LANGUAGE TRANSLATION USING TRANSFORMER ALGORITHM IN MACHINE LEARNING
Abstract
This study investigates the application of the (TRANSFORMER ALGORITHM) model for enhancing machine translation accuracy. While traditional natural language processing (NLP) models have relied on sequential, unidirectional text processing, transformer algorithm’s bidirectional approach allows for a deeper, context-aware understanding of language. The model is pretrained on a large corpus of text, enabling it to generate rich, contextualized word embedding’s that capture the nuances of language more effectively.We propose a methodology that incorporates a pertained transformer algorithm encoder with a transformer-based decoder for a specific translation task from [Source Language] to [Target Language]. The model is initialized with the pretained transformer algorithm parameters and then fine-tuned on a smaller, labeled dataset to adapt its general language knowledge to the specific translation domain.
Full-Text Access Notice
In accordance with the NERD Policy on promoting peer-reviewed publication, public access to the full text of a project, thesis or dissertation is restricted for three years, allowing the author and supervisors sufficient time to pursue peer-reviewed publication.
During this period, researchers with legitimate academic or research purposes may request authorisation directly from the author to enable NERD to release the indexed full texts of the work using the form below.