@inproceedings{6339e057daca41deb810e77ed999bb87,
title = "Distributional consistency: As a general method for defining a core lexicon",
abstract = "We propose Distributional Consistency (DC) as a general method for defining a Core Lexicon. The property of DC is investigated theoretically and empirically, showing that it is clearly distinguishable from word frequency and range of distribution. DC is also shown to reflect intuitive interpretations, especially when its value is close to 1. Its immediate application in NLP would include defining a core lexicon in a language and identifying topical words in a document. We also categorize the existent measures of dispersion into 3 groups via ratio of norm or entropy, proposed a simplified measure and a combined kind of measure. These new measures can be used as virtual prototype or medium type for the study and comparison of existent measures in the future. Keywords: Distributional Consistency; Lexical Usuality; Measure of Dispersion; Square Mean Root (SMR); Modified Frequency; Core Lexicon.",
author = "Huarui Zhang and Churen Huang and Shiwen Yu",
year = "2004",
month = jan,
day = "1",
language = "English",
series = "Proceedings of the 4th International Conference on Language Resources and Evaluation, LREC 2004",
publisher = "European Language Resources Association (ELRA)",
pages = "1119--1122",
editor = "Xavier, {Maria Francisca} and Rute Costa and Fatima Ferreira and Lino, {Maria Teresa} and Raquel Silva",
booktitle = "Proceedings of the 4th International Conference on Language Resources and Evaluation, LREC 2004",
note = "4th International Conference on Language Resources and Evaluation, LREC 2004 ; Conference date: 26-05-2004 Through 28-05-2004",
}