Advertisement

Locating and parsing bibliographic references in HTML medical articles

  • Jie ZouEmail author
  • Daniel Le
  • George R. Thoma
Original Paper

Abstract

The set of references that typically appear toward the end of journal articles is sometimes, though not always, a field in bibliographic (citation) databases. But even if references do not constitute such a field, they can be useful as a preprocessing step in the automated extraction of other bibliographic data from articles, as well as in computer-assisted indexing of articles. Automation in data extraction and indexing to minimize human labor is key to the affordable creation and maintenance of large bibliographic databases. Extracting the components of references, such as author names, article title, journal name, publication date and other entities, is therefore a valuable and sometimes necessary task. This paper describes a two-step process using statistical machine learning algorithms, to first locate the references in HTML medical articles and then to parse them. Reference locating identifies the reference section in an article and then decomposes it into individual references. We formulate this step as a two-class classification problem based on text and geometric features. An evaluation conducted on 500 articles drawn from 100 medical journals achieves near-perfect precision and recall rates for locating references. Reference parsing identifies the components of each reference. For this second step, we implement and compare two algorithms. One relies on sequence statistics and trains a Conditional Random Field. The other focuses on local feature statistics and trains a Support Vector Machine to classify each individual word, followed by a search algorithm that systematically corrects low confidence labels if the label sequence violates a set of predefined rules. The overall performance of these two reference-parsing algorithms is about the same: above 99% accuracy at the word level, and over 97% accuracy at the chunk level.

Keywords

HTML document analysis Document Object Model (DOM) Reference parsing Support Vector Machine (SVM) Conditional Random Field (CRF) 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Aronson, A.R., Bodenreider, O., Chang, H.F., Humphrey, S.M., Mork, J.G., Nelson, S.J., Rindflesch, T.C., Wilbur, W.J.: The NLM indexing initiative. In: Proceedings of AMIA Symposium, pp. 17–21 (2000)Google Scholar
  2. 2.
    Baird, H.S., Jones, S.E., Fortune, S.J.: Image segmentation by shape-directed covers. In: Proceedings of International Conference Pattern Recognition, pp. 820–825 (1990)Google Scholar
  3. 3.
    Besagni D., Belaïd A., Benet N.: A segmentation method for bibliographic references by contextual tagging of fields. Proc. ICDAR 1, 384–388 (2003)Google Scholar
  4. 4.
    Buyukkokten, O., Garcia-Molina, H., Paepche, A.: Accordion summarization for end-game browsing on PDAs and cellular phones. In: Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, pp. 213–220 (2001)Google Scholar
  5. 5.
    Chang, C.-C., Lin, C.-J.: LIBSVM: a library for support vector machines. Software available at http://www.csie.ntu.edu.tw/~cjlin/libsvm (2001)
  6. 6.
    Chowdhury G.: Template mining for information extraction from digital documents. Libr. Trends 48(1), 182–208 (1999)Google Scholar
  7. 7.
    Cortez E., da Silva A.S., Goncalves M.A., Mesquita F., de Moura E.S.: A flexible approach for extracting metadata from bibliographic citations. J. Am. Soc. Inf. Sci. Technol. 60(6), 1144–1158 (2009)CrossRefGoogle Scholar
  8. 8.
    Councill, I.G., Giles, C.L., Kan, M.-Y.: ParsCit: an open-source CRF reference string parsing package. In: Proceedings of the 6th International Language Resources and Evaluation (2008)Google Scholar
  9. 9.
    Day, M.-Y., Tsai, T.-H., Sung, C.-L., Lee, C.-W., Wu, S.-H., Ong, C.-S., Hsu, W.-L.: A knowledge-based approach to citation extraction. In: IEEE International Conference Information Reuse and Integration, pp. 50–55 (2005)Google Scholar
  10. 10.
    Day M.-Y., Tsai R.T.-H., Sung C.-L., Hsieh C.-C., Lee C.-W., Wu S.-H., Wu K.-P., Ong C.-S., Hsu W.-L.: Reference metadata extraction using a hierarchical knowledge representation framework. Decis. Support Syst. 43(1), 152–167 (2007)CrossRefGoogle Scholar
  11. 11.
    Diao, Y., Lu, H., Chen, S., Tian, Z.: Toward learning based web query processing. In: Proceedings of International Conference on Very Large Databases, pp. 317–328 (2000)Google Scholar
  12. 12.
    Ding, Y., Chowdhury, G., Foo, S.: Template mining for the extraction of citation from digital documents. In: Proceedings of the 2nd Asian Digital Library Conference, pp. 47–62 (1999)Google Scholar
  13. 13.
    Galavotti, L., Sebastiani, F., Simi, M.: Experiments on the use of feature selection and negative evidence in automated text categorization. In: Proceedings of ECDL, pp. 59–68 (2000)Google Scholar
  14. 14.
    Ha, J., Haralick, R., Phillips, I.: Recursive X-Y cut using bounding boxes of connected components. In: Proceedings 3rd International Conference Document Analysis and Recognition, pp. 952–955 (1995)Google Scholar
  15. 15.
    Hauser S.E., Le D.X., Thoma G.R.: Automated zone correction in bitmapped document images. Proc. SPIE: Document Recognit. Retr. VII 3976, 248–258 (2000)Google Scholar
  16. 16.
    Huang, I.-A., Ho, J.-M., Kao, H.-Y., Lin, W.-C.: Extracting citation metadata from online publication lists using BLAST. In: Proceedings of the 8th Pacific–Asia Conference on Knowledge Discovery and Data Mining, pp. 26–28 (2004)Google Scholar
  17. 17.
    Jain A.K., Yu B.: Document representation and its application to page decomposition. IEEE Trans. Pattern Recognit. Mach. Intell. 20(3), 294–308 (1998)CrossRefGoogle Scholar
  18. 18.
    Kaasinen, E., Aaltonen, M., Kolari, J., Melakoski, S., Laakko, T.: Two approaches to bringing internet services to WAP devices. In: Proceedings of the 9th International World Wide Web Conference, pp. 231–246 (2000)Google Scholar
  19. 19.
    Kim, I., Le, D., Thoma, G.R.: Identification of “comment-on sentences” in online biomedical documents using support vector machines. In: Proceedings of the SPIE Conference on Document Recognition and Retrieval, vol. 68150, pp. X1–X9 (2007)Google Scholar
  20. 20.
    Kim, J., Le, D., Thoma, G.R.: Automatic labeling in document images. In: Proceedings of the SPIE Conference on Document Recognition and Retrieval, pp. 111–122 (2001)Google Scholar
  21. 21.
    Klink S., Kieninger T.: Rule-based document structure understanding with a fuzzy combination of layout and textual features. Int. J. Document Anal. Recognit. 4, 18–26 (2001)CrossRefGoogle Scholar
  22. 22.
    Lafferty, J., McCallum, A., and Pereira, F.: Conditional random fields: probabilistic models for segmenting and labeling sequence data. In: Proceedings of the ICML, pp. 282–289 (2001)Google Scholar
  23. 23.
    Lawrence S., Giles C.L., Bollacker K.: Digital libraries and autonomous citation indexing. IEEE Comput. 32(6), 67–71 (1999)Google Scholar
  24. 24.
    Likforman-Sulem L., Vaillant P., de Bodard A.: Automatic name extraction from degraded document images. Pattern. Anal. Appl. 9(2), 211–227 (2006)CrossRefMathSciNetGoogle Scholar
  25. 25.
    Liu B., Grossman R., Zhai Y.: Mining Web pages for data records. IEEE Intell. Syst. 19(6), 49–55 (2004)CrossRefGoogle Scholar
  26. 26.
    McCallum, A.K.: MALLET: a machine learning for language toolkit. http://mallet.cs.umass.edu (2002)
  27. 27.
    Nagy G., Seth S., Viswanathan M.: A prototype document image analysis system for technical journals. Computer 25, 10–22 (1992)CrossRefGoogle Scholar
  28. 28.
    Nagy G.: Twenty years of document image analysis in PAMI. IEEE Trans. Pattern Anal. Mach. Intell. 22(1), 38–62 (2000)CrossRefGoogle Scholar
  29. 29.
    O’Gorman L.: The document spectrum for page layout analysis. IEEE Trans. Pattern Recognit. Mach. Intell. 15, 1162–1173 (1993)CrossRefGoogle Scholar
  30. 30.
    Okada, T., Takasu, A., Adachi, J.: Bibliographic component extraction using support vector machines and hidden Markov models. In: Proceedings of the ECDL, pp. 501–512 (2004)Google Scholar
  31. 31.
    Parmentier, F., Belaïd, A.: Logical structure recognition of scientific bibliographic references. In: Proceedings of the ICDAR, pp. 1072–1076 (1997)Google Scholar
  32. 32.
    Pavlidis T., Zhou J.: Page segmentation and classification. Graph. Models Image Process. 54, 484–496 (1992)CrossRefGoogle Scholar
  33. 33.
    Peng, F., McCallum, A.: Accurate information extraction from research papers using conditional random fields. In: Proceedings of Human Language Technology Conference, pp. 329–336 (2004)Google Scholar
  34. 34.
    Reis, D.C., Golgher, P.B., Silva, A.S., Laender, A.F.: Automatic web news extraction using tree edit distance. In: Proceedings of the WWW, pp. 502–511 (2004)Google Scholar
  35. 35.
    Sebastiani F.: Machine learning in automated text categorization. ACM Comput. Surv. 34(1), 1–47 (2002)CrossRefGoogle Scholar
  36. 36.
    Sutton C., McCallum A.: An introduction to conditional random fields for relational learning. In: Getoor, L., Taskar, B. (eds) Introduction to statistical relational learning, MIT Press, Cambridge (2006)Google Scholar
  37. 37.
    Takasu, A.: Bibliographic attribute extraction from erroneous references based on a statistical model. In: Proceedings of the JCDL, pp. 49–60 (2003)Google Scholar
  38. 38.
    Zhai Y., Liu B.: Structure data extraction from the Web based on partial tree alignment. IEEE Tran. Knowl. Data Eng. 18(12), 1614–1628 (2006)CrossRefGoogle Scholar
  39. 39.
    Zou, J., Le, D., Thoma, G.R.: Structure and content analysis for HTML medical articles: a hidden markov model approach. In: Proceedings of the DocEng, pp. 119–201 (2007)Google Scholar
  40. 40.
    Zou J., Le D., Thoma G.R.: Extracting a sparsely-located named entity from online HTML medical articles using support vector machine. Proc. Document Recognit. Retr. 68150, P1–P10 (2008)Google Scholar
  41. 41.
  42. 42.

Copyright information

© Springer-Verlag 2009

Authors and Affiliations

  1. 1.Lister Hill National Center for Biomedical Communications, National Library of MedicineNational Institutes of HealthBethesdaUSA

Personalised recommendations