Fast and Robust Multilingual Dependency Parsing with a Generative Latent Variable Model

Ivan Titov, James Henderson

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

Abstract

We use a generative history-based model to predict the most likely derivation of a dependency parse. Our probabilistic model is based on Incremental Sigmoid Belief Networks, a recently proposed class of latent variable models for structure prediction. Their ability to automatically induce features results in multilingual parsing which is robust enough to achieve accuracy well above the average for each individual language in the multilingual track of the CoNLL-2007 shared task. This robustness led to the third best overall average labeled attachment score in the task, despite using no discriminative methods. We also demonstrate that the parser is quite fast, and can provide even faster parsing times without much loss of accuracy.
Original languageEnglish
Title of host publicationEMNLP-CoNLL 2007, Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, June 28-30, 2007, Prague, Czech Republic
PublisherAssociation for Computational Linguistics
Pages947-951
Number of pages5
Publication statusPublished - 2007

Fingerprint Dive into the research topics of 'Fast and Robust Multilingual Dependency Parsing with a Generative Latent Variable Model'. Together they form a unique fingerprint.

Cite this