Human Variation and Lexical Choice

Research output: Contribution to journalArticle

31 Citations (Scopus)

Abstract

Much natural language processing research implicitly assumes that word meanings are fixed in a language community, but in fact there is good evidence that different people probably associate slightly different meanings with words. We summarize some evidence for this claim from the literature and from an ongoing research project, and discuss its implications for natural language generation, especially for lexical choice, that is, choosing appropriate words for a generated text.

Original languageEnglish
Pages (from-to)545-553
Number of pages8
JournalComputational Linguistics
Volume28
DOIs
Publication statusPublished - Dec 2002

Cite this

Human Variation and Lexical Choice. / Reiter, Ehud Baruch; Sripada, Gowri Somayajulu.

In: Computational Linguistics, Vol. 28, 12.2002, p. 545-553.

Research output: Contribution to journalArticle

@article{b97cf7d83d09477597ee729921b6a2e4,
title = "Human Variation and Lexical Choice",
abstract = "Much natural language processing research implicitly assumes that word meanings are fixed in a language community, but in fact there is good evidence that different people probably associate slightly different meanings with words. We summarize some evidence for this claim from the literature and from an ongoing research project, and discuss its implications for natural language generation, especially for lexical choice, that is, choosing appropriate words for a generated text.",
author = "Reiter, {Ehud Baruch} and Sripada, {Gowri Somayajulu}",
year = "2002",
month = "12",
doi = "10.1162/089120102762671981",
language = "English",
volume = "28",
pages = "545--553",
journal = "Computational Linguistics",
issn = "0891-2017",
publisher = "MIT Press Journals",

}

TY - JOUR

T1 - Human Variation and Lexical Choice

AU - Reiter, Ehud Baruch

AU - Sripada, Gowri Somayajulu

PY - 2002/12

Y1 - 2002/12

N2 - Much natural language processing research implicitly assumes that word meanings are fixed in a language community, but in fact there is good evidence that different people probably associate slightly different meanings with words. We summarize some evidence for this claim from the literature and from an ongoing research project, and discuss its implications for natural language generation, especially for lexical choice, that is, choosing appropriate words for a generated text.

AB - Much natural language processing research implicitly assumes that word meanings are fixed in a language community, but in fact there is good evidence that different people probably associate slightly different meanings with words. We summarize some evidence for this claim from the literature and from an ongoing research project, and discuss its implications for natural language generation, especially for lexical choice, that is, choosing appropriate words for a generated text.

U2 - 10.1162/089120102762671981

DO - 10.1162/089120102762671981

M3 - Article

VL - 28

SP - 545

EP - 553

JO - Computational Linguistics

JF - Computational Linguistics

SN - 0891-2017

ER -