TY - GEN
T1 - A Latent Variable Model of Synchronous Parsing for Syntactic and Semantic Dependencies
AU - Henderson, James
AU - Merlo, Paola
AU - Musillo, Gabriele
AU - Titov, Ivan
PY - 2008/8
Y1 - 2008/8
N2 - We propose a solution to the challenge of the CoNLL 2008 shared task that uses a generative history-based latent variable model to predict the most likely derivation of a synchronous dependency parser for both syntactic and semantic dependencies. The submitted model yields 79.1% macro-average F1 performance, for the joint task, 86.9% syntactic dependencies LAS and 71.0% semantic dependencies F1. A larger model trained after the deadline achieves 80.5% macro-average F1, 87.6% syntactic dependencies LAS, and 73.1% semantic dependencies F1.
AB - We propose a solution to the challenge of the CoNLL 2008 shared task that uses a generative history-based latent variable model to predict the most likely derivation of a synchronous dependency parser for both syntactic and semantic dependencies. The submitted model yields 79.1% macro-average F1 performance, for the joint task, 86.9% syntactic dependencies LAS and 71.0% semantic dependencies F1. A larger model trained after the deadline achieves 80.5% macro-average F1, 87.6% syntactic dependencies LAS, and 73.1% semantic dependencies F1.
M3 - Conference contribution
SN - 978-1-905593-48-4
T3 - CoNLL '08
SP - 178
EP - 182
BT - Proceedings of the Twelfth Conference on Computational Natural Language Learning
PB - Association for Computational Linguistics
CY - Stroudsburg, PA, USA
ER -