Landmarks and Regions: A Robust Approach to Data Extraction

TL;DR

This paper introduces a landmark-based data extraction method that improves robustness to format changes in semi-structured documents by focusing on small regions of interest, inspired by human document processing.

Contribution

The paper presents a novel landmark and region-based approach for data extraction, implemented in the LRSyn tool, enhancing robustness over traditional methods.

Findings

Robustness to format changes demonstrated in HTML and scanned documents

Effective extraction of specific fields like passenger info and prices

LRSyn outperforms traditional extraction methods in varied formats

Abstract

We propose a new approach to extracting data items or field values from semi-structured documents. Examples of such problems include extracting passenger name, departure time and departure airport from a travel itinerary, or extracting price of an item from a purchase receipt. Traditional approaches to data extraction use machine learning or program synthesis to process the whole document to extract the desired fields. Such approaches are not robust to format changes in the document, and the extraction process typically fails even if changes are made to parts of the document that are unrelated to the desired fields of interest. We propose a new approach to data extraction based on the concepts of landmarks and regions. Humans routinely use landmarks in manual processing of documents to zoom in and focus their attention on small regions of interest in the document. Inspired by this human intuition, we use the notion of landmarks in program synthesis to automatically synthesize extraction programs that first extract a small region of interest, and then automatically extract the desired value from the region in a subsequent step. We have implemented our landmark-based extraction approach in a tool LRSyn, and show extensive evaluation on documents in HTML as well as scanned images of invoices and receipts. Our results show that our approach is robust to various types of format changes that routinely happen in real-world settings.