# One-shot Information Extraction from Document Images using Neuro-Deductive Program Synthesis

arXiv: https://arxiv.org/abs/1906.02427 · HTML: https://mlsanity.com/paper/1906.02427/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jun 2019.

## Built on by (most cited first, 8 of 8)

- [DocILE Benchmark for Document Information Localization and Extraction](https://mlsanity.com/paper/2302.05658/) (2023)
- [Business Document Information Extraction: Towards Practical Benchmarks](https://mlsanity.com/paper/2206.11229/) (2022)
- [Synthesizing Visual Concepts as Vision-Language Programs](https://mlsanity.com/paper/2511.18964/) (2025)
- [One-shot Key Information Extraction from Document with Deep Partial Graph Matching](https://mlsanity.com/paper/2109.13967/) (2021)
- [Combining Deep Learning and Reasoning for Address Detection in Unstructured Text Documents](https://mlsanity.com/paper/2202.03103/) (2022)
- [DocILE 2023 Teaser: Document Information Localization and Extraction](https://mlsanity.com/paper/2301.12394/) (2023)
- [Neural Feature-Adaptation for Symbolic Predictions Using Pre-Training and Semantic Loss](https://mlsanity.com/paper/2211.16047/) (2022)
- [Zero-shot Classification using Hyperdimensional Computing](https://mlsanity.com/paper/2401.16876/) (2024)

## Abstract (arXiv)

Our interest in this paper is in meeting a rapidly growing industrial demand for information extraction from images of documents such as invoices, bills, receipts etc. In practice users are able to provide a very small number of example images labeled with the information that needs to be extracted. We adopt a novel two-level neuro-deductive, approach where (a) we use pre-trained deep neural networks to populate a relational database with facts about each document-image; and (b) we use a form of deductive reasoning, related to meta-interpretive learning of transition systems to learn extraction programs: Given task-specific transitions defined using the entities and relations identified by the neural detectors and a small number of instances (usually 1, sometimes 2) of images and the desired outputs, a resource-bounded meta-interpreter constructs proofs for the instance(s) via logical deduction; a set of logic programs that extract each desired entity is easily synthesized from such proofs. In most cases a single training example together with a noisy-clone of itself suffices to learn a program-set that generalizes well on test documents, at which time the value of each entity is determined by a majority vote across its program-set. We demonstrate our two-level neuro-deductive approach on publicly available datasets ("Patent" and "Doctor's Bills") and also describe its use in a real-life industrial problem.