: Modern cars are equipped with advanced technology requiring cognitively complex operation that is reliant on the user’s visual attention. It is therefore hazardous for drivers ...
We combine two complementary ideas for learning supertaggers from highly ambiguous lexicons: grammar-informed tag transitions and models minimized via integer programming. Each st...
Incremental parsing techniques such as shift-reduce have gained popularity thanks to their efficiency, but there remains a major problem: the search is greedy and only explores a ...
In anonymous credential schemes, users obtain credentials on certain attributes from an issuer, and later show these credentials to a relying party anonymously and without fully di...
We describe a method of incorporating taskspecific cost functions into standard conditional log-likelihood (CLL) training of linear structured prediction models. Recently introduc...