A caption annotation scheme for georeferencing images

ABSTRACT

We propose a caption annotation scheme to address the task of obtaining a geo-footprint for an image from caption text, introducing tags to identify image subject and using SpatialML to annotate and ground references to image subject location.

REFERENCES

• 1: ACE08 Task: http://projects.ldc.upenn.edu/ace/annotation.
• 2: Defense Advanced Research Projects Agency. (1998). Proc. of the 7th Message Understanding Conference (MUC7).
• 3: Christopher B. Jones , Ross S. Purves, Geographical information retrieval, International Journal of Geographical Information Science, v.22 n.3, p.219-228, January 2008 [doi>10.1080/13658810701626343]
• 4: Leidner, J. L. (2006). Toponym Resolution: A First Large-Scale Comparative Evaluation. Research Report EDI-INF-RR-0839.
• 5: Mani, I., Hitzeman, J., Harris, D. R., Quimby, R. and Wellner, B. (2008). SpatialML: Annotation Scheme, Corpora and Tools. Proceedings of LREC 2008.
• 6: Erik Rauch , Michael Bukatin , Kenneth Baker, A confidence-based framework for disambiguating geographic terms, Proceedings of the HLT-NAACL 2003 workshop on Analysis of geographic references, p.50-54, May 31, 2003 [doi>10.3115/1119394.1119402]

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL
      H.3.1 Content Analysis and Indexing
          Subjects: Indexing methods

Additional Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL
      H.3.1 Content Analysis and Indexing
          Subjects: Linguistic processing

General Terms:
Design, Experimentation, Standardization

Keywords:
evaluation, geo-referencing, gir, image captions, location information, semantic annotation, text analysis