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.

翻译：我们提出并测试了一种技术，即利用预训练多语言模型进行涌现通信（Emergent Communication, EC），以改进现代无监督神经机器翻译（Unsupervised NMT）系统，尤其针对低资源语言。已有观点认为，当前NLP领域主流的纯文本语料预训练范式无法产生鲁棒的自然语言理解系统，而基于具体情境、目标导向和交互式的语言学习需求日益凸显。在我们的方法中，我们将多语言模型（mBART，Liu等人，2020）嵌入到EC图像指称游戏中，激励模型利用多语言生成完成视觉基础任务。假设是，这将使多种语言对齐到共享的任务空间。我们提出了两种EC微调变体（Steinert-Threlkeld等人，2022），其中一种变体在所有四种研究语言（包括低资源语言尼泊尔语）上的表现均优于仅使用反向翻译的基线方法。