@inproceedings{pimentel-etal-2021-disambiguatory,
title = "Disambiguatory Signals are Stronger in Word-initial Positions",
author = "Pimentel, Tiago and
Cotterell, Ryan and
Roark, Brian",
editor = "Merlo, Paola and
Tiedemann, Jorg and
Tsarfaty, Reut",
booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume",
month = apr,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.eacl-main.3",
doi = "10.18653/v1/2021.eacl-main.3",
pages = "31--41",
abstract = "Psycholinguistic studies of human word processing and lexical access provide ample evidence of the preferred nature of word-initial versus word-final segments, e.g., in terms of attention paid by listeners (greater) or the likelihood of reduction by speakers (lower). This has led to the conjecture{---}as in Wedel et al. (2019b), but common elsewhere{---}that languages have evolved to provide more information earlier in words than later. Information-theoretic methods to establish such tendencies in lexicons have suffered from several methodological shortcomings that leave open the question of whether this high word-initial informativeness is actually a property of the lexicon or simply an artefact of the incremental nature of recognition. In this paper, we point out the confounds in existing methods for comparing the informativeness of segments early in the word versus later in the word, and present several new measures that avoid these confounds. When controlling for these confounds, we still find evidence across hundreds of languages that indeed there is a cross-linguistic tendency to front-load information in words.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pimentel-etal-2021-disambiguatory">
<titleInfo>
<title>Disambiguatory Signals are Stronger in Word-initial Positions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tiago</namePart>
<namePart type="family">Pimentel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Brian</namePart>
<namePart type="family">Roark</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume</title>
</titleInfo>
<name type="personal">
<namePart type="given">Paola</namePart>
<namePart type="family">Merlo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jorg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reut</namePart>
<namePart type="family">Tsarfaty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Psycholinguistic studies of human word processing and lexical access provide ample evidence of the preferred nature of word-initial versus word-final segments, e.g., in terms of attention paid by listeners (greater) or the likelihood of reduction by speakers (lower). This has led to the conjecture—as in Wedel et al. (2019b), but common elsewhere—that languages have evolved to provide more information earlier in words than later. Information-theoretic methods to establish such tendencies in lexicons have suffered from several methodological shortcomings that leave open the question of whether this high word-initial informativeness is actually a property of the lexicon or simply an artefact of the incremental nature of recognition. In this paper, we point out the confounds in existing methods for comparing the informativeness of segments early in the word versus later in the word, and present several new measures that avoid these confounds. When controlling for these confounds, we still find evidence across hundreds of languages that indeed there is a cross-linguistic tendency to front-load information in words.</abstract>
<identifier type="citekey">pimentel-etal-2021-disambiguatory</identifier>
<identifier type="doi">10.18653/v1/2021.eacl-main.3</identifier>
<location>
<url>https://aclanthology.org/2021.eacl-main.3</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>31</start>
<end>41</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Disambiguatory Signals are Stronger in Word-initial Positions
%A Pimentel, Tiago
%A Cotterell, Ryan
%A Roark, Brian
%Y Merlo, Paola
%Y Tiedemann, Jorg
%Y Tsarfaty, Reut
%S Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F pimentel-etal-2021-disambiguatory
%X Psycholinguistic studies of human word processing and lexical access provide ample evidence of the preferred nature of word-initial versus word-final segments, e.g., in terms of attention paid by listeners (greater) or the likelihood of reduction by speakers (lower). This has led to the conjecture—as in Wedel et al. (2019b), but common elsewhere—that languages have evolved to provide more information earlier in words than later. Information-theoretic methods to establish such tendencies in lexicons have suffered from several methodological shortcomings that leave open the question of whether this high word-initial informativeness is actually a property of the lexicon or simply an artefact of the incremental nature of recognition. In this paper, we point out the confounds in existing methods for comparing the informativeness of segments early in the word versus later in the word, and present several new measures that avoid these confounds. When controlling for these confounds, we still find evidence across hundreds of languages that indeed there is a cross-linguistic tendency to front-load information in words.
%R 10.18653/v1/2021.eacl-main.3
%U https://aclanthology.org/2021.eacl-main.3
%U https://doi.org/10.18653/v1/2021.eacl-main.3
%P 31-41
Markdown (Informal)
[Disambiguatory Signals are Stronger in Word-initial Positions](https://aclanthology.org/2021.eacl-main.3) (Pimentel et al., EACL 2021)
ACL
- Tiago Pimentel, Ryan Cotterell, and Brian Roark. 2021. Disambiguatory Signals are Stronger in Word-initial Positions. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 31–41, Online. Association for Computational Linguistics.