Parsing the Uzbek language universal dependency treebank using a bi-affine neural model

Matlatipov, Sanatbek

Al-Farg'oniy avlodlari · 2025-yil

Annotatsiya

This study implements the deep bi-affine neural dependency parsing for the Uzbek language using a available Universal Dependency treebank. Key aspects such as attention layers, network architecture, embedding dropout rates, and optimization parameters (e.g., Adam optimizer) are discussed comprehensively. Experimental results demonstrate the bi-affine model achieves a UAS of 79.5% and a LAS of 72.4%, significantly outperforming a transition-based baseline parser by 6.7% (UAS) and 7.4% (LAS). 

Maqola ma’lumotlari
MualliflarMatlatipov, Sanatbek
JurnalAl-Farg'oniy avlodlari
Nashr sanasi2025-03-23
Son1
Betlar143-148
TilRus

Kalit so‘zlar

синтаксический анализ зависимостей, би-аффинное внимание, Узбекский язык, низкоресурсные языки, нейронные сети, Universal Dependencies, BiLSTM, dependency parsing, Uzbek language, bi-affine attention, BiLSTM, neural networks, low-resource, NLP (Natural Language Processing), Universal Dependencies, O'zbek tili, bi-affin neyron modeli, BiLSTM, chuqur neyron tarmoqlari, kam resursli tillar universal bog‘liqliklar

Ilmiy soha

Al-Farg'oniy avlodlari jurnalidan boshqa maqolalar

Al-Farg'oniy avlodlari — barcha maqolalar