Human-like general language processing

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.

[1]  D C Van Essen,et al.  Information processing in the primate visual system: an integrated systems perspective. , 1992, Science.

[2]  P. Hagoort.  On Broca, brain, and binding: a new framework , 2005, Trends in Cognitive Sciences.

[3]  Angela D. Friederici,et al.  The ontogeny of the cortical language network , 2016, Nature Reviews Neuroscience.

[4]  Takashi Kitamura,et al.  The role of engram cells in the systems consolidation of memory , 2018, Nature Reviews Neuroscience.

[5]  A. Friederici.  The cortical language circuit: from auditory perception to sentence comprehension , 2012, Trends in Cognitive Sciences.

[6]  Peter Dayan,et al.  A Neural Substrate of Prediction and Reward , 1997, Science.

[7]  Richard S. J. Frackowiak,et al.  A voxel‐based morphometry study of semantic dementia: Relationship between temporal lobe atrophy and semantic memory , 2000, Annals of neurology.

[8]  M. L. Lambon Ralph,et al.  The Neural Organization of Semantic Control: TMS Evidence for a Distributed Network in Left Inferior Frontal and Posterior Middle Temporal Gyrus , 2010, Cerebral cortex.

[9]  M. D’Esposito.  Working memory. , 2008, Handbook of clinical neurology.

[10]  D. Poeppel,et al.  The cortical organization of speech processing , 2007, Nature Reviews Neuroscience.

[11]  Emeran A. Mayer,et al.  Gut feelings: the emerging biology of gut–brain communication , 2011, Nature Reviews Neuroscience.

[12]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[13]  T. Rogers,et al.  The neural and computational bases of semantic cognition , 2016, Nature Reviews Neuroscience.

[14]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[15]  Susumu Tonegawa,et al.  Memory engrams: Recalling the past and imagining the future , 2020, Science.

[16]  A. Nieder.  The neuronal code for number , 2016, Nature Reviews Neuroscience.

[17]  Zheng Xie,et al.  AlphaGomoku: An AlphaGo-based Gomoku Artificial Intelligence using Curriculum Learning , 2018, ArXiv.

[18]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[19]  B. McNaughton,et al.  Independent Codes for Spatial and Episodic Memory in Hippocampal Neuronal Ensembles , 2005, Science.

[20]  Vinod Menon,et al.  Prefrontal cortex involvement in processing incorrect arithmetic equations: Evidence from event‐related fMRI , 2002, Human brain mapping.

[21]  H. Funkenstein,et al.  Broca aphasia , 1978, Neurology.

[22]  Cordelia Schmid,et al.  VideoBERT: A Joint Model for Video and Language Representation Learning , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[23]  K. Sakai.  Task set and prefrontal cortex. , 2008, Annual review of neuroscience.

[24]  Zhoujun Li,et al.  Sequential Match Network: A New Architecture for Multi-turn Response Selection in Retrieval-based Chatbots , 2016, ArXiv.

[25]  S. Corkin.  What's new with the amnesic patient H.M.? , 2002, Nature Reviews Neuroscience.

[26]  James J. DiCarlo,et al.  How Does the Brain Solve Visual Object Recognition? , 2012, Neuron.

[27]  E. Miller,et al.  An integrative theory of prefrontal cortex function. , 2001, Annual review of neuroscience.

[28]  L. Shapiro,et al.  Verb-Argument Structure Processing in Complex Sentences in Broca′s and Wernicke′s Aphasia , 1993, Brain and Language.

[29]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[30]  E. Murray,et al.  Specializations for reward-guided decision-making in the primate ventral prefrontal cortex , 2018, Nature Reviews Neuroscience.

[31]  L. Fadiga,et al.  Active perception: sensorimotor circuits as a cortical basis for language , 2010, Nature Reviews Neuroscience.

[32]  Shane Legg,et al.  Human-level control through deep reinforcement learning , 2015, Nature.

[33]  H. Yin,et al.  The role of the basal ganglia in habit formation , 2006, Nature Reviews Neuroscience.

[34]  Noam Chomsky,et al.  Language, mind and brain , 2017, Nature Human Behaviour.

[35]  P. Goldman-Rakic.  Cellular basis of working memory , 1995, Neuron.

[36]  Ying Chen,et al.  Multi-Turn Response Selection for Chatbots with Deep Attention Matching Network , 2018, ACL.