Unveiling the Effectiveness of NLP-based DL Methods for Urdu Text Analysis

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F24%3A43972891" target="_blank" >RIV/49777513:23520/24:43972891 - isvavai.cz</a>

Výsledek na webu

<a href="https://link.springer.com/chapter/10.1007/978-3-031-75329-9_12" target="_blank" >https://link.springer.com/chapter/10.1007/978-3-031-75329-9_12</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-031-75329-9_12" target="_blank" >10.1007/978-3-031-75329-9_12</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Unveiling the Effectiveness of NLP-based DL Methods for Urdu Text Analysis

Popis výsledku v původním jazyce

The analysis of text data has become a significant challenge while its size is gradually increasing in massive amounts. Various textual analysis methods exist, dealing with different processing styles due to multiple data types, mainly for English. Therefore, the other low-resource languages are difficult to process due to the unavailability of intelligent methods. Similarly, Urdu, as a low-resource language, requires effective methods based on machine learning or deep learning mechanisms. Our study has identified the rarely used pure Urdu text dataset, an effective combination of embeddings, and the best combination of hyperparameters for DL methods trained on that dataset. According to the evaluation results, our study has also determined the best methods regarding embeddings, hyperparameters, and overall performance. Moreover, combining pre-trained BERT embeddings with the fine-tuned BiLSTM and BERT was the best method to cope with Urdu as a low-resource language. As per the findings, our study recommends the pre-trained embedding models and hyperparameters settings for Urdu text classification analysis.

Název v anglickém jazyce

Unveiling the Effectiveness of NLP-based DL Methods for Urdu Text Analysis

Popis výsledku anglicky

The analysis of text data has become a significant challenge while its size is gradually increasing in massive amounts. Various textual analysis methods exist, dealing with different processing styles due to multiple data types, mainly for English. Therefore, the other low-resource languages are difficult to process due to the unavailability of intelligent methods. Similarly, Urdu, as a low-resource language, requires effective methods based on machine learning or deep learning mechanisms. Our study has identified the rarely used pure Urdu text dataset, an effective combination of embeddings, and the best combination of hyperparameters for DL methods trained on that dataset. According to the evaluation results, our study has also determined the best methods regarding embeddings, hyperparameters, and overall performance. Moreover, combining pre-trained BERT embeddings with the fine-tuned BiLSTM and BERT was the best method to cope with Urdu as a low-resource language. As per the findings, our study recommends the pre-trained embedding models and hyperparameters settings for Urdu text classification analysis.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

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

Projekt

<a href="/cs/project/LM2018140" target="_blank" >LM2018140: e-Infrastruktura CZ</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2024

Kód důvěrnosti údajů

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

Název statě ve sborníku

Information Systems and Technological Advances for Sustainable Development. Lecture Notes in Information Systems and Organisation

ISBN

978-3-031-75328-2

ISSN

2195-4968

e-ISSN

2195-4976

Počet stran výsledku

12

Strana od-do

102-113

Název nakladatele

Springer Cham

Místo vydání

Cham

Místo konání akce

Košice

Datum konání akce

27. 5. 2024

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—