arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1911.09896cs.CL
收藏

持续适应,实现高效的机器通信

Continual adaptation for efficient machine communication

Stanford University(斯坦福大学)

Robert D. Hawkins, Minae Kwon, Dorsa Sadigh, Noah D. Goodman

摘要:

为了在新的环境中与新的伙伴交流,人类迅速形成了新的语言习惯。最近的神经语言模型能够理解和产生存在于其训练数据中的现有约定,但不能像人类那样灵活地和交互地动态地适应这些约定。我们引入了一个交互式的重复参考任务作为基准模型的适应通信,并提出了一个正规化的持续学习框架,允许一个人工代理初始化与通用语言模型更准确,更有效地与合作伙伴随着时间的推移进行通信。我们评估这个框架,通过模拟COCO和实时参考游戏实验与人类合作伙伴。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑