@inproceedings{evaldo-leal-etal-2020-using,
title = "Using Eye-tracking Data to Predict the Readability of {B}razilian {P}ortuguese Sentences in Single-task, Multi-task and Sequential Transfer Learning Approaches",
author = "Evaldo Leal, Sidney and
Munguba Vieira, Jo{\~a}o Marcos and
dos Santos Rodrigues, Erica and
Nogueira Teixeira, Elis{\^a}ngela and
Alu{\'\i}sio, Sandra",
editor = "Scott, Donia and
Bel, Nuria and
Zong, Chengqing",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.512",
doi = "10.18653/v1/2020.coling-main.512",
pages = "5821--5831",
abstract = "Sentence complexity assessment is a relatively new task in Natural Language Processing. One of its aims is to highlight in a text which sentences are more complex to support the simplification of contents for a target audience (e.g., children, cognitively impaired users, non-native speakers and low-literacy readers (Scarton and Specia, 2018)). This task is evaluated using datasets of pairs of aligned sentences including the complex and simple version of the same sentence. For Brazilian Portuguese, the task was addressed by (Leal et al., 2018), who set up the first dataset to evaluate the task in this language, reaching 87.8{\%} of accuracy with linguistic features. The present work advances these results, using models inspired by (Gonzalez-Gardu{\~n}o and S{\o}gaard, 2018), which hold the state-of-the-art for the English language, with multi-task learning and eye-tracking measures. First-Pass Duration, Total Regression Duration and Total Fixation Duration were used in two moments; first to select a subset of linguistic features and then as an auxiliary task in the multi-task and sequential learning models. The best model proposed here reaches the new state-of-the-art for Portuguese with 97.5{\%} accuracy 1 , an increase of almost 10 points compared to the best previous results, in addition to proposing improvements in the public dataset after analysing the errors of our best model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="evaldo-leal-etal-2020-using">
<titleInfo>
<title>Using Eye-tracking Data to Predict the Readability of Brazilian Portuguese Sentences in Single-task, Multi-task and Sequential Transfer Learning Approaches</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sidney</namePart>
<namePart type="family">Evaldo Leal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">João</namePart>
<namePart type="given">Marcos</namePart>
<namePart type="family">Munguba Vieira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erica</namePart>
<namePart type="family">dos Santos Rodrigues</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elisângela</namePart>
<namePart type="family">Nogueira Teixeira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sandra</namePart>
<namePart type="family">Aluísio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Donia</namePart>
<namePart type="family">Scott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nuria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Sentence complexity assessment is a relatively new task in Natural Language Processing. One of its aims is to highlight in a text which sentences are more complex to support the simplification of contents for a target audience (e.g., children, cognitively impaired users, non-native speakers and low-literacy readers (Scarton and Specia, 2018)). This task is evaluated using datasets of pairs of aligned sentences including the complex and simple version of the same sentence. For Brazilian Portuguese, the task was addressed by (Leal et al., 2018), who set up the first dataset to evaluate the task in this language, reaching 87.8% of accuracy with linguistic features. The present work advances these results, using models inspired by (Gonzalez-Garduño and Søgaard, 2018), which hold the state-of-the-art for the English language, with multi-task learning and eye-tracking measures. First-Pass Duration, Total Regression Duration and Total Fixation Duration were used in two moments; first to select a subset of linguistic features and then as an auxiliary task in the multi-task and sequential learning models. The best model proposed here reaches the new state-of-the-art for Portuguese with 97.5% accuracy 1 , an increase of almost 10 points compared to the best previous results, in addition to proposing improvements in the public dataset after analysing the errors of our best model.</abstract>
<identifier type="citekey">evaldo-leal-etal-2020-using</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.512</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.512</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>5821</start>
<end>5831</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Using Eye-tracking Data to Predict the Readability of Brazilian Portuguese Sentences in Single-task, Multi-task and Sequential Transfer Learning Approaches
%A Evaldo Leal, Sidney
%A Munguba Vieira, João Marcos
%A dos Santos Rodrigues, Erica
%A Nogueira Teixeira, Elisângela
%A Aluísio, Sandra
%Y Scott, Donia
%Y Bel, Nuria
%Y Zong, Chengqing
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F evaldo-leal-etal-2020-using
%X Sentence complexity assessment is a relatively new task in Natural Language Processing. One of its aims is to highlight in a text which sentences are more complex to support the simplification of contents for a target audience (e.g., children, cognitively impaired users, non-native speakers and low-literacy readers (Scarton and Specia, 2018)). This task is evaluated using datasets of pairs of aligned sentences including the complex and simple version of the same sentence. For Brazilian Portuguese, the task was addressed by (Leal et al., 2018), who set up the first dataset to evaluate the task in this language, reaching 87.8% of accuracy with linguistic features. The present work advances these results, using models inspired by (Gonzalez-Garduño and Søgaard, 2018), which hold the state-of-the-art for the English language, with multi-task learning and eye-tracking measures. First-Pass Duration, Total Regression Duration and Total Fixation Duration were used in two moments; first to select a subset of linguistic features and then as an auxiliary task in the multi-task and sequential learning models. The best model proposed here reaches the new state-of-the-art for Portuguese with 97.5% accuracy 1 , an increase of almost 10 points compared to the best previous results, in addition to proposing improvements in the public dataset after analysing the errors of our best model.
%R 10.18653/v1/2020.coling-main.512
%U https://aclanthology.org/2020.coling-main.512
%U https://doi.org/10.18653/v1/2020.coling-main.512
%P 5821-5831
Markdown (Informal)
[Using Eye-tracking Data to Predict the Readability of Brazilian Portuguese Sentences in Single-task, Multi-task and Sequential Transfer Learning Approaches](https://aclanthology.org/2020.coling-main.512) (Evaldo Leal et al., COLING 2020)
ACL