University of Illinois Urbana-Champaign

Automatic Metadata Extraction Using Machine Learning

Wei, Qin; Heidorn, P. Bryan

Permalink

https://hdl.handle.net/2142/9139

Description

Title
Automatic Metadata Extraction Using Machine Learning
Author(s)
  • Wei, Qin
  • Heidorn, P. Bryan
Issue Date
2008-10-17
Keyword(s)
  • Metadata Extraction
  • Machine Learning
Abstract
The information in museum specimen labels is not well recognized and used. The reason is mainly because this information is not part of the information retrieval systems. It is very expensive to have human to hand input the data to the system. We are using machine learning tools to automatically extract Darwin Core (DwC) and other metadata from these labels processed through Optical Character Recognition (OCR). The DwC is a metadata profile describing the core set of access points for search and retrieval of natural history collections and observation databases. Using the HERBIS Learning System (HLS) we extract 74 independent elements from these labels. The automated text extraction tools are provided as a web service so that users can reference digital images of specimens and receive back an extended Darwin Core XML representation of the content of the label. This automated extraction task is made more difficult by the high variability of museum label formats, OCR errors and the open class nature of some elements. Here, we introduce our overall system architecture, and variability robust solutions including, the application of Hidden Markov and Naïve Bayes machine learning models, data cleaning, use of field element identifiers, and specialist learning models. The techniques developed here could be adapted to any metadata extraction situation with noisy text and weakly ordered elements.
Type of Resource
text
Language
en
Permalink
http://hdl.handle.net/2142/9139

Owning Collections

Student Publications and Research - Information Sciences PRIMARY
Publications, conference papers, and other research and scholarship of iSchool students.