Consistency-Constrained Joint Learning of Dependency, Constituency, and Grammatical Roles in Low-Resource Uzbek
Authors:
- Botir Boltayevich ElovBEBotir Boltayevich Elov
- Mukhabbat Matyakubovna KurbanovaMKMukhabbat Matyakubovna Kurbanova
- Ruhillo Habibovich AlaevRARuhillo Habibovich Alaev
- Oqila Xolmo'Minovna AbdullayevaOAOqila Xolmo'Minovna Abdullayeva
- Shakhnoza Burievna NashirovaSNShakhnoza Burievna Nashirova
- Sayyora Abdinaviyevna NurmatovaSNSayyora Abdinaviyevna Nurmatova
Preprint
- 9 November 2026
- preprint
- Published by MDPI AG in Preprints.org
Abstract
Complementary syntactic annotations may support learning in low-resource languages, but compatibility penalties require evaluation beyond parameter sharing. We study dependency parsing, constituency parsing, grammatical-role labeling and chunking in Uzbek using a shared XLM-R encoder, structured predictors and empirical implication penalties during training. UzSyn contains 1,123 sentences and 4,955 tokens, partitioned into 898 training, 112 development and 113 test sentences. Comparisons used five seeds, independent models and unconstrained multi-task learning. With all training sentences, the constrained model reached 85.53% labeled attachment score and 76.55% constituency F1. Differences from unconstrained multi-task learning were +0.52 and +0.06 percentage points; paired 97.5% confidence intervals of [−1.71, 2.93] and [−2.08, 2.52] included zero. At the exploratory 50% final-fitting fraction, constituency and chunk F1 increased by 4.04 and 2.97 points, with descriptive 95% intervals excluding zero. Fitting budgets excluded prior annotation access during rule-template design. Coherence changes varied by rule family. Constrained fitting required 3.66 times the mean elapsed fitting time of unconstrained multi-task learning. The findings identify intermediate-budget gains for replication while leaving full-data superiority unresolved. Independent linguistic validation and external evaluation are needed before broader accuracy or annotation-saving claims.Keywords
All Related Versions
This publication has 11 references indexed in Scilit:
- Dynamic Head Selection for Neural Lexicalized Constituency Parsing2025
- Headed-Span-Based Projective Dependency Parsing2022
- Universal DependenciesComputational Linguistics, 2021
- Fast and Accurate Neural CRF Constituency Parsing2020
- Parsing All: Syntax and Semantics, Dependencies and Spans2020
- Unsupervised Cross-lingual Representation Learning at Scale2020
- Sequence Labeling Parsing by Learning across Representations2019
- Head-Driven Phrase Structure Grammar Parsing on Penn Treebank2019
- Constituency Parsing with a Self-Attentive Encoder2018
- Harnessing Deep Neural Networks with Logic Rules2016