Mining Measured Information from Text

TL;DR

This paper introduces a robust rule-based system for extracting measured quantities and their properties from text, supporting diverse units and formats, and demonstrates its application in a specialized search engine.

Contribution

It presents a novel rule-based method for extracting measured information and properties from text, including handling format errors, and integrates this into a search engine.

Findings

Supports a wide range of measurement units

Robust to format conversion errors

Enables specialized search for measured data

Abstract

We present an approach to extract measured information from text (e.g., a 1370 degrees C melting point, a BMI greater than 29.9 kg/m^2 ). Such extractions are critically important across a wide range of domains - especially those involving search and exploration of scientific and technical documents. We first propose a rule-based entity extractor to mine measured quantities (i.e., a numeric value paired with a measurement unit), which supports a vast and comprehensive set of both common and obscure measurement units. Our method is highly robust and can correctly recover valid measured quantities even when significant errors are introduced through the process of converting document formats like PDF to plain text. Next, we describe an approach to extracting the properties being measured (e.g., the property "pixel pitch" in the phrase "a pixel pitch as high as 352 {\mu}m"). Finally, we present MQSearch: the realization of a search engine with full support for measured information.