To communicate with new partners in new contexts, humans rapidly form new linguistic conventions. Recent neural language models are able to comprehend and produce the existing conventions present in their training data, but are not able to flexibly and interactively adapt those conventions on the fly as humans do. We introduce an interactive repeated reference task as a benchmark for models of adaptation in communication and propose a regularized continual learning framework that allows an artificial agent initialized with a generic language model to more accurately and efficiently communicate with a partner over time. We evaluate this framework through simulations on COCO and in real-time reference game experiments with human partners.

翻译：为了在新的环境下与新的伙伴进行交流,人类迅速形成了新的语言公约; 最近的神经语言模型能够理解和产生其培训数据中的现有公约,但不能像人类那样灵活和互动地在飞行上适应这些公约; 我们引入了互动性反复参照任务,作为通信适应模式的基准,并提出一个正规化的持续学习框架,允许一个人工代剂,以通用语言模型为初始,在一段时间内与伙伴进行更准确和高效的交流; 我们通过COCOCO模拟以及与人类伙伴进行实时参考游戏实验,对该框架进行评估。