Urdu AI Dashboard

Monitoring AI enhancements in Urdu

Research Papers

Google Scholar papers focused on Urdu AI, LLMs, and datasets

2020 Urdu NLP

An unsupervised lexical normalization for Roman Hindi andUrdusentiment analysis

Authors:

K. Mehmood D. Essam K. Shafi M. K. Malik- Information Processing & … 2020

… becomes apparent while developingnaturallanguageprocessingapplications. This paper…Urdutext Normalization (TERUN). TERUN utilizes the linguistic aspects of Roman Hindi/Urdu…

2020 Urdu NLP

Is machine learning speaking my language? A critical look at theNLP-pipeline across 8 human languages

Authors:

E. Wali Y. Chen C. Mahoney T. Middleton…

… For Arabic andUrdu, we found many texts available as scanned images rather than textformat. With wide ranges of accuracy rates for OCR of 70 to 98% (Holley, 2009), OCR to convert …

2020 Urdu NLP

RomanUrdumulti-class offensive text detection using hybrid features and SVM

Authors:

T. Sajid M. Hassan M. Ali…

… works ofnaturallanguageprocessing(NLP) [11]. …Urdudata to convert the word into itsoriginal form. For this challenging task, we start working on making a dictionary for RomanUrdu…

2020 Urdu NLP

UrduTo Punjabi Machine Translation System

Authors:

U. P. Singh V. Goyal G. S. Lehal- … onNatural Language Processing… 2020

… As mentioned previously,Urduand Punjabi are resource-poor languages therefore we have… forUrdu. The word tokenization system forUrduis not simple like any other language. In …

2020 Urdu NLP

Authorship attribution inurdupoetry

Authors:

M. Dar

…Urdulanguage. For example, there is a demand of transcribing audio file to text file that isUrdulanguage audio file toUrdu…Urdulanguage processing inNaturalLanguageProcessing, …

2020 Urdu NLP

Urdufake news detection using generalized autoregressors

Authors:

A. F. U. R. Khiljia S. R. Laskara P. Pakraya…

… news detection task of theUrdulanguage. In this work, …Urdulanguage and developedpre-trained language models for giving an impetus for various downstreamNLPtasks in theUrdu…

2020 Urdu NLP

RomanUrdunews headline classification empowered with machine learning

Authors:

R. A. Naqvi M. A. Khan N. Malik S. Saqib…

…naturallanguageprocessingbut there have been only a few efforts to examine romanUrdu… For this, we usedUrduto the RomanUrdutransliterator created by ijunoon.com [ijunoon (…

2020 Urdu NLP

Multi-text classification ofUrdu/Roman using machine learning and natural language preprocessing techniques

Authors:

M. Chhajro M. Khuhro K. Kumar A. Wagan…

… -text forUrduand Roman language usingNaturalLanguageprocessingand Machine Learning… The main news corpus data consists of 10500 news inUrduand RomanUrdulanguage …

2020 Urdu NLP

RomanUrduheadline news text classification using RNN, LSTM and CNN

Authors:

I. A. Kandhro S. Z. Jumani K. Kumar…

… ofnaturallanguageprocessing(NLP) to evaluate verbal and language patterns [Brindha …in romanUrdublogs and sites.Urduscript is not so common and romanUrduis used for the …

2020 Urdu NLP

Towards building aurdulanguage corpus using common crawl

Authors:

H. M. Shafiq B. Tahir…

… researches andNaturalLanguageProcessing(NLP) applications. … %Urdudomains arehosted in the USA with at least 1% ofUrdu. This figure increases to 70% for a minimum 5%Urdu…

2020 Urdu NLP

Sentiment analysis of user reviews about hotel in RomanUrdu

Authors:

M. K. Nazir M. Ahmad H. Ahmad…

… include in the RomanUrdudataset because RomanUrducomments are used in this research.… Chen, “A review ofnaturallanguageprocessingtechniques for opinion mining systems,” …

2020 Urdu NLP

Lexical variation and sentiment analysis of RomanUrdusentences with deep neural networks

Authors:

M. A. Manzoor S. Mamoon S. K. Tao Z. Ali…

…Urduthat has more complex syntax and numerous lexical variations, few research is carriedout on it. In this paper, for sentiment analysis of RomanUrdu, … the RomanUrdusentences. …