Bibliographic attribute extraction from erroneous references based on a statistical model
- 23 January 2004
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
In this paper, we propose a method for extracting bibliographic attributes from reference strings captured using Optical Character Recognition (OCR) and an extended hidden Markov model. Bibliographic attribute extraction can be used in two ways. One is reference parsing in which attribute values are extracted from OCR-processed references for bibliographic matching. The other is reference alignment in which attribute values are aligned to the bibliographic record to enrich the vocabulary of the bibliographic database. In this paper, we first propose a statistical model for attribute extraction that represents both the syntactical structure of references and OCR error patterns. Then, we perform experiments using bibliographic references obtained from scanned images of papers in journals and transactions and show that useful attribute values are extracted from OCR-processed references. We also show that the proposed model has advantages in reducing the cost of preparing training data, a critical problem in rule-based systems.Keywords
This publication has 15 references indexed in Scilit:
- DVHMM: variable length text recognition error modelPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Statistical Analysis of Bibliographic Strings for Constructing an Integrated Document SpacePublished by Springer Nature ,2002
- Digital libraries and autonomous citation indexingComputer, 1999
- Autonomous citation matchingPublished by Association for Computing Machinery (ACM) ,1999
- CiteSeerPublished by Association for Computing Machinery (ACM) ,1998
- A Probabilistic Theory of Pattern RecognitionPublished by Springer Nature ,1996
- Bibliography references validation using emergent architecturePublished by Institute of Electrical and Electronics Engineers (IEEE) ,1995
- Techniques for automatically correcting words in textACM Computing Surveys, 1992
- A prototype document image analysis system for technical journalsComputer, 1992
- An investigation of different string coding methodsJournal of the American Society for Information Science, 1984