Semantic relations between nominals

Vivi Nastase, Preslav Nakov, Diarmuid Séaghdha, Stan Szpakowicz

Research output: Contribution to journalReview article

10 Citations (Scopus)

Abstract

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 simple sentence such as "Opportunity and Curiosity find similar rocks on Mars" requires recognizing relations (rocks are located on Mars, signalled by the word on) and drawing on already known relations (Opportunity and Curiosity are instances of the class of Mars rovers). A languageunderstanding system should be able to find such relations in documents and progressively build a knowledge base or even an ontology. Resources of this kind assist continuous learning and other advanced language-processing tasks such as text summarization, question answering and machine translation. The book discusses the recognition in text of semantic relations which capture interactions between base noun phrases. After a brief historical background, we introduce a range of relation inventories of varying granularity, which have been proposed by computational linguists. There is also variation in the scale at which systems operate, from snippets all the way to the wholeWeb, and in the techniques of recognizing relations in texts, from full supervision through weak or distant supervision to self-supervised or completely unsupervised methods. A discussion of supervised learning covers available datasets, feature sets which describe relation instances, and successful algorithms. An overview of weakly supervised and unsupervised learning zooms in on the acquisition of relations from large corpora with hardly any annotated data.We show how bootstrapping from seed examples or patterns scales up to very large text collections on the Web.We also present machine learning techniques in which data redundancy and variability lead to fast and reliable relation extraction.

Original languageEnglish
Pages (from-to)1-121
Number of pages121
JournalSynthesis Lectures on Human Language Technologies
Volume6
Issue number1
DOIs
Publication statusPublished - 1 Jan 2013

Fingerprint

Semantics
Supervised learning
semantics
Rocks
Unsupervised learning
Redundancy
Ontology
Seed
Learning systems
learning
supervision
Processing
redundancy
ontology
present
interaction
language
resources
performance

Keywords

  • Computational linguistics
  • Information extraction
  • Lexical semantics
  • Natural language processing
  • Nominals
  • Noun compounds
  • Semantic relations

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Computer Science Applications
  • Linguistics and Language

Cite this

Semantic relations between nominals. / Nastase, Vivi; Nakov, Preslav; Séaghdha, Diarmuid; Szpakowicz, Stan.

In: Synthesis Lectures on Human Language Technologies, Vol. 6, No. 1, 01.01.2013, p. 1-121.

Research output: Contribution to journalReview article

Nastase, Vivi ; Nakov, Preslav ; Séaghdha, Diarmuid ; Szpakowicz, Stan. / Semantic relations between nominals. In: Synthesis Lectures on Human Language Technologies. 2013 ; Vol. 6, No. 1. pp. 1-121.
@article{5ac8137bfe224a2ead562d1f30870ce3,
title = "Semantic relations between nominals",
abstract = "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 simple sentence such as {"}Opportunity and Curiosity find similar rocks on Mars{"} requires recognizing relations (rocks are located on Mars, signalled by the word on) and drawing on already known relations (Opportunity and Curiosity are instances of the class of Mars rovers). A languageunderstanding system should be able to find such relations in documents and progressively build a knowledge base or even an ontology. Resources of this kind assist continuous learning and other advanced language-processing tasks such as text summarization, question answering and machine translation. The book discusses the recognition in text of semantic relations which capture interactions between base noun phrases. After a brief historical background, we introduce a range of relation inventories of varying granularity, which have been proposed by computational linguists. There is also variation in the scale at which systems operate, from snippets all the way to the wholeWeb, and in the techniques of recognizing relations in texts, from full supervision through weak or distant supervision to self-supervised or completely unsupervised methods. A discussion of supervised learning covers available datasets, feature sets which describe relation instances, and successful algorithms. An overview of weakly supervised and unsupervised learning zooms in on the acquisition of relations from large corpora with hardly any annotated data.We show how bootstrapping from seed examples or patterns scales up to very large text collections on the Web.We also present machine learning techniques in which data redundancy and variability lead to fast and reliable relation extraction.",
keywords = "Computational linguistics, Information extraction, Lexical semantics, Natural language processing, Nominals, Noun compounds, Semantic relations",
author = "Vivi Nastase and Preslav Nakov and Diarmuid S{\'e}aghdha and Stan Szpakowicz",
year = "2013",
month = "1",
day = "1",
doi = "10.2200/S00489ED1V01Y201303HLT019",
language = "English",
volume = "6",
pages = "1--121",
journal = "Synthesis Lectures on Human Language Technologies",
issn = "1947-4040",
publisher = "Morgan and Claypool Publishers",
number = "1",

}

TY - JOUR

T1 - Semantic relations between nominals

AU - Nastase, Vivi

AU - Nakov, Preslav

AU - Séaghdha, Diarmuid

AU - Szpakowicz, Stan

PY - 2013/1/1

Y1 - 2013/1/1

N2 - 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 simple sentence such as "Opportunity and Curiosity find similar rocks on Mars" requires recognizing relations (rocks are located on Mars, signalled by the word on) and drawing on already known relations (Opportunity and Curiosity are instances of the class of Mars rovers). A languageunderstanding system should be able to find such relations in documents and progressively build a knowledge base or even an ontology. Resources of this kind assist continuous learning and other advanced language-processing tasks such as text summarization, question answering and machine translation. The book discusses the recognition in text of semantic relations which capture interactions between base noun phrases. After a brief historical background, we introduce a range of relation inventories of varying granularity, which have been proposed by computational linguists. There is also variation in the scale at which systems operate, from snippets all the way to the wholeWeb, and in the techniques of recognizing relations in texts, from full supervision through weak or distant supervision to self-supervised or completely unsupervised methods. A discussion of supervised learning covers available datasets, feature sets which describe relation instances, and successful algorithms. An overview of weakly supervised and unsupervised learning zooms in on the acquisition of relations from large corpora with hardly any annotated data.We show how bootstrapping from seed examples or patterns scales up to very large text collections on the Web.We also present machine learning techniques in which data redundancy and variability lead to fast and reliable relation extraction.

AB - 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 simple sentence such as "Opportunity and Curiosity find similar rocks on Mars" requires recognizing relations (rocks are located on Mars, signalled by the word on) and drawing on already known relations (Opportunity and Curiosity are instances of the class of Mars rovers). A languageunderstanding system should be able to find such relations in documents and progressively build a knowledge base or even an ontology. Resources of this kind assist continuous learning and other advanced language-processing tasks such as text summarization, question answering and machine translation. The book discusses the recognition in text of semantic relations which capture interactions between base noun phrases. After a brief historical background, we introduce a range of relation inventories of varying granularity, which have been proposed by computational linguists. There is also variation in the scale at which systems operate, from snippets all the way to the wholeWeb, and in the techniques of recognizing relations in texts, from full supervision through weak or distant supervision to self-supervised or completely unsupervised methods. A discussion of supervised learning covers available datasets, feature sets which describe relation instances, and successful algorithms. An overview of weakly supervised and unsupervised learning zooms in on the acquisition of relations from large corpora with hardly any annotated data.We show how bootstrapping from seed examples or patterns scales up to very large text collections on the Web.We also present machine learning techniques in which data redundancy and variability lead to fast and reliable relation extraction.

KW - Computational linguistics

KW - Information extraction

KW - Lexical semantics

KW - Natural language processing

KW - Nominals

KW - Noun compounds

KW - Semantic relations

UR - http://www.scopus.com/inward/record.url?scp=84923609648&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84923609648&partnerID=8YFLogxK

U2 - 10.2200/S00489ED1V01Y201303HLT019

DO - 10.2200/S00489ED1V01Y201303HLT019

M3 - Review article

AN - SCOPUS:84923609648

VL - 6

SP - 1

EP - 121

JO - Synthesis Lectures on Human Language Technologies

JF - Synthesis Lectures on Human Language Technologies

SN - 1947-4040

IS - 1

ER -