TY  - JOUR
AU  - M. Sumanjali
AU  - P. Swathi
PY  - 2025
DA  - 2025/03/05
TI  - Exploring Attention Mechanisms In Transformer Models For Machine Translation
JO  - Global Journal of Engineering Innovations and Interdisciplinary Research
VL  - 5
IS  - 1
AB  - This work delves into the utilization of attention mechanisms within Transformer models for machine
translation, aiming to enhance the efficacy and interpretability of these models. By systematically
analyzing various attention mechanisms, such as self-attention and cross-attention, the study investigates
their impact on translation accuracy and computational efficiency. The research also explores the
interplay between different attention layers and the overall performance of Transformer-based systems
in diverse linguistic contexts. Our findings highlight significant improvements in translation quality
and model interpretability when leveraging advanced attention strategies. This work provides a
comprehensive evaluation of current techniques and proposes optimizations that could advance the
state-of-the-art in machine translation.
SN  - 3066-1226
UR  - https://dx.doi.org/10.33425/3066-1226.1076
DO  - 10.33425/3066-1226.1076