Recipe Generator: A Lightweight Transformer-Based Approach Using SentencePiece Tokenization
International Journal of Recent Advances in Engineering and Technology · 08.04.2026 · 15 (1) · 127-131
DOI: 10.65521/intjournalrecadvengtech.v15i1.2066 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Recent Advances in Engineering and Technology, online erschienen am 08.04.2026. Verfasst von Anushka Ghosh und 4 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-ND 4.0).
Abstract (Originalsprache)
Auto-generation of recipes is on the border of structured knowledge and open-ended language generation. The following paper introduces a light-weight encoder-decoder trans- former that is trained on a instruction-conditioned recipe dataset, in which SentencePeice tokenization can be effective to process culinary words. In the event a user query is a short query, which includes specifications on the type of cuisine, remodel produces a step- by- step cooking instructions. It is a model architecture, training process, evaluation process and a quantitative case study tour. Findings indicate that there are no changes in training and average BLEU scores, which proves that a smaller model is capable of producing useful recipes at a tenth of the computation cost. We also address the existing constraints.
Zitieren
APA
Ghosh, A., Dewangan, N., Srivastava, S., Chandra, A., & Mishra, A. (2026). Recipe Generator: A Lightweight Transformer-Based Approach Using SentencePiece Tokenization. International Journal of Recent Advances in Engineering and Technology, 15(1), 127-131. https://doi.org/10.65521/intjournalrecadvengtech.v15i1.2066
Vancouver
Ghosh A, Dewangan N, Srivastava S, Chandra A, Mishra A. Recipe Generator: A Lightweight Transformer-Based Approach Using SentencePiece Tokenization. International Journal of Recent Advances in Engineering and Technology. 2026;15(1):127-131. doi:10.65521/intjournalrecadvengtech.v15i1.2066
BibTeX
@article{Ghosh2026,
author = {Ghosh, Anushka and Dewangan, Narendra and Srivastava, Saksham and Chandra, Anjali and Mishra, Asmita},
title = {Recipe Generator: A Lightweight Transformer-Based Approach Using SentencePiece Tokenization},
journal = {International Journal of Recent Advances in Engineering and Technology},
year = {2026},
volume = {15},
number = {1},
pages = {127--131},
doi = {10.65521/intjournalrecadvengtech.v15i1.2066}
}
EUVIMED