Learning to translate by learning to communicate
C.M. Downey, Xuhui Zhou, Leo Z. Liu, Shane Steinert-Threlkeld

TL;DR
This paper introduces a novel approach combining emergent communication with a pre-trained multilingual model to enhance unsupervised neural machine translation, especially benefiting low-resource languages through vision-grounded tasks.
Contribution
It proposes a new EC fine-tuning method that aligns multiple languages in a shared task space, improving translation quality over traditional backtranslation methods.
Findings
EC fine-tuning outperforms backtranslation baseline in four languages
Method improves translation for low-resource language Nepali
Multilingual shared task space enhances language alignment
Abstract
We formulate and test a technique to use Emergent Communication (EC) with a pre-trained multilingual model to improve on modern Unsupervised NMT systems, especially for low-resource languages. It has been argued that the current dominant paradigm in NLP of pre-training on text-only corpora will not yield robust natural language understanding systems, and the need for grounded, goal-oriented, and interactive language learning has been high lighted. In our approach, we embed a multilingual model (mBART, Liu et al., 2020) into an EC image-reference game, in which the model is incentivized to use multilingual generations to accomplish a vision-grounded task. The hypothesis is that this will align multiple languages to a shared task space. We present two variants of EC Fine-Tuning (Steinert-Threlkeld et al., 2022), one of which outperforms a backtranslation-only baseline in all four…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsLanguage and cultural evolution · Natural Language Processing Techniques · Topic Modeling
MethodsTest · ALIGN
