Universal constituency treebanking and parsing: A pilot study

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F26%3AIR8EH96X" target="_blank" >RIV/00216208:11320/26:IR8EH96X - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1016/j.csl.2025.101826" target="_blank" >http://dx.doi.org/10.1016/j.csl.2025.101826</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.csl.2025.101826" target="_blank" >10.1016/j.csl.2025.101826</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Universal constituency treebanking and parsing: A pilot study

Popis výsledku v původním jazyce

Universal language processing is crucial for developing models that work across multiple languages. However, universal constituency parsing has lagged due to the lack of annotated universal constituency (UC) treebanks. To address this, we propose two cost-effective approaches. First, we unify existing annotated language-specific treebanks using phrase label mapping to create UC trees, but this is limited to only a handful of languages. Second, we develop a novel method to convert Universal Dependency (UD) treebanks into UC treebanks using large language models (LLMs) with syntactic knowledge, enabling the construction of UC treebanks for over 150 languages. We adopt the graph-based max margin model as our baseline and introduce a language adapter to fine-tune the universal parser. Our experiments show that the language adapter maintains performance for high-resource languages and improves performance for low-resource languages. We evaluate different scales of multilingual pre-trained models, confirming the effectiveness and robustness of our approach. In summary, we conduct the first pilot study on universal constituency parsing, introducing novel methods for creating and utilizing UC treebanks, thereby advancing treebanking and parsing methodologies.1 © 2025 Elsevier Ltd

Název v anglickém jazyce

Universal constituency treebanking and parsing: A pilot study

Popis výsledku anglicky

Universal language processing is crucial for developing models that work across multiple languages. However, universal constituency parsing has lagged due to the lack of annotated universal constituency (UC) treebanks. To address this, we propose two cost-effective approaches. First, we unify existing annotated language-specific treebanks using phrase label mapping to create UC trees, but this is limited to only a handful of languages. Second, we develop a novel method to convert Universal Dependency (UD) treebanks into UC treebanks using large language models (LLMs) with syntactic knowledge, enabling the construction of UC treebanks for over 150 languages. We adopt the graph-based max margin model as our baseline and introduce a language adapter to fine-tune the universal parser. Our experiments show that the language adapter maintains performance for high-resource languages and improves performance for low-resource languages. We evaluate different scales of multilingual pre-trained models, confirming the effectiveness and robustness of our approach. In summary, we conduct the first pilot study on universal constituency parsing, introducing novel methods for creating and utilizing UC treebanks, thereby advancing treebanking and parsing methodologies.1 © 2025 Elsevier Ltd

Druh

J_SC - Článek v periodiku v databázi SCOPUS

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

—

Rok uplatnění

2026

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Computer Speech and Language

ISSN

0885-2308

e-ISSN

—

Svazek periodika

95

Číslo periodika v rámci svazku

2026

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

16

Strana od-do

1-16

Kód UT WoS článku

—

EID výsledku v databázi Scopus

2-s2.0-105007423678