A Large-Scale Exploration of Effective Global Features for a Joint Entity Detection and Tracking Model. (arXiv:0907.0807v1 [cs.CL])

1. Entity detection and tracking (EDT) is the task of identifying textual mentions of real-world entities in documents, extending the named entity detection and coreference resolution task by considering mentions other than names (pronouns, definite descriptions, etc.). Like NE tagging and coreference resolution, most solutions to the EDT task separate out the mention detection aspect from the coreference aspect. By doing so, these solutions are limited to using only local features for learning. In contrast, by modeling both aspects of the EDT task simultaneously, we are able to learn using highly complex, non-local features. We develop a new joint EDT model ... (Read Full Article)

   Bookmark or Share this article

   
   

   Related Articles

   • Induction of Word and Phrase Alignments for Automatic Document Summarization. (arXiv:0907.0804v1 [cs.CL])
   • also written by Hal Daumé III, Daniel Marcu
   • Learning as Search Optimization: Approximate Large Margin Methods for Structured Prediction. (arXiv:0907.0809v1 [cs.LG])
   • also written by Hal Daumé III, Daniel Marcu
   • Entropy estimation of symbol sequences. (arXiv:cond-mat/0203436v1 [cond-mat.stat-mech] Cross Listed)
   • also published in arxiv.org

   • Clairlib Documentation v1.03
   • also published in arxiv.org
   • Framework and Resources for Natural Language Parser Evaluation
   • also published in arxiv.org
   • A Noisy-Channel Model for Document Compression. (arXiv:0907.0806v1 [cs.CL])
   • also written by Hal Daumé III, Daniel Marcu

Login to comment.