2015/05/05 by Arun S. Maiya, D. W. Visser, Dale Visser +4
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #H.3.3 #Handwritten Text Recognition Techniques #I.2.7 #Information Retrieval (cs.IR) #Mathematics, Computing, and Information Processing #Semantic Web and Ontologies #cs.CL #cs.IR
paper · pdf · doi:10.48550/arxiv.1505.01072
4 pages; 38th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR '15)
arxiv created 2015/05/05 · openalex publication_date 2015/05/05 · arxiv updated 2015/05/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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/m2 ). 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 μm"). Finally, we present MQSearch: the realization of a search engine with full support for measured information.