Scholarlink

<p>This paper presents a neurosymbolic framework for information extraction from documents, evaluated on transactional documents. We introduce a schema-based approach that integrates symbolic validation methods to enable more effective zero-shot output and knowledge distillation. The methodology uses language models to generate candidate extractions, which are then filtered through syntactic-, task-, and domain-level validation to ensure adherence to domain-specific arithmetic constraints. Our contributions include a comprehensive schema for transactional documents, relabeled datasets, and an approach for generating high-quality labels for knowledge distillation. Experimental results demonstrate significant improvements in <InlineEquation ID="IEq1"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="10032_2025_530_Article_IEq1.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="18" /> </InlineMediaObject> <EquationSource Format="TEX">\(F_1\)</EquationSource> <EquationSource Format="MATHML"><math> <msub> <mi>F</mi> <mn>1</mn> </msub> </math></EquationSource> </InlineEquation>-scores and accuracy, highlighting the effectiveness of neurosymbolic validation in transactional document processing.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Neurosymbolic Information Extraction from Transactional Documents

  • 期刊论文

  • 发表日期：

    2025年6月16日

查看全文
  • Arthur Hemmer,
  • Mickaël Coustaty,
  • Nicola Bartolo,
  • Jean-Marc Ogier

摘要

This paper presents a neurosymbolic framework for information extraction from documents, evaluated on transactional documents. We introduce a schema-based approach that integrates symbolic validation methods to enable more effective zero-shot output and knowledge distillation. The methodology uses language models to generate candidate extractions, which are then filtered through syntactic-, task-, and domain-level validation to ensure adherence to domain-specific arithmetic constraints. Our contributions include a comprehensive schema for transactional documents, relabeled datasets, and an approach for generating high-quality labels for knowledge distillation. Experimental results demonstrate significant improvements in \(F_1\) F 1 -scores and accuracy, highlighting the effectiveness of neurosymbolic validation in transactional document processing.