Semantic interpretation of noun compounds using verbal and other paraphrases

Preslav Nakov, Marti A. Hearst

Research output: Contribution to journalArticle

16 Citations (Scopus)

Abstract

We study the problem of semantic interpretation of noun compounds such as bee honey, malaria mosquito, apple cake, and stem cell. In particular, we explore the potential of using predicates that make explicit the hidden relation that holds between the nouns that form the noun compound. For example, mosquito that carries malaria is a paraphrase of the compound malaria mosquito in which the verb explicitly states the semantic relation between the two nouns. We study the utility of using such paraphrasing verbs, with associated weights, to build a representation of the semantics of a noun compound, for example, malaria mosquito can be represented as follows: carry (23), spread (16), cause (12), transmit (9), and so on. We also explore the potential of using multiple paraphrasing verbs as features for predicting abstract semantic relations such as CAUSE, and we demonstrate that using explicit paraphrases can help improve statistical machine translation.

Original languageEnglish
Article number13
JournalACM Transactions on Speech and Language Processing
Volume10
Issue number3
DOIs
Publication statusPublished - 1 Jul 2013

Fingerprint

Malaria
Semantics
Statistical Machine Translation
Apple
Stem Cells
Stem cells
Predicate
Interpretation
Demonstrate

Keywords

  • Lexical semantics
  • Machine translation
  • Multiword expressions
  • Noun compounds
  • Paraphrases
  • Web as a corpus

ASJC Scopus subject areas

  • Computer Science (miscellaneous)
  • Computational Mathematics

Cite this

Semantic interpretation of noun compounds using verbal and other paraphrases. / Nakov, Preslav; Hearst, Marti A.

In: ACM Transactions on Speech and Language Processing, Vol. 10, No. 3, 13, 01.07.2013.

Research output: Contribution to journalArticle

@article{92eff11084da4783a612f0167bb5a21a,
title = "Semantic interpretation of noun compounds using verbal and other paraphrases",
abstract = "We study the problem of semantic interpretation of noun compounds such as bee honey, malaria mosquito, apple cake, and stem cell. In particular, we explore the potential of using predicates that make explicit the hidden relation that holds between the nouns that form the noun compound. For example, mosquito that carries malaria is a paraphrase of the compound malaria mosquito in which the verb explicitly states the semantic relation between the two nouns. We study the utility of using such paraphrasing verbs, with associated weights, to build a representation of the semantics of a noun compound, for example, malaria mosquito can be represented as follows: carry (23), spread (16), cause (12), transmit (9), and so on. We also explore the potential of using multiple paraphrasing verbs as features for predicting abstract semantic relations such as CAUSE, and we demonstrate that using explicit paraphrases can help improve statistical machine translation.",
keywords = "Lexical semantics, Machine translation, Multiword expressions, Noun compounds, Paraphrases, Web as a corpus",
author = "Preslav Nakov and Hearst, {Marti A.}",
year = "2013",
month = "7",
day = "1",
doi = "10.1145/2483969.2483975",
language = "English",
volume = "10",
journal = "ACM Transactions on Speech and Language Processing",
issn = "1550-4875",
publisher = "Association for Computing Machinery (ACM)",
number = "3",

}

TY - JOUR

T1 - Semantic interpretation of noun compounds using verbal and other paraphrases

AU - Nakov, Preslav

AU - Hearst, Marti A.

PY - 2013/7/1

Y1 - 2013/7/1

N2 - We study the problem of semantic interpretation of noun compounds such as bee honey, malaria mosquito, apple cake, and stem cell. In particular, we explore the potential of using predicates that make explicit the hidden relation that holds between the nouns that form the noun compound. For example, mosquito that carries malaria is a paraphrase of the compound malaria mosquito in which the verb explicitly states the semantic relation between the two nouns. We study the utility of using such paraphrasing verbs, with associated weights, to build a representation of the semantics of a noun compound, for example, malaria mosquito can be represented as follows: carry (23), spread (16), cause (12), transmit (9), and so on. We also explore the potential of using multiple paraphrasing verbs as features for predicting abstract semantic relations such as CAUSE, and we demonstrate that using explicit paraphrases can help improve statistical machine translation.

AB - We study the problem of semantic interpretation of noun compounds such as bee honey, malaria mosquito, apple cake, and stem cell. In particular, we explore the potential of using predicates that make explicit the hidden relation that holds between the nouns that form the noun compound. For example, mosquito that carries malaria is a paraphrase of the compound malaria mosquito in which the verb explicitly states the semantic relation between the two nouns. We study the utility of using such paraphrasing verbs, with associated weights, to build a representation of the semantics of a noun compound, for example, malaria mosquito can be represented as follows: carry (23), spread (16), cause (12), transmit (9), and so on. We also explore the potential of using multiple paraphrasing verbs as features for predicting abstract semantic relations such as CAUSE, and we demonstrate that using explicit paraphrases can help improve statistical machine translation.

KW - Lexical semantics

KW - Machine translation

KW - Multiword expressions

KW - Noun compounds

KW - Paraphrases

KW - Web as a corpus

UR - http://www.scopus.com/inward/record.url?scp=84880214824&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84880214824&partnerID=8YFLogxK

U2 - 10.1145/2483969.2483975

DO - 10.1145/2483969.2483975

M3 - Article

VL - 10

JO - ACM Transactions on Speech and Language Processing

JF - ACM Transactions on Speech and Language Processing

SN - 1550-4875

IS - 3

M1 - 13

ER -