Research Article
A domain-adapted abstractive Transformer model for multilingual summarization of agricultural literature
|
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
|
| Volume 187 - Issue 81 |
| Published: February 2026 |
| Authors: Chandrakala D., Jayanth R., Gowtham P., Bala Pranav V.S. |
10.5120/ijca2026926407
|
Chandrakala D., Jayanth R., Gowtham P., Bala Pranav V.S. . A domain-adapted abstractive Transformer model for multilingual summarization of agricultural literature. International Journal of Computer Applications. 187, 81 (February 2026), 26-31. DOI=10.5120/ijca2026926407
@article{ 10.5120/ijca2026926407,
author = { Chandrakala D.,Jayanth R.,Gowtham P.,Bala Pranav V.S. },
title = { A domain-adapted abstractive Transformer model for multilingual summarization of agricultural literature },
journal = { International Journal of Computer Applications },
year = { 2026 },
volume = { 187 },
number = { 81 },
pages = { 26-31 },
doi = { 10.5120/ijca2026926407 },
publisher = { Foundation of Computer Science (FCS), NY, USA }
}
%0 Journal Article
%D 2026
%A Chandrakala D.
%A Jayanth R.
%A Gowtham P.
%A Bala Pranav V.S.
%T A domain-adapted abstractive Transformer model for multilingual summarization of agricultural literature%T
%J International Journal of Computer Applications
%V 187
%N 81
%P 26-31
%R 10.5120/ijca2026926407
%I Foundation of Computer Science (FCS), NY, USA
Abstract
It is hard for agricultural researchers and forest rangers to get timely, useful information from the growing amount of multilingual agricultural literature. This paper describes an abstractive summarization system that has been adapted to work in a specific field. It uses the Google mT5 Transformer model, which has been fine-tuned on data from the agricultural field, to make short summaries in more than 100 languages. This multilingual feature lets you access content that is specific to your region without having to translate it first, which makes it easier for everyone to understand. The system has an internal domain-specific vector database (using FAISS) that lets you quickly find relevant documents. It also has an Agentic RAG retrieval system that lets you dynamically query external scientific sources (like PubMed and Springer Nature) when you need more information. Evaluation shows that the summarization quality and coverage are better than static baselines. This helps researchers and rangers quickly find and share agricultural knowledge.
References
- A. Vaswani et al., “Attention Is All You Need,” Proceedings of the 31st International Conference on Neural Information Processing Systems (NeurIPS), vol. 30, pp. 5998–6008, 2017.
- C. Raffel et al., “Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer,” Journal of Machine Learning Research, vol. 21, no. 140, pp. 1–67, 2020.
- L. Xue et al., “mT5: A Massively Multilingual Pre-trained Text-to-Text Transformer,” Proceedings of NAACL 2021, pp. 483–498, 2021.
- P. Lewis et al., “Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks,” Advances in Neural Information Processing Systems (NeurIPS), vol. 33, pp. 9459–9474, 2020.
- N. Reimers and I. Gurevych, “Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks,” Proceedings of EMNLP 2019, pp. 3982–3992, 2019.
- J. Johnson, M. Douze, and H. Jégou, “Billion-Scale Similarity Search with GPUs,” IEEE Transactions on Big Data, vol. 7, no. 3, pp. 535–547, 2019.
- Y. Wang and A. Singh, “Agent-Based Intelligent Information Retrieval for Dynamic Knowledge Environments,” IEEE Transactions on Knowledge and Data Engineering, vol. 35, no. 4, pp. 1567–1580, 2023.
- D. Weissenbacher et al., “Multilingual Natural Language Processing in Agricultural and Environmental Domains,” Journal of Computational Linguistics, vol. 50, no. 1, pp. 145–167, 2024.
- Food and Agriculture Organization of the United Nations (FAO), Artificial Intelligence in Agriculture: Opportunities and Challenges, FAO Publications, Rome, Italy, 2023.
- Indian Council of Agricultural Research (ICAR), Artificial Intelligence Applications in Indian Agriculture, ICAR Report Series, vol. 78, no. 2, pp. 1–45, 2024.
Index Terms
Keywords