Result Details

SmartScrape: A Neuro-Symbolic Web Information Extraction

IMANOV, G.; BURGET, R. SmartScrape: A Neuro-Symbolic Web Information Extraction. In Lecture Notes in Computer Science. Lecture Notes in Computer Science. Lyon: Springer Science and Business Media Deutschland GmbH, 2026. iss. 16625 LNCS, p. 301-305. ISBN: 9783032293718.
Type
conference paper
Language
English
Authors
Abstract

We introduce SmartScrape, a neuro-symbolic framework for extracting structured information from the web. The task addressed is to extract records that follow a predefined schema from semi-structured sources, such as product web pages. The system integrates a Graph Neural Network (GNN) that scores content elements with an Integer Linear Programming (ILP) constraint solver, which guarantees schema consistency, uniqueness, and additional logical and presentation constraints. We illustrate the method on a basic (product, price) extraction scenario. The implemented system outputs visual proof-carrying justifications, supports drift detection using the stability metric σ(P), and we also include an ablation study contrasting ILP-based and greedy reasoning modes. On a set of 100 pages, SmartScrape attains 97% field-level accuracy with no constraint violations.

Keywords

Constraint solving | Drift detection | FitLayout | GNN | ILP | Web information extraction

URL
Published
2026
Pages
301–305
Journal
Lecture Notes in Computer Science, no. 16625 LNCS, ISSN
Proceedings
Lecture Notes in Computer Science
Conference
26th International Conference on Web Engineering
ISBN
9783032293718
Publisher
Springer Science and Business Media Deutschland GmbH
Place
Lyon
DOI
EID Scopus
BibTeX
@inproceedings{BUT212243,
  author="Ganjali {Imanov} and Radek {Burget}",
  title="SmartScrape: A Neuro-Symbolic Web Information Extraction",
  booktitle="Lecture Notes in Computer Science",
  year="2026",
  journal="Lecture Notes in Computer Science",
  number="16625 LNCS",
  pages="301--305",
  publisher="Springer Science and Business Media Deutschland GmbH",
  address="Lyon",
  doi="10.1007/978-3-032-29372-5\{_}29",
  isbn="9783032293718",
  url="https://link.springer.com/chapter/10.1007/978-3-032-29372-5_29"
}
Projects
Aplikace pokročilých technik pro kybernetickou bezpečnost a efektivní zpracování heterogenních dat., BUT, Vnitřní projekty VUT, FIT-S-26-9019, start: 2026-03-01, end: 2027-02-28, running
Departments
Back to top