Paper: Minimized Models and Grammar-Informed Initialization for Supertagging with Highly Ambiguous Lexicons

ACL ID P10-1051
Title Minimized Models and Grammar-Informed Initialization for Supertagging with Highly Ambiguous Lexicons
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2010
Authors

We combine two complementary ideas for learning supertaggers from highly am- biguous lexicons: grammar-informed tag transitions and models minimized via in- teger programming. Each strategy on its own greatly improves performance over basic expectation-maximization training with a bitag Hidden Markov Model, which we show on the CCGbank and CCG-TUT corpora. The strategies provide further er- ror reductions when combined. We de- scribe a new two-stage integer program- ming strategy that efficiently deals with the high degree of ambiguity on these datasets while obtaining the full effect of model minimization.