SemTag and seeker: bootstrapping the semantic web via automated semantic annotation
WWW '03 Proceedings of the 12th international conference on World Wide Web
Towards the self-annotating web
Proceedings of the 13th international conference on World Wide Web
KIM – a semantic platform for information extraction and retrieval
Natural Language Engineering
Gimme' the context: context-driven automatic semantic annotation with C-PANKOW
WWW '05 Proceedings of the 14th international conference on World Wide Web
Survey of semantic annotation platforms
Proceedings of the 2005 ACM symposium on Applied computing
AAAI'06 proceedings of the 21st national conference on Artificial intelligence - Volume 2
Hi-index | 0.00 |
Due to ambiguity, search engines for scientific literatures may not return right search results. One efficient solution to the problems is to automatically annotate literatures and attach the semantic information to them. Generally, semantic annotation requires identifying entities before attaching semantic information to them. However, due to abbreviation and other reasons, it is very difficult to identify entities correctly. The paper presents a Semantic Annotation System for Literature (SASL), which utilizes Wikipedia as knowledge base to annotate literatures. SASL mainly attaches semantic to terminology, academic institutions, conferences, and journals etc. Many of them are usually abbreviations, which induces ambiguity. Here, SASL uses regular expressions to extract the mapping between full name of entities and their abbreviation. Since full names of several entities may map to a single abbreviation, SASL introduces Hidden Markov Model to implement name disambiguation. Finally, the paper presents the experimental results, which confirm SASL a good performance.