraction from semi-structured documents is crucial for frictionless business-to-business (B2B) communication. While machine learning problems related to Document Information Extraction (IE) have been studied for decades, many common problem definitions and benchmarks do not reflect domain-specific aspects and practical needs for automating B2B document communication. We review the landscape of Document IE problems, datasets and benchmarks. We highlight the practical aspects missing in the common definitions and define the Key Information Localization and Extraction (KILE) and Line Item Recognition (LIR) problems. There is a lack of relevant datasets and benchmarks for Document IE on semi-structured business documents as their content is typically legally protected or sensitive. We discuss potential sources of available documents including synthetic data.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据