Multimodal neural machine translation for low-resource
language pairs using synthetic data
Dutta Chowdhury, Koel, Hasanuzzaman, MohammedORCID: 0000-0003-1838-0091 and Liu, QunORCID: 0000-0002-7000-1792
(2018)
Multimodal neural machine translation for low-resource
language pairs using synthetic data.
In: Workshop on Deep Learning Approaches for Low-Resource NLP, 19 July 2018, Melbourne, Australia.
In this paper, we investigate the effectiveness of training a multimodal neural machine translation (MNMT) system with image features for a lowresource language pair, Hindi and English, using synthetic data. A threeway parallel corpus which contains
bilingual texts and corresponding images is required to train a MNMT system with image features. However,
such a corpus is not available for low resource language pairs. To address this,
we developed both a synthetic training dataset and a manually curated development/test dataset for Hindi based
on an existing English-image parallel
corpus. We used these datasets to
build our image description translation system by adopting state-of-theart MNMT models. Our results show
that it is possible to train a MNMT
system for low-resource language pairs
through the use of synthetic data and
that such a system can benefit from image features.
This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License
Funders:
ADAPT Centre for Digital Content Technology is founded under the SFI Research Centres Programme (Grant 13/RC/2106) and is co-funded under the European Regional Development Fund.
ID Code:
23355
Deposited On:
24 May 2019 15:11 by
Thomas Murtagh
. Last Modified 04 Jan 2021 16:59