@inproceedings{tercon-dobrovoljc-2025-comparatree,
title = "{C}ompara{T}ree: A Multi-Level Comparative Treebank Analysis Tool",
author = "Ter{\v{c}}on, Luka and
Dobrovoljc, Kaja",
editor = {Jablotschkin, Sarah and
K{\"u}bler, Sandra and
Zinsmeister, Heike},
booktitle = "Proceedings of the 23rd International Workshop on Treebanks and Linguistic Theories (TLT, SyntaxFest 2025)",
month = aug,
year = "2025",
address = "Ljubljana, Slovenia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.tlt-1.15/",
pages = "129--139",
ISBN = "979-8-89176-291-6",
abstract = "ComparaTree is a tool for comparative treebank analysis that combines various methods of quantitative linguistic analysis to provide a general overview of the differences and similarities between two treebanks. The comparison tool covers a range of subfields of linguistic analysis, providing a summary of the differences and similarities in terms of the lexical diversity, n-gram diversity, part-of-speech and dependency relation proportions, syntactic complexity, and syntactic diversity. We explain the various quantitative analyses performed on every level along with the generation of graphical visualizations, which add value by enabling user-friendly comparisons at a glance. We exemplify the comparison process by presenting the results produced by the tool when comparing two treebanks from the Universal Dependencies collection."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tercon-dobrovoljc-2025-comparatree">
<titleInfo>
<title>ComparaTree: A Multi-Level Comparative Treebank Analysis Tool</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luka</namePart>
<namePart type="family">Terčon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kaja</namePart>
<namePart type="family">Dobrovoljc</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 23rd International Workshop on Treebanks and Linguistic Theories (TLT, SyntaxFest 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sarah</namePart>
<namePart type="family">Jablotschkin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sandra</namePart>
<namePart type="family">Kübler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heike</namePart>
<namePart type="family">Zinsmeister</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">979-8-89176-291-6</identifier>
</relatedItem>
<abstract>ComparaTree is a tool for comparative treebank analysis that combines various methods of quantitative linguistic analysis to provide a general overview of the differences and similarities between two treebanks. The comparison tool covers a range of subfields of linguistic analysis, providing a summary of the differences and similarities in terms of the lexical diversity, n-gram diversity, part-of-speech and dependency relation proportions, syntactic complexity, and syntactic diversity. We explain the various quantitative analyses performed on every level along with the generation of graphical visualizations, which add value by enabling user-friendly comparisons at a glance. We exemplify the comparison process by presenting the results produced by the tool when comparing two treebanks from the Universal Dependencies collection.</abstract>
<identifier type="citekey">tercon-dobrovoljc-2025-comparatree</identifier>
<location>
<url>https://aclanthology.org/2025.tlt-1.15/</url>
</location>
<part>
<date>2025-08</date>
<extent unit="page">
<start>129</start>
<end>139</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ComparaTree: A Multi-Level Comparative Treebank Analysis Tool
%A Terčon, Luka
%A Dobrovoljc, Kaja
%Y Jablotschkin, Sarah
%Y Kübler, Sandra
%Y Zinsmeister, Heike
%S Proceedings of the 23rd International Workshop on Treebanks and Linguistic Theories (TLT, SyntaxFest 2025)
%D 2025
%8 August
%I Association for Computational Linguistics
%C Ljubljana, Slovenia
%@ 979-8-89176-291-6
%F tercon-dobrovoljc-2025-comparatree
%X ComparaTree is a tool for comparative treebank analysis that combines various methods of quantitative linguistic analysis to provide a general overview of the differences and similarities between two treebanks. The comparison tool covers a range of subfields of linguistic analysis, providing a summary of the differences and similarities in terms of the lexical diversity, n-gram diversity, part-of-speech and dependency relation proportions, syntactic complexity, and syntactic diversity. We explain the various quantitative analyses performed on every level along with the generation of graphical visualizations, which add value by enabling user-friendly comparisons at a glance. We exemplify the comparison process by presenting the results produced by the tool when comparing two treebanks from the Universal Dependencies collection.
%U https://aclanthology.org/2025.tlt-1.15/
%P 129-139
Markdown (Informal)
[ComparaTree: A Multi-Level Comparative Treebank Analysis Tool](https://aclanthology.org/2025.tlt-1.15/) (Terčon & Dobrovoljc, TLT-SyntaxFest 2025)
ACL