@inproceedings{zechner-2023-length,
title = "Length Dependence of Vocabulary Richness",
author = "Zechner, Niklas",
editor = {Alum{\"a}e, Tanel and
Fishel, Mark},
booktitle = "Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa)",
month = may,
year = "2023",
address = "T{\'o}rshavn, Faroe Islands",
publisher = "University of Tartu Library",
url = "https://aclanthology.org/2023.nodalida-1.56",
pages = "565--573",
abstract = "The relation between the length of a text and the number of unique words is investigated using several Swedish language corpora. We consider a number of existing measures of vocabulary richness, show that they are not length-independent, and try to improve on some of them based on statistical evidence. We also look at the spectrum of values over text lengths, and find that genres have characteristic shapes.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zechner-2023-length">
<titleInfo>
<title>Length Dependence of Vocabulary Richness</title>
</titleInfo>
<name type="personal">
<namePart type="given">Niklas</namePart>
<namePart type="family">Zechner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tanel</namePart>
<namePart type="family">Alumäe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Fishel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>University of Tartu Library</publisher>
<place>
<placeTerm type="text">Tórshavn, Faroe Islands</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The relation between the length of a text and the number of unique words is investigated using several Swedish language corpora. We consider a number of existing measures of vocabulary richness, show that they are not length-independent, and try to improve on some of them based on statistical evidence. We also look at the spectrum of values over text lengths, and find that genres have characteristic shapes.</abstract>
<identifier type="citekey">zechner-2023-length</identifier>
<location>
<url>https://aclanthology.org/2023.nodalida-1.56</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>565</start>
<end>573</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Length Dependence of Vocabulary Richness
%A Zechner, Niklas
%Y Alumäe, Tanel
%Y Fishel, Mark
%S Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa)
%D 2023
%8 May
%I University of Tartu Library
%C Tórshavn, Faroe Islands
%F zechner-2023-length
%X The relation between the length of a text and the number of unique words is investigated using several Swedish language corpora. We consider a number of existing measures of vocabulary richness, show that they are not length-independent, and try to improve on some of them based on statistical evidence. We also look at the spectrum of values over text lengths, and find that genres have characteristic shapes.
%U https://aclanthology.org/2023.nodalida-1.56
%P 565-573
Markdown (Informal)
[Length Dependence of Vocabulary Richness](https://aclanthology.org/2023.nodalida-1.56) (Zechner, NoDaLiDa 2023)
ACL
- Niklas Zechner. 2023. Length Dependence of Vocabulary Richness. In Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa), pages 565–573, Tórshavn, Faroe Islands. University of Tartu Library.