Learning to translate by learning to communicate
This addresses the problem of enhancing translation quality for low-resource languages in NLP, though it is incremental as it builds on existing emergent communication and pre-trained model techniques.
The paper tackled improving unsupervised neural machine translation for low-resource languages by using emergent communication with a pre-trained multilingual model, resulting in a variant that outperformed a backtranslation-only baseline across four languages, including Nepali.
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 languages investigated, including the low-resource language Nepali.