期刊
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
卷 117, 期 42, 页码 25966-25974出版社
NATL ACAD SCIENCES
DOI: 10.1073/pnas.1910416117
关键词
natural language understanding; deep learning; situation models; cognitive neuroscience; artificial intelligence
资金
- European Research Council [740516]
- European Research Council (ERC) [740516] Funding Source: European Research Council (ERC)
Language is crucial for human intelligence, but what exactly is its role? We take language to be a part of a system for understanding and communicating about situations. In humans, these abilities emerge gradually from experience and depend on domain-general principles of biological neural networks: connection-based learning, distributed representation, and context-sensitive, mutual constraint satisfaction-based processing. Current artificial language processing systems rely on the same domain general principles, embodied in artificial neural networks. Indeed, recent progress in this field depends on query-based attention, which extends the ability of these systems to exploit context and has contributed to remarkable breakthroughs. Nevertheless, most current models focus exclusively on language-internal tasks, limiting their ability to perform tasks that depend on understanding situations. These systems also lack memory for the contents of prior situations outside of a fixed contextual span. We describe the organization of the brain's distributed understanding system, which includes a fast learning system that addresses the memory problem. We sketch a framework for future models of understanding drawing equally on cognitive neuroscience and artificial intelligence and exploiting query-based attention. We highlight relevant current directions and consider further developments needed to fully capture human-level language understanding in a computational system.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据