Urdu Poetry Generated by Using Deep Learning Techniques

TL;DR

This paper explores generating Urdu poetry using deep learning models like LSTM and GRU, aiming for accurate, pure Urdu poem creation from a diverse dataset without sampling, advancing NLP applications in Urdu language processing.

Contribution

It introduces a deep learning approach for Urdu poetry generation using LSTM and GRU models trained on a comprehensive dataset, emphasizing generating authentic Urdu text.

Findings

Models produced poetry with good accuracy

Generated poems are in pure Urdu, not Roman Urdu

Approach outperforms previous sampling methods

Abstract

This study provides Urdu poetry generated using different deep-learning techniques and algorithms. The data was collected through the Rekhta website, containing 1341 text files with several couplets. The data on poetry was not from any specific genre or poet. Instead, it was a collection of mixed Urdu poems and Ghazals. Different deep learning techniques, such as the model applied Long Short-term Memory Networks (LSTM) and Gated Recurrent Unit (GRU), have been used. Natural Language Processing (NLP) may be used in machine learning to understand, analyze, and generate a language humans may use and understand. Much work has been done on generating poetry for different languages using different techniques. The collection and use of data were also different for different researchers. The primary purpose of this project is to provide a model that generates Urdu poems by using data completely, not by sampling data. Also, this may generate poems in pure Urdu, not Roman Urdu, as in the base paper. The results have shown good accuracy in the poems generated by the model.