Hybrid Deep Learning Approaches for Assamese Part-of-Speech Tagging Using BIS Tag Set

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F26%3AQR3BPYXU" target="_blank" >RIV/00216208:11320/26:QR3BPYXU - isvavai.cz</a>

Result on the web

<a href="http://dx.doi.org/10.1016/j.procs.2025.04.509" target="_blank" >http://dx.doi.org/10.1016/j.procs.2025.04.509</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.procs.2025.04.509" target="_blank" >10.1016/j.procs.2025.04.509</a>

Result language

angličtina

Original language name

Hybrid Deep Learning Approaches for Assamese Part-of-Speech Tagging Using BIS Tag Set

Original language description

In this study, a parts-of-speech (POS) tagger designed exclusively for the Assamese language, utilizing advanced neural network architectures such as Long Short-Term Memory (LSTM) and Bidirectional LSTM (Bi-LSTM) was proposed. The primary objective is to accomplish high-accuracy POS tagging for Assamese text using the Bureau of Indian Standards (BIS) tagset. A large Assamese corpus was created and annotated with BIS-compliant POS tags. After painstaking data preprocessing to clean and tokenize the text, words and tags were turned into numerical representations. The neural network architecture includes an embedding layer with pre-trained word embeddings, an output layer for POS tag prediction, and several LSTM and Bi-LSTM layers that recognize sequential patterns. The models include LSTM at the word and character level and LSTM-CRF and Bi-LSTM-CRF variants. The LSTM-word level model achieved 87.39% accuracy, LSTM-CRF word level 89.13%, Bi-LSTM word level 91.83%, Bi-LSTM-CRF word level 93.23%, Bi-LSTM character level 96.17%, and Bi-LSTM-CRF word level 94.24%. This work outperforms prior Assamese POS tagging efforts and provides useful insights for related languages. © 2024 The Authors. Published by ELSEVIER B.V.

Czech name

—

Czech description

—

Type

D - Article in proceedings

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

Article name in the collection

Procedia Comput. Sci.

ISBN

—

ISSN

18770509

e-ISSN

—

Number of pages

10

Pages from-to

2469-2478

Publisher name

Elsevier B.V.

Place of publication

—

Event location

Dehradun

Event date

Jan 1, 2026

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—