INTERNATIONAL JOURNAL OF NOVEL RESEARCH AND DEVELOPMENT International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2456-4184 | Impact factor: 8.76 | ESTD Year: 2016
Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.76 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
Text classification is an essential task in natural language processing (NLP) that involves assigning a category or label to a given text. While significant progress has been made in text classification for high-resource languages, low-resource languages still pose a significant challenge. In this paper, we explore the effectiveness of transfer learning techniques for text classification in low-resource languages. Specifically, we investigate the performance of pre-trained language models, such as BERT and GPT, on a text classification task in a low-resource language.
We conduct experiments on a publicly available dataset of news articles in the Nepali language, which is a low-resource language. We compare the performance of several transfer learning models against traditional machine learning models and baseline models. Our results show that transfer learning models outperform the traditional machine learning models and the baseline models, achieving an F1 score of 0.87.
We also perform an ablation study to investigate the effect of different training strategies and model architectures on the performance of transfer learning models. Our findings suggest that fine-tuning a pre-trained language model on a small amount of task-specific data is an effective strategy for text classification in low-resource languages.
Overall, our study highlights the potential of transfer learning for text classification in low-resource languages and provides valuable insights for researchers and practitioners working on NLP tasks in low-resource settings.
Keywords: Transfer learning, text classification, low-resource languages, pre-trained language models, Nepali language.
Keywords:
transfer learning, text classification, low-resource languages, pre-trained language models, Nepali language.
Cite Article:
"'Exploring the Effectiveness of Transfer Learning for Text Classification in Low-Resource Languages'", International Journal of Novel Research and Development (www.ijnrd.org), ISSN:2456-4184, Vol.8, Issue 5, page no.e24-e49, May-2023, Available :http://www.ijnrd.org/papers/IJNRD2305404.pdf
Downloads:
000118759
ISSN:
2456-4184 | IMPACT FACTOR: 8.76 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.76 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Facebook Twitter Instagram LinkedIn