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

Result code in 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>

Result on the web

<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>

Result language

angličtina

Original language name

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

Original language description

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.

Czech name

—

Czech description

—

Type

J_SC - Article in a specialist periodical, which is included in the SCOPUS database

CEP classification

—

OECD FORD branch

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

Project

—

Continuities

—

Publication year

2025

Confidentiality

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

Name of the periodical

PLOS ONE

ISSN

1932-6203

e-ISSN

—

Volume of the periodical

20

Issue of the periodical within the volume

9 September

Country of publishing house

US - UNITED STATES

Number of pages

40

Pages from-to

1-40

UT code for WoS article

—

EID of the result in the Scopus database

2-s2.0-105017184700