Semantic Role LabelingMorgan & Claypool Publishers, 2010 - 91 páginas This book is aimed at providing an overview of several aspects of semantic role labeling. Chapter 1 begins with linguistic background on the definition of semantic roles and the controversies surrounding them. Chapter 2 describes how the theories have led to structured lexicons such as FrameNet, VerbNet and the PropBank Frame Files that in turn provide the basis for large scale semantic annotation of corpora. This data has facilitated the development of automatic semantic role labeling systems based on supervised machine learning techniques. Chapter 3 presents the general principles of applying both supervised and unsupervised machine learning to this task, with a description of the standard stages and feature choices, as well as giving details of several specific systems. Recent advances include the use of joint inference to take advantage of context sensitivities, and attempts to improve performance by closer integration of the syntactic parsing task with semantic role labeling. Chapter 3 also discusses the impact the granularity of the semantic roles has on system performance. Having outlined the basic approach with respect to English, Chapter 4 goes on to discuss applying the same techniques to other languages, using Chinese as the primary example. Although substantial training data is available for Chinese, this is not the case for many other languages, and techniques for projecting English role labels onto parallel corpora are also presented. Table of Contents: Preface / Semantic Roles / Available Lexical Resources / Machine Learning for Semantic Role Labeling / A Cross-Lingual Perspective / Summary |
Contenido
1 | |
Available Lexical Resources | 21 |
Machine Learning for Semantic Role Labeling | 31 |
A CrossLingual Perspective | 53 |
Summary | 77 |
Bibliography | 79 |
Authors Biographies | 91 |
Otras ediciones - Ver todas
Términos y frases comunes
accuracy adjuncts Agent Arg0 Arg1 argument labels argument structure assigned Association for Computational Chapter Chinese Propbank classifier Computational Linguistics Conference on Empirical corpora corpus Daniel Jurafsky defined described direct object discussed Dowty Dowty’s Empirical Methods English example feature combinations Fillmore Frame Elements Frame Semantics FrameNet FrameNet Frame Gildea and Jurafsky Goal grammatical head word Incremental Theme Jackendoff Kipper Levin classes Lexical Resources light verb LOCATION machine learning mapping Martha Palmer maximum entropy Methods in Natural Natural Language Processing node nominalized predicate noun phrase Padó parallel data parse tree parser participant path feature Patient Penn Treebank phrase type Pradhan predicate-argument structure prepositional phrase Proceedings pruning algorithm representation role labeling system semantic frame semantic role annotation semantic role labeling semantic role projection sentence SRL system support verb syntactic frames syntactic parsing Thematic Role training data verb arguments verb class verb-specific VerbNet and FrameNet word alignment