@inproceedings{ishii-miyao-2025-flatness,
title = "On the Flatness, Non-linearity, and Branching Direction of Natural Language and Random Constituency Trees: Analyzing Structural Variation within and across Languages",
author = "Ishii, Taiga and
Miyao, Yusuke",
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-1.12/",
pages = "90--104",
ISBN = "979-8-89176-293-0",
abstract = "Natural languages exhibit remarkable diversity in their syntactic structures. Previous research has investigated the cross-lingual differences in local structural features such as word order or dependency relations. However, considering structural variation within individual language, it remains unclear how such features influence the variation in the overall constituency tree structure and hence the structural variation across languages. To this end, we focus on the shape of constituency trees, analyzing the cross-lingual overlap in the distributions of flatness, non-linearity, and branching direction. While acknowledging that the findings may be influenced by the potential annotation idiosyncrasies across treebanks, the experiments quantitatively suggest that flatness and branching direction vary significantly across languages. As for non-linearity, the cross-lingual difference was relatively small, and the distributions tend to skew towards linear structures. Furthermore, comparison with randomly generated trees suggests that while phrase category and frequency information is crucial for reproducing the branching direction found in natural languages, non-linearity can be replicated reasonably well even without such information."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ishii-miyao-2025-flatness">
<titleInfo>
<title>On the Flatness, Non-linearity, and Branching Direction of Natural Language and Random Constituency Trees: Analyzing Structural Variation within and across Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Taiga</namePart>
<namePart type="family">Ishii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yusuke</namePart>
<namePart type="family">Miyao</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>Natural languages exhibit remarkable diversity in their syntactic structures. Previous research has investigated the cross-lingual differences in local structural features such as word order or dependency relations. However, considering structural variation within individual language, it remains unclear how such features influence the variation in the overall constituency tree structure and hence the structural variation across languages. To this end, we focus on the shape of constituency trees, analyzing the cross-lingual overlap in the distributions of flatness, non-linearity, and branching direction. While acknowledging that the findings may be influenced by the potential annotation idiosyncrasies across treebanks, the experiments quantitatively suggest that flatness and branching direction vary significantly across languages. As for non-linearity, the cross-lingual difference was relatively small, and the distributions tend to skew towards linear structures. Furthermore, comparison with randomly generated trees suggests that while phrase category and frequency information is crucial for reproducing the branching direction found in natural languages, non-linearity can be replicated reasonably well even without such information.</abstract>
<identifier type="citekey">ishii-miyao-2025-flatness</identifier>
<location>
<url>https://aclanthology.org/2025.quasy-1.12/</url>
</location>
<part>
<date>2025-08</date>
<extent unit="page">
<start>90</start>
<end>104</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T On the Flatness, Non-linearity, and Branching Direction of Natural Language and Random Constituency Trees: Analyzing Structural Variation within and across Languages
%A Ishii, Taiga
%A Miyao, Yusuke
%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 ishii-miyao-2025-flatness
%X Natural languages exhibit remarkable diversity in their syntactic structures. Previous research has investigated the cross-lingual differences in local structural features such as word order or dependency relations. However, considering structural variation within individual language, it remains unclear how such features influence the variation in the overall constituency tree structure and hence the structural variation across languages. To this end, we focus on the shape of constituency trees, analyzing the cross-lingual overlap in the distributions of flatness, non-linearity, and branching direction. While acknowledging that the findings may be influenced by the potential annotation idiosyncrasies across treebanks, the experiments quantitatively suggest that flatness and branching direction vary significantly across languages. As for non-linearity, the cross-lingual difference was relatively small, and the distributions tend to skew towards linear structures. Furthermore, comparison with randomly generated trees suggests that while phrase category and frequency information is crucial for reproducing the branching direction found in natural languages, non-linearity can be replicated reasonably well even without such information.
%U https://aclanthology.org/2025.quasy-1.12/
%P 90-104
Markdown (Informal)
[On the Flatness, Non-linearity, and Branching Direction of Natural Language and Random Constituency Trees: Analyzing Structural Variation within and across Languages](https://aclanthology.org/2025.quasy-1.12/) (Ishii & Miyao, Quasy-SyntaxFest 2025)
ACL