Version 1
: Received: 12 December 2023 / Approved: 13 December 2023 / Online: 13 December 2023 (05:04:39 CET)
How to cite:
Alkmim, K.; Patel, R.; Dave, D. Learning Machine Translation with Linguistic Interpretation. Preprints2023, 2023120921. https://doi.org/10.20944/preprints202312.0921.v1
Alkmim, K.; Patel, R.; Dave, D. Learning Machine Translation with Linguistic Interpretation. Preprints 2023, 2023120921. https://doi.org/10.20944/preprints202312.0921.v1
Alkmim, K.; Patel, R.; Dave, D. Learning Machine Translation with Linguistic Interpretation. Preprints2023, 2023120921. https://doi.org/10.20944/preprints202312.0921.v1
APA Style
Alkmim, K., Patel, R., & Dave, D. (2023). Learning Machine Translation with Linguistic Interpretation. Preprints. https://doi.org/10.20944/preprints202312.0921.v1
Chicago/Turabian Style
Alkmim, K., Rodolfo Patel and Dolcetti Dave. 2023 "Learning Machine Translation with Linguistic Interpretation" Preprints. https://doi.org/10.20944/preprints202312.0921.v1
Abstract
The Transformer architecture, while adept at capturing context through self-attention, falls short in encapsulating complex syntactic structures effectively. Addressing this gap, we introduce the Linguistic Structure through Graphical Interpretation with BERT (LSGIB) approach in Machine Translation (MT) frameworks. Combining the strengths of Graph Attention Network (GAT) and BERT, LSGIB intricately captures syntactic dependencies as explicit knowledge from the source language. This enhances the source language representation and aids in more accurate target language generation. Our empirical analysis leverages gold-standard syntax-annotated sentences and employs a Quality Estimation (QE) model. This approach enables us to assess translation improvements in terms of syntactic accuracy, extending beyond traditional BLEU score metrics. The LSGIB model demonstrates superior translation quality across diverse MT tasks, maintaining robust BLEU scores. Our study delves into the optimal sentence lengths benefiting from LSGIB and identifies which syntactic dependencies are more precisely captured. We observe that GAT's ability to learn specific dependency relations directly influences the translation quality of sentences with those relations. Additionally, we discover that incorporating syntactic structure into BERT's intermediate and lower layers offers a novel approach to modeling linguistic structure in source sentences.
Keywords
Machine Translation; Linguistic Interpretation; Attention Models
Subject
Computer Science and Mathematics, Artificial Intelligence and Machine Learning
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
