@inproceedings{herrera-etal-2025-extraction,
title = "Extraction of Contrastive Rules from Syntactic Treebanks: A Case Study in {R}omance Languages",
author = "Herrera, Santiago and
Silai, Ioana-Madalina and
Corro, Caio and
Guillaume, Bruno and
Kahane, Sylvain",
editor = "Chen, Xinying and
Wang, Yaqin",
booktitle = "Proceedings of the Third Workshop on Quantitative Syntax (QUASY, SyntaxFest 2025)",
month = aug,
year = "2025",
address = "Ljubljana, Slovenia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.quasy-1.5/",
pages = "26--38",
ISBN = "979-8-89176-293-0",
abstract = "In this paper, we develop a data-driven contrastive framework to extract common and distinctive linguistic descriptions from syntactic treebanks. The extracted contrastive rules are defined by a statistically significant difference in precision and classified as common and distinctive rules across the set of treebanks. We illustrate our method by working on object word order using Universal Dependencies (UD) treebanks in 6 Romance languages: Brazilian Portuguese, Catalan, French, Italian, Romanian and Spanish. We discuss the limitations faced due to inconsistent annotation and the feasibility of conducting contrasting studies using the UD collection."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="herrera-etal-2025-extraction">
<titleInfo>
<title>Extraction of Contrastive Rules from Syntactic Treebanks: A Case Study in Romance Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Santiago</namePart>
<namePart type="family">Herrera</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ioana-Madalina</namePart>
<namePart type="family">Silai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Caio</namePart>
<namePart type="family">Corro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bruno</namePart>
<namePart type="family">Guillaume</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sylvain</namePart>
<namePart type="family">Kahane</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on Quantitative Syntax (QUASY, SyntaxFest 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xinying</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaqin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Ljubljana, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-293-0</identifier>
</relatedItem>
<abstract>In this paper, we develop a data-driven contrastive framework to extract common and distinctive linguistic descriptions from syntactic treebanks. The extracted contrastive rules are defined by a statistically significant difference in precision and classified as common and distinctive rules across the set of treebanks. We illustrate our method by working on object word order using Universal Dependencies (UD) treebanks in 6 Romance languages: Brazilian Portuguese, Catalan, French, Italian, Romanian and Spanish. We discuss the limitations faced due to inconsistent annotation and the feasibility of conducting contrasting studies using the UD collection.</abstract>
<identifier type="citekey">herrera-etal-2025-extraction</identifier>
<location>
<url>https://aclanthology.org/2025.quasy-1.5/</url>
</location>
<part>
<date>2025-08</date>
<extent unit="page">
<start>26</start>
<end>38</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Extraction of Contrastive Rules from Syntactic Treebanks: A Case Study in Romance Languages
%A Herrera, Santiago
%A Silai, Ioana-Madalina
%A Corro, Caio
%A Guillaume, Bruno
%A Kahane, Sylvain
%Y Chen, Xinying
%Y Wang, Yaqin
%S Proceedings of the Third Workshop on Quantitative Syntax (QUASY, SyntaxFest 2025)
%D 2025
%8 August
%I Association for Computational Linguistics
%C Ljubljana, Slovenia
%@ 979-8-89176-293-0
%F herrera-etal-2025-extraction
%X In this paper, we develop a data-driven contrastive framework to extract common and distinctive linguistic descriptions from syntactic treebanks. The extracted contrastive rules are defined by a statistically significant difference in precision and classified as common and distinctive rules across the set of treebanks. We illustrate our method by working on object word order using Universal Dependencies (UD) treebanks in 6 Romance languages: Brazilian Portuguese, Catalan, French, Italian, Romanian and Spanish. We discuss the limitations faced due to inconsistent annotation and the feasibility of conducting contrasting studies using the UD collection.
%U https://aclanthology.org/2025.quasy-1.5/
%P 26-38
Markdown (Informal)
[Extraction of Contrastive Rules from Syntactic Treebanks: A Case Study in Romance Languages](https://aclanthology.org/2025.quasy-1.5/) (Herrera et al., Quasy-SyntaxFest 2025)
ACL