@inproceedings{de-varda-marelli-2022-effects,
title = "The Effects of Surprisal across Languages: Results from Native and Non-native Reading",
author = "de Varda, Andrea and
Marelli, Marco",
editor = "He, Yulan and
Ji, Heng and
Li, Sujian and
Liu, Yang and
Chang, Chua-Hui",
booktitle = "Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022",
month = nov,
year = "2022",
address = "Online only",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-aacl.13",
pages = "138--144",
abstract = {It is well known that the surprisal of an upcoming word, as estimated by language models, is a solid predictor of reading times (Smith and Levy, 2013). However, most of the studies that support this view are based on English and few other Germanic languages, leaving an open question as to the cross-lingual generalizability of such findings. Moreover, they tend to consider only the best-performing eye-tracking measure, which might conflate the effects of predictive and integrative processing. Furthermore, it is not clear whether prediction plays a role in non-native language processing in bilingual individuals (Gr{\"u}ter et al., 2014). We approach these problems at large scale, extracting surprisal estimates from mBERT, and assessing their psychometric predictive power on the MECO corpus, a cross-linguistic dataset of eye movement behavior in reading (Siegelman et al., 2022; Kuperman et al., 2020). We show that surprisal is a strong predictor of reading times across languages and fixation measurements, and that its effects in L2 are weaker with respect to L1.},
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="de-varda-marelli-2022-effects">
<titleInfo>
<title>The Effects of Surprisal across Languages: Results from Native and Non-native Reading</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">de Varda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Marelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sujian</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chua-Hui</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online only</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>It is well known that the surprisal of an upcoming word, as estimated by language models, is a solid predictor of reading times (Smith and Levy, 2013). However, most of the studies that support this view are based on English and few other Germanic languages, leaving an open question as to the cross-lingual generalizability of such findings. Moreover, they tend to consider only the best-performing eye-tracking measure, which might conflate the effects of predictive and integrative processing. Furthermore, it is not clear whether prediction plays a role in non-native language processing in bilingual individuals (Grüter et al., 2014). We approach these problems at large scale, extracting surprisal estimates from mBERT, and assessing their psychometric predictive power on the MECO corpus, a cross-linguistic dataset of eye movement behavior in reading (Siegelman et al., 2022; Kuperman et al., 2020). We show that surprisal is a strong predictor of reading times across languages and fixation measurements, and that its effects in L2 are weaker with respect to L1.</abstract>
<identifier type="citekey">de-varda-marelli-2022-effects</identifier>
<location>
<url>https://aclanthology.org/2022.findings-aacl.13</url>
</location>
<part>
<date>2022-11</date>
<extent unit="page">
<start>138</start>
<end>144</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Effects of Surprisal across Languages: Results from Native and Non-native Reading
%A de Varda, Andrea
%A Marelli, Marco
%Y He, Yulan
%Y Ji, Heng
%Y Li, Sujian
%Y Liu, Yang
%Y Chang, Chua-Hui
%S Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022
%D 2022
%8 November
%I Association for Computational Linguistics
%C Online only
%F de-varda-marelli-2022-effects
%X It is well known that the surprisal of an upcoming word, as estimated by language models, is a solid predictor of reading times (Smith and Levy, 2013). However, most of the studies that support this view are based on English and few other Germanic languages, leaving an open question as to the cross-lingual generalizability of such findings. Moreover, they tend to consider only the best-performing eye-tracking measure, which might conflate the effects of predictive and integrative processing. Furthermore, it is not clear whether prediction plays a role in non-native language processing in bilingual individuals (Grüter et al., 2014). We approach these problems at large scale, extracting surprisal estimates from mBERT, and assessing their psychometric predictive power on the MECO corpus, a cross-linguistic dataset of eye movement behavior in reading (Siegelman et al., 2022; Kuperman et al., 2020). We show that surprisal is a strong predictor of reading times across languages and fixation measurements, and that its effects in L2 are weaker with respect to L1.
%U https://aclanthology.org/2022.findings-aacl.13
%P 138-144
Markdown (Informal)
[The Effects of Surprisal across Languages: Results from Native and Non-native Reading](https://aclanthology.org/2022.findings-aacl.13) (de Varda & Marelli, Findings 2022)
ACL