Visual Abstract

Visual abstract

Abstract

This research centers on automated invoice processing, entailing an analysis of existing methods and systems to construct a comprehensive overview. The objective is to develop a pipeline based on established software and to construct a corresponding testing framework. Leveraging this foundation, the aim is to refine the pipeline and evaluate its efficacy within the established testing framework. The subsequent findings shed light on the performance and potential enhancements of the automated invoice processing pipeline.

Slides

Invoices Recognition with Large Language Models

Lecture Recordings

Readings

1. Šárka Ščavnická et al.: Towards General Document Understanding through Question Answering  https://nlp.fi.muni.cz/raslan/2022/paper17.pdf 
2. Martin Geletka et al.:  Information Extraction from Business Documents A Case Study  https://nlp.fi.muni.cz/raslan/2022/paper18.pdf 
   
3. Rossum AI: Docile  https://docile.rossum.ai/ 
4. Štěpán Šimša et al.:  DocILE Benchmark for Document Information Localization and Extraction https://arxiv.org/abs/2302.05658 
   

Catering

None :-/.