DMCA
Multilingual Joint Parsing of Syntactic and Semantic Dependencies with a Latent Variable Model (2012)
| Citations: | 5 - 2 self |
BibTeX
@MISC{Henderson12multilingualjoint,
author = {James Henderson and Paola Merlo and Ivan Titov and Gabriele Musillo},
title = {Multilingual Joint Parsing of Syntactic and Semantic Dependencies with a Latent Variable Model},
year = {2012}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
dMetrics Current investigations in data-driven models of parsing have shifted from purely syntactic anal-ysis to richer semantic representations, showing that the successful recovery of the meaning of text requires structured analyses of both its grammar and its semantics. In this article, we report on a joint generative history-based model to predict the most likely derivation of a dependency parser for both syntactic and semantic dependencies, in multiple languages. Because these two dependency structures are not isomorphic, we propose a weak synchronization at the level of meaningful subsequences of the two derivations. These synchronized subsequences encompass decisions about the left side of each individual word. We also propose novel derivations for semantic dependency structures, which are appropriate for the relatively unconstrained nature of these graphs. To train a joint model of these synchronized derivations, we make use of a latent variable model of parsing, the Incremental Sigmoid Belief Network (ISBN) architecture. This architecture induces latent feature representations of the derivations, which are used to discover correlations both within and between the two derivations, providing the first application of ISBNs to a multi-task learning problem. This joint model achieves competitive performance
Keyphrases
latent variable model semantic dependency multilingual joint parsing multiple language latent feature representation likely derivation successful recovery synchronized subsequence unconstrained nature semantic dependency structure synchronized derivation left side dependency structure incremental sigmoid belief network structured analysis first application semantic representation dependency parser joint generative history-based model weak synchronization individual word novel derivation meaningful subsequence multi-task learning problem joint model achieves competitive performance dmetrics current investigation joint model data-driven model syntactic anal-ysis
