@inproceedings{steuer-etal-2026-evaluating,
title = "Evaluating the Interplay of Information Status and Information Content in a Multilingual Parallel Corpus",
author = "Steuer, Julius and
Nakai, Toshiki and
Dyer, Andrew Thomas and
Talamo, Luigi and
Verkerk, Annemarie",
editor = "Vylomova, Ekaterina and
Shcherbakov, Andrei and
Rani, Priya",
booktitle = "Proceedings of the 8th Workshop on Research in Computational Linguistic Typology and Multilingual {NLP}",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.sigtyp-main.3/",
pages = "18--25",
ISBN = "979-8-89176-374-6",
abstract = "The uniform information density (UID) hypothesis postulates that linguistic units are distributed in a text in such a way that the variance around an average information density is minimized. The relationship between information density and information status (IS) is so far underexplored. In this ongoing work, we project IS annotations on the English section of the CIEP+ corpus (Verkerk Talamo 2024) to parallel sections in other languages. We then use the projected annotations to evaluate the relationship between IS and information content in a typologically diverse sample of languages. Our preliminary findings indicate that there is an effect of information status on information density, with the directionality of the effect depending on language and part of speech."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="steuer-etal-2026-evaluating">
<titleInfo>
<title>Evaluating the Interplay of Information Status and Information Content in a Multilingual Parallel Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Julius</namePart>
<namePart type="family">Steuer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Toshiki</namePart>
<namePart type="family">Nakai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="given">Thomas</namePart>
<namePart type="family">Dyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luigi</namePart>
<namePart type="family">Talamo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Annemarie</namePart>
<namePart type="family">Verkerk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 8th Workshop on Research in Computational Linguistic Typology and Multilingual NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Vylomova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrei</namePart>
<namePart type="family">Shcherbakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Priya</namePart>
<namePart type="family">Rani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-374-6</identifier>
</relatedItem>
<abstract>The uniform information density (UID) hypothesis postulates that linguistic units are distributed in a text in such a way that the variance around an average information density is minimized. The relationship between information density and information status (IS) is so far underexplored. In this ongoing work, we project IS annotations on the English section of the CIEP+ corpus (Verkerk Talamo 2024) to parallel sections in other languages. We then use the projected annotations to evaluate the relationship between IS and information content in a typologically diverse sample of languages. Our preliminary findings indicate that there is an effect of information status on information density, with the directionality of the effect depending on language and part of speech.</abstract>
<identifier type="citekey">steuer-etal-2026-evaluating</identifier>
<location>
<url>https://aclanthology.org/2026.sigtyp-main.3/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>18</start>
<end>25</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating the Interplay of Information Status and Information Content in a Multilingual Parallel Corpus
%A Steuer, Julius
%A Nakai, Toshiki
%A Dyer, Andrew Thomas
%A Talamo, Luigi
%A Verkerk, Annemarie
%Y Vylomova, Ekaterina
%Y Shcherbakov, Andrei
%Y Rani, Priya
%S Proceedings of the 8th Workshop on Research in Computational Linguistic Typology and Multilingual NLP
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-374-6
%F steuer-etal-2026-evaluating
%X The uniform information density (UID) hypothesis postulates that linguistic units are distributed in a text in such a way that the variance around an average information density is minimized. The relationship between information density and information status (IS) is so far underexplored. In this ongoing work, we project IS annotations on the English section of the CIEP+ corpus (Verkerk Talamo 2024) to parallel sections in other languages. We then use the projected annotations to evaluate the relationship between IS and information content in a typologically diverse sample of languages. Our preliminary findings indicate that there is an effect of information status on information density, with the directionality of the effect depending on language and part of speech.
%U https://aclanthology.org/2026.sigtyp-main.3/
%P 18-25
Markdown (Informal)
[Evaluating the Interplay of Information Status and Information Content in a Multilingual Parallel Corpus](https://aclanthology.org/2026.sigtyp-main.3/) (Steuer et al., SIGTYP 2026)
ACL