Generative models for syntactic and semantic structure prediction using latent variables

Diplôme Thèse Generative models for syntactic and semantic structure prediction using latent variables eng 2015-11-09 author Garg Nikhil 703057 director Henderson James 529988 director Marchand-Maillet Stéphane 0000-0002-4875-6101 518563 10.13097/archive-ouverte/unige:88095 urn:nbn:ch:unige-880950 Sc. 4977 Linguistic structures capture varying degrees of information in natural language text, for instance, from simple per word part-of-speech tags to more complicated phrases bearing semantic roles. In Natural Language Processing, it is common to use a pipeline approach, where simpler tasks or structures are used as inputs to more complicated problems. We explore the Semantic Role Labeling pipeline which is composed of part-of-speech tagging, syntactic parsing, semantic argument identification, and semantic role classification. In particular, we propose generative models for dependency parsing and semantic role classification, which use inter-connected latent variables to encode the parsing history in the first model, and role correlations in the second model. The dependency parsing model is based on Temporal Restricted Boltzmann Machines, where we show its effectiveness in reducing the feature engineering effort. The semantic role classification model is a Bayesian model, where we demonstrate a way to combine local constituent features with global role correlations in a unified framework. Dewey 025.063 Dewey 410 13 Centre universitaire d'informatique 0D3 32 Département d'informatique 18 82 Département de linguistique 39 false 730 Geneva Artificial Intelligence Laboratory 722 Laboratoire d'Analyse et de Traitement du Langage (LATL) 12cef7ac-86c7-4a7b-88c9-1d8a44c51d14 Thesis Public These-Garg.pdf 1254380 application/pdf openAccess Centres et instituts / Centre universitaire d'informatique Faculté des sciences / Département d'informatique Faculté des lettres / Département de linguistique

Title	Published in	Access level	OA Policy	Year	Views	Downloads

Generative models for syntactic and semantic structure prediction using latent variables				2015	792	363

Archive ouverte UNIGE

Garg, Nikhil