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
Author(s): Martha Palmer, Daniel Gildea, Nianwen Xue
Edition: 1
Year: 2010
Language: English
Pages: 104
Tags: Информатика и вычислительная техника;Искусственный интеллект;Компьютерная лингвистика;
Preface......Page 12
Introduction......Page 14
Linguistic Background......Page 15
Lexical Conceptual Structures......Page 20
Proto-Roles......Page 22
Levin's Verb Classes and Alternations......Page 27
Frame Semantics......Page 31
FrameNet......Page 34
VerbNet......Page 35
PropBank......Page 37
Limitations to a Verb-Specific Approach......Page 39
Semlink......Page 40
Summary......Page 41
Identification and Classification......Page 44
Phrase Type......Page 46
Parse Tree Path......Page 48
Position......Page 52
Head Word......Page 53
Features Introduced in Later Systems......Page 54
Choice of Machine Learning Method......Page 55
Feature Combinations......Page 56
Reranking......Page 57
Integer Linear Programming......Page 58
Integrated Parsing and SRL......Page 59
Choice of Syntactic Representation......Page 60
Combining Parsers......Page 61
Evaluation......Page 62
Choice of Resources and Combination of Resources......Page 63
Unsupervised and Partially Supervised Approaches......Page 64
A Cross-Lingual Perspective......Page 66
Semantic Role Projection......Page 69
Semantic Role Alignment......Page 72
Language-(In)Dependent Semantic Role Labeling......Page 74
The Chinese PropBank......Page 75
Semantic Role Labeling for Verbs......Page 76
Semantic Role Labeling for Nouns......Page 83
Summary......Page 88
Summary......Page 90
Bibliography......Page 92
Authors' Biographies......Page 104
