News Headline Generation in Telugu
Keywords: News Headline Generation, Natural Language Processing, Machine Learning, Automated Headline Generation, Language Models, Deep Learning, Text Summarization, Indian Languages Processing, Computational Linguistics, Headlines in Telugu, Artificial Intelligence in Telugu, Fine-tuning, mBART50, mT5, IndicBART, Dataset Creation, Web Scraping, BLEU, ROUGE, Sentence Similarity
TL;DR: Created a dataset of Telugu article-headline pairs through web scraping, fine-tuned mBART50, mT5, and IndicBART for Telugu headline generation, and evaluated results using BLEU, ROUGE, and sentence similarity.
Abstract: News headline generation has seen significant advancements in resource-rich languages like the English language, leveraging sophisticated natural language processing (NLP) techniques. However, similar progress has not been observed for low-resource Indian languages, particularly Telugu. We focus on implementing news headline generation given the news article using an abstractive summarization approach, which enables the generation of contextually rich headlines by interpreting and rephrasing content using deep learning techniques. We create a dataset of articles and headlines scraped from the Telugu news website `Sakshi'. We use pre-trained language models such as mBART50, MT5, and IndicBART for fine-tuning using our dataset. Our findings show the effectiveness of fine-tuning pre-trained models for news headline-generation tasks in Telugu.
Submission Number: 63
Loading