Human-like general language processing
This work addresses the problem of achieving human-like language processing for AI systems, presenting a novel architecture but with incremental elements in its approach.
The authors tackled the challenge of enabling machines to understand and use language flexibly by proposing a human-like general language processing (HGLP) architecture, which rapidly learned over 10 different tasks, including object recognition and sentence comprehension, by learning from easy to hard and using language as a script to control imagination.
Using language makes human beings surpass animals in wisdom. To let machines understand, learn, and use language flexibly, we propose a human-like general language processing (HGLP) architecture, which contains sensorimotor, association, and cognitive systems. The HGLP network learns from easy to hard like a child, understands word meaning by coactivating multimodal neurons, comprehends and generates sentences by real-time constructing a virtual world model, and can express the whole thinking process verbally. HGLP rapidly learned 10+ different tasks including object recognition, sentence comprehension, imagination, attention control, query, inference, motion judgement, mixed arithmetic operation, digit tracing and writing, and human-like iterative thinking process guided by language. Language in the HGLP framework is not matching nor correlation statistics, but a script that can describe and control the imagination.