Multi-task learning by using contextualized word representations for syntactic parsing of a morphologically rich language

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F26%3AUYEJKP7I" target="_blank" >RIV/00216208:11320/26:UYEJKP7I - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1371/journal.pone.0332580" target="_blank" >https://doi.org/10.1371/journal.pone.0332580</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1371/journal.pone.0332580" target="_blank" >10.1371/journal.pone.0332580</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Multi-task learning by using contextualized word representations for syntactic parsing of a morphologically rich language

Popis výsledku v původním jazyce

We address the challenge of syntactic parsing for Urdu, a morphologically rich language, and present state-of-the-art results for both constituency and dependency parsing. This paper offers four major contributions: 1) the conversion of the CLE-UTB phrase structure treebank into a dependency treebank by developing language-specific head-word and phrase-to-dependency label mapping rules; 2) a novel sequence labeling scheme that transforms the parsing task into a unified representation; 3) the training of contextualized word representations on a large 220 million tokens Urdu corpus collected from the web; and 4) development of parsing framework using two learning paradigms, single-task and multi-task learning. Several post-processing rules are applied to improve the quality of the automatically converted dependency structure treebank. The proposed sequence labeling scheme enables the use of a shared architecture that learns the syntactic structures from both grammatical structures simultaneously and hence improves generalization. Experiments show that the multi-task learning setup significantly enhances parsing performance, achieving an F1 score of 91.39 for constituency parsing (an improvement of 3.29 points) and a labeled attachment score of 85.69 for dependency parsing (an improvement of 1.49 points). These results demonstrate that learning cross-task representations provides measurable benefits and advances the state of syntactic parsing for Urdu. © 2025 Ehsan et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

Název v anglickém jazyce

Multi-task learning by using contextualized word representations for syntactic parsing of a morphologically rich language

Popis výsledku anglicky

We address the challenge of syntactic parsing for Urdu, a morphologically rich language, and present state-of-the-art results for both constituency and dependency parsing. This paper offers four major contributions: 1) the conversion of the CLE-UTB phrase structure treebank into a dependency treebank by developing language-specific head-word and phrase-to-dependency label mapping rules; 2) a novel sequence labeling scheme that transforms the parsing task into a unified representation; 3) the training of contextualized word representations on a large 220 million tokens Urdu corpus collected from the web; and 4) development of parsing framework using two learning paradigms, single-task and multi-task learning. Several post-processing rules are applied to improve the quality of the automatically converted dependency structure treebank. The proposed sequence labeling scheme enables the use of a shared architecture that learns the syntactic structures from both grammatical structures simultaneously and hence improves generalization. Experiments show that the multi-task learning setup significantly enhances parsing performance, achieving an F1 score of 91.39 for constituency parsing (an improvement of 3.29 points) and a labeled attachment score of 85.69 for dependency parsing (an improvement of 1.49 points). These results demonstrate that learning cross-task representations provides measurable benefits and advances the state of syntactic parsing for Urdu. © 2025 Ehsan et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

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

2025

Kód důvěrnosti údajů

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

Název periodika

PLOS ONE

ISSN

1932-6203

e-ISSN

—

Svazek periodika

20

Číslo periodika v rámci svazku

9 September

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

40

Strana od-do

1-40

Kód UT WoS článku

—

EID výsledku v databázi Scopus

2-s2.0-105017184700