- Abstract:
-
Named entity tagging comprises the sub-tasks of identifying a text span and classifying it, but this view ignores the re- lationship between the entities and the world. Spatial and temporal entities ground events in space-time, and this rela- tionship is vital for applications such as question answering and event tracking. There is much recent work regarding the temporal dimension [13, 10], but no extensive study of the spatial dimension. I propose to investigate how spatial named entities (which are often referentially ambiguous) can be automatically re- solved with respect to an extensional coordinate model (to- ponym resolution), using hybrid heuristic/statistical meth- ods. The major contributions of this research project are a corpus of text manually annotated for spatial named entities with their model correlates as a training/evaluation resource [4] and a novel method to spatially ground toponyms in text.
- Links To Paper
- Archived Abstract
- Extended Abstract
- Bibtex format
- @InProceedings{EDI-INF-RR-1025,
- author = {
Jochen Leidner
},
- title = {Toponym Resolution in Text: "Which Sheffield is it?" [Doctoral Consortium]},
- book title = {Proceedings of the 28th Annual International ACM SIGIR Conference on Research and Development on Information Retrieval (SIGIR)},
- publisher = {ACM},
- year = 2004,
- pages = {602-602},
- url = {http://portal.acm.org/citation.cfm?doid=1008992.1009147},
- }
|
