A Latent Variable Model of Synchronous Parsing for Syntactic and Semantic Dependencies

James Henderson, Paola Merlo, Gabriele Musillo, Ivan Titov

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

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.
Original languageEnglish
Title of host publicationProceedings of the Twelfth Conference on Computational Natural Language Learning
Place of PublicationStroudsburg, PA, USA
PublisherAssociation for Computational Linguistics
Pages178-182
Number of pages5
ISBN (Print)978-1-905593-48-4
Publication statusPublished - Aug 2008

Publication series

NameCoNLL '08
PublisherAssociation for Computational Linguistics

Fingerprint

Dive into the research topics of 'A Latent Variable Model of Synchronous Parsing for Syntactic and Semantic Dependencies'. Together they form a unique fingerprint.

Cite this