Semantic relations between nominals

other_versions_link

People make sense of a text by identifying the semantic relations which connect the entities or concepts described by that text. A system which aspires to human-like performance must also be equipped to identify, and learn from, semantic relations in the texts it processes. Understanding even a simp...

Full description

Bibliographic Details
Other Authors: Nastase, Vivi
Format: eBook
Language:English
Published: San Rafael, Calif. (1537 Fourth Street, San Rafael, CA 94901 USA) : Morgan & Claypool, c2013.
Series:Synthesis digital library of engineering and computer science.
Synthesis lectures on human language technologies ; # 19.
Subjects:
Computational linguistics.
Grammar, Comparative and general > Nominals.
computational linguistics
information extraction
lexical semantics
natural language processing
nominals
noun compounds
semantic relations
Online Access:Abstract with links to full text
Table of Contents:
  • 1. Introduction
  • 1.1 Motivation
  • 1.2 Applications
  • 1.3 What this book is about
  • 1.4 What this book is not about
  • 2. Relations between nominals, relations between concepts
  • 2.1 Historical overview
  • 2.2 A menagerie of relation schemata
  • 2.2.1 Relations between words, relations within noun compounds
  • 2.2.2 Relations in ontologies and knowledge bases
  • 2.2.3 A conclusion
  • 2.3 Dimensions of variation across relations
  • 2.3.1 Properties of relations
  • 2.3.2 Properties of relation schemata
  • 2.4 Summary
  • 3. Extracting semantic relations with supervision
  • 3.1 Data
  • 3.1.1 MUC and ACE
  • 3.1.2 SemEval-2007/2010
  • 3.1.3 Datasets for relations in noun-noun compounds
  • 3.1.4 Relations in manually built ontologies
  • 3.1.5 Relations from collaboratively built resources
  • 3.1.6 Domain-specific data
  • 3.2 Features
  • 3.2.1 Entity features
  • 3.2.2 Relational features
  • 3.3 Learning methods
  • 3.3.1 Supervised machine learning
  • 3.3.2 Learning algorithms
  • 3.3.3 Determining the semantic class of relation arguments
  • 3.4 Beyond binary relations
  • 3.5 Practical considerations
  • 3.6 Summary
  • 4. Extracting semantic relations with little or no supervision
  • 4.1 Mining ontologies from machine-readable dictionaries
  • 4.2 Mining relations with patterns
  • 4.2.1 Bootstrapping relations from large corpora
  • 4.2.2 Tackling semantic drift
  • 4.3 Distant supervision
  • 4.4 Unsupervised relation extraction
  • 4.4.1 Extracting IS-A relations
  • 4.4.2 Emergent relations in open relation extraction
  • 4.4.3 Extreme unsupervised relation extraction
  • 4.5 Self-supervised relation extraction
  • 4.6 Web-scale relation extraction
  • 4.6.1 Never-ending language learner
  • 4.6.2 Machine reading at the University of Washington
  • 4.7 Summary
  • 5. Conclusion
  • Bibliography
  • Authors' biographies
  • Index.

Similar Items