539 citations
- Massachusetts Institute of TechnologyUS15 papers
- Sandia National LaboratoriesUS11 papers
- Harvard UniversityUS8 papers
- Brookhaven National LaboratoryUS7 papers
- Eaton (United States)US7 papers
- University of Maryland, College ParkUS7 papers
- University of ArizonaUS6 papers
- George Mason UniversityUS5 papers
- University of VermontUS5 papers
- University of WashingtonUS4 papers
- California Institute of TechnologyUS3 papers
- Center for Astrophysics Harvard & SmithsonianUS3 papers
7 papers · 1 filter
Using existing systems to supplement small amounts of annotated grammatical relations training data
Alexander Yeh
Grammatical relationships (GRs) form an important level of natural language processing, but different sets of GRs are useful for different purposes. Therefore, one may often only h…
Practical Quantum Cryptography: A Comprehensive Analysis (Part One)
G. Gilbert, M. Hamrick
We perform a comprehensive analysis of practical quantum cryptography (QC) systems implemented in actual physical environments via either free-space or fiber-optic cable quantum ch…
More accurate tests for the statistical significance of result differences
Alexander Yeh
Statistical significance testing of differences in values of metrics like recall, precision and balanced F-score is a necessary part of empirical natural language processing. Unfor…
Comparing two trainable grammatical relations finders
Alexander Yeh
Grammatical relationships (GRs) form an important level of natural language processing, but different sets of GRs are useful for different purposes. Therefore, one may often only h…
ATLAS: A flexible and extensible architecture for linguistic annotation
Steven Bird, David Day, John Garofolo +3
We describe a formal model for annotating linguistic artifacts, from which we derive an application programming interface (API) to a suite of tools for manipulating these annotatio…
Bagging and Boosting a Treebank Parser
John C. Henderson, Eric Brill
Bagging and boosting, two effective machine learning techniques, are applied to natural language parsing. Experiments using these techniques with a trainable statistical parser are…