English

Zero-shot Task Transfer for Invoice Extraction via Class-aware QA Ensemble

Information Retrieval 2021-08-16 v1 Artificial Intelligence Computation and Language Machine Learning

Abstract

We present VESPA, an intentionally simple yet novel zero-shot system for layout, locale, and domain agnostic document extraction. In spite of the availability of large corpora of documents, the lack of labeled and validated datasets makes it a challenge to discriminatively train document extraction models for enterprises. We show that this problem can be addressed by simply transferring the information extraction (IE) task to a natural language Question-Answering (QA) task without engineering task-specific architectures. We demonstrate the effectiveness of our system by evaluating on a closed corpus of real-world retail and tax invoices with multiple complex layouts, domains, and geographies. The empirical evaluation shows that our system outperforms 4 prominent commercial invoice solutions that use discriminatively trained models with architectures specifically crafted for invoice extraction. We extracted 6 fields with zero upfront human annotation or training with an Avg. F1 of 87.50.

Cite

@article{arxiv.2108.06069,
  title  = {Zero-shot Task Transfer for Invoice Extraction via Class-aware QA Ensemble},
  author = {Prithiviraj Damodaran and Prabhkaran Singh and Josemon Achankuju},
  journal= {arXiv preprint arXiv:2108.06069},
  year   = {2021}
}
R2 v1 2026-06-24T05:05:11.156Z