Summary of the paper
| Title | Fine-Grained Geographical Relation Extraction from Wikipedia |
|---|---|
| Authors | Andre Blessing and Hinrich Schütze |
| Abstract | In this paper, we present work on enhancing the basic data resource ofa context-aware system. Electronic text offers a wealth ofinformation about geospatial data and can be used to improve thecompleteness and accuracy of geospatial resources (e.g., gazetteers).First, we introduce a supervised approach to extracting geographicalrelations on a fine-grained level. Second, we present a novel way ofusing Wikipedia as a corpus based on self-annotation. Aself-annotation is an automatically created high-quality annotationthat can be used for training and evaluation. Wikipedia contains twotypes of different context: (i) unstructured text and (ii) structureddata: templates (e.g., infoboxes about cities), lists and tables. Weuse the structured data to annotate the unstructured text. Finally, theextracted fine-grained relations are used to complete gazetteer data. Theprecision and recall scores of more than 97 percent confirm that astatistical IE pipeline can be used to improve the data quality ofcommunity-based resources. |
| Language | Corpus (creation, annotation, etc.) |
| Topics | Information Extraction, Information Retrieval, Acquisition, Corpus (creation, annotation, etc.) |
Full paper  |
Fine-Grained Geographical Relation Extraction from Wikipedia |
| Bibtex | @InProceedings{BLESSING10.519, author = {Andre Blessing and Hinrich Schütze}, title = {Fine-Grained Geographical Relation Extraction from Wikipedia}, booktitle = {Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC'10)}, year = {2010}, month = {may}, date = {19-21}, address = {Valletta, Malta}, editor = {Nicoletta Calzolari (Conference Chair), Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odjik, Stelios Piperidis, Mike Rosner, Daniel Tapias}, publisher = {European Language Resources Association (ELRA)}, isbn = {2-9517408-6-7}, language = {english} } |