@inproceedings{juzek-2024-syntactic-acceptability,
title = "The Syntactic Acceptability Dataset (Preview): A Resource for Machine Learning and Linguistic Analysis of {E}nglish",
author = "Juzek, Tom S",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1401",
pages = "16113--16120",
abstract = "We present a preview of the Syntactic Acceptability Dataset, a resource being designed for both syntax and computational linguistics research. In its current form, the dataset comprises 1,000 English sequences from the syntactic discourse: Half from textbooks and half from the journal Linguistic Inquiry, the latter to ensure a representation of the contemporary discourse. Each entry is labeled with its grammatical status ({``}well-formedness{''} according to syntactic formalisms) extracted from the literature, as well as its acceptability status ({``}intuitive goodness{''} as determined by native speakers) obtained through crowdsourcing, with highest experimental standards. Even in its preliminary form, this dataset stands as the largest of its kind that is publicly accessible. We also offer preliminary analyses addressing three debates in linguistics and computational linguistics: We observe that grammaticality and acceptability judgments converge in about 83{\%} of the cases and that {``}in-betweenness{''} occurs frequently. This corroborates existing research. We also find that while machine learning models struggle with predicting grammaticality, they perform considerably better in predicting acceptability. This is a novel finding. Future work will focus on expanding the dataset.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="juzek-2024-syntactic-acceptability">
<titleInfo>
<title>The Syntactic Acceptability Dataset (Preview): A Resource for Machine Learning and Linguistic Analysis of English</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="given">S</namePart>
<namePart type="family">Juzek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a preview of the Syntactic Acceptability Dataset, a resource being designed for both syntax and computational linguistics research. In its current form, the dataset comprises 1,000 English sequences from the syntactic discourse: Half from textbooks and half from the journal Linguistic Inquiry, the latter to ensure a representation of the contemporary discourse. Each entry is labeled with its grammatical status (“well-formedness” according to syntactic formalisms) extracted from the literature, as well as its acceptability status (“intuitive goodness” as determined by native speakers) obtained through crowdsourcing, with highest experimental standards. Even in its preliminary form, this dataset stands as the largest of its kind that is publicly accessible. We also offer preliminary analyses addressing three debates in linguistics and computational linguistics: We observe that grammaticality and acceptability judgments converge in about 83% of the cases and that “in-betweenness” occurs frequently. This corroborates existing research. We also find that while machine learning models struggle with predicting grammaticality, they perform considerably better in predicting acceptability. This is a novel finding. Future work will focus on expanding the dataset.</abstract>
<identifier type="citekey">juzek-2024-syntactic-acceptability</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1401</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>16113</start>
<end>16120</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Syntactic Acceptability Dataset (Preview): A Resource for Machine Learning and Linguistic Analysis of English
%A Juzek, Tom S.
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F juzek-2024-syntactic-acceptability
%X We present a preview of the Syntactic Acceptability Dataset, a resource being designed for both syntax and computational linguistics research. In its current form, the dataset comprises 1,000 English sequences from the syntactic discourse: Half from textbooks and half from the journal Linguistic Inquiry, the latter to ensure a representation of the contemporary discourse. Each entry is labeled with its grammatical status (“well-formedness” according to syntactic formalisms) extracted from the literature, as well as its acceptability status (“intuitive goodness” as determined by native speakers) obtained through crowdsourcing, with highest experimental standards. Even in its preliminary form, this dataset stands as the largest of its kind that is publicly accessible. We also offer preliminary analyses addressing three debates in linguistics and computational linguistics: We observe that grammaticality and acceptability judgments converge in about 83% of the cases and that “in-betweenness” occurs frequently. This corroborates existing research. We also find that while machine learning models struggle with predicting grammaticality, they perform considerably better in predicting acceptability. This is a novel finding. Future work will focus on expanding the dataset.
%U https://aclanthology.org/2024.lrec-main.1401
%P 16113-16120
Markdown (Informal)
[The Syntactic Acceptability Dataset (Preview): A Resource for Machine Learning and Linguistic Analysis of English](https://aclanthology.org/2024.lrec-main.1401) (Juzek, LREC-COLING 2024)
ACL