ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
Contextual search and name disambiguation in email using graphs
SIGIR '06 Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval
| Hi-index | 0.01 |
One step in the curation process is geneId finding---the task of finding the database identifier of every gene discussed in an article. GeneId-finding was studied experimentally in the BioCreatIvE challenge (Hirschman et al., 2005), which developed testbed problems for each of three model organisms (yeast, mice, and fruitflies). Here we consider geneId ranking, a relaxation of geneId-finding in which the system provides a ranked list of genes that might be discussed by the document. We show how multiple named entity recognition (NER) methods can be combined into a single high-performance geneIdranking system.