Multimodal Neural Machine Translation System for English to Bengali

Shantipriya Parida, Subhadarshi Panda, Satya Prakash Biswal, Ketan Kotwal, Arghyadeep Sen, Satya Ranjan Dash, Petr Motlicek


Abstract
Multimodal Machine Translation (MMT) systems utilize additional information from other modalities beyond text to improve the quality of machine translation (MT). The additional modality is typically in the form of images. Despite proven advantages, it is indeed difficult to develop an MMT system for various languages primarily due to the lack of a suitable multimodal dataset. In this work, we develop an MMT for English-> Bengali using a recently published Bengali Visual Genome (BVG) dataset that contains images with associated bilingual textual descriptions. Through a comparative study of the developed MMT system vis-a-vis a Text-to-text translation, we demonstrate that the use of multimodal data not only improves the translation performance improvement in BLEU score of +1.3 on the development set, +3.9 on the evaluation test, and +0.9 on the challenge test set but also helps to resolve ambiguities in the pure text description. As per best of our knowledge, our English-Bengali MMT system is the first attempt in this direction, and thus, can act as a baseline for the subsequent research in MMT for low resource languages.
Anthology ID:
2021.mmtlrl-1.6
Volume:
Proceedings of the First Workshop on Multimodal Machine Translation for Low Resource Languages (MMTLRL 2021)
Month:
September
Year:
2021
Address:
Online (Virtual Mode)
Venue:
MMTLRL
SIG:
Publisher:
INCOMA Ltd.
Note:
Pages:
31–39
Language:
URL:
https://aclanthology.org/2021.mmtlrl-1.6
DOI:
Bibkey:
Cite (ACL):
Shantipriya Parida, Subhadarshi Panda, Satya Prakash Biswal, Ketan Kotwal, Arghyadeep Sen, Satya Ranjan Dash, and Petr Motlicek. 2021. Multimodal Neural Machine Translation System for English to Bengali. In Proceedings of the First Workshop on Multimodal Machine Translation for Low Resource Languages (MMTLRL 2021), pages 31–39, Online (Virtual Mode). INCOMA Ltd..
Cite (Informal):
Multimodal Neural Machine Translation System for English to Bengali (Parida et al., MMTLRL 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2021.mmtlrl-1.6.pdf