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 ha...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Qi, Feng, Jiang, Guanjun
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Qi, Feng
Jiang, Guanjun
description 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.
doi_str_mv 10.48550/arxiv.2005.09175
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2005_09175</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2005_09175</sourcerecordid><originalsourceid>FETCH-LOGICAL-a675-6d6810a8e8ca3431139086a9d0b45fa4e9844b329455ae66bf56e17ffa56085f3</originalsourceid><addsrcrecordid>eNotzrsKwjAUgOEsDqI-gJOd3FpPmpw0GUW8geDiXk71pBTbWlIUfXvxMv3bzyfEVEKiLSIsKDyrR5ICYAJOZjgU8929oTauqytHJbccqI5qass7lRx14Xbmvq_aciwGnuqeJ_-OxGmzPq128eG43a-Wh5hMhrG5GCuBLNszKa2kVA6sIXeBQqMnzc5qXajUaURiYwqPhmXmPaEBi16NxOy3_ULzLlQNhVf-AedfsHoDLcA5tg</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Human-like general language processing</title><source>arXiv.org</source><creator>Qi, Feng ; Jiang, Guanjun</creator><creatorcontrib>Qi, Feng ; Jiang, Guanjun</creatorcontrib><description>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.</description><identifier>DOI: 10.48550/arxiv.2005.09175</identifier><language>eng</language><subject>Computer Science - Artificial Intelligence ; Computer Science - Learning ; Quantitative Biology - Neurons and Cognition</subject><creationdate>2020-05</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,781,886</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2005.09175$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2005.09175$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Qi, Feng</creatorcontrib><creatorcontrib>Jiang, Guanjun</creatorcontrib><title>Human-like general language processing</title><description>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.</description><subject>Computer Science - Artificial Intelligence</subject><subject>Computer Science - Learning</subject><subject>Quantitative Biology - Neurons and Cognition</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotzrsKwjAUgOEsDqI-gJOd3FpPmpw0GUW8geDiXk71pBTbWlIUfXvxMv3bzyfEVEKiLSIsKDyrR5ICYAJOZjgU8929oTauqytHJbccqI5qass7lRx14Xbmvq_aciwGnuqeJ_-OxGmzPq128eG43a-Wh5hMhrG5GCuBLNszKa2kVA6sIXeBQqMnzc5qXajUaURiYwqPhmXmPaEBi16NxOy3_ULzLlQNhVf-AedfsHoDLcA5tg</recordid><startdate>20200518</startdate><enddate>20200518</enddate><creator>Qi, Feng</creator><creator>Jiang, Guanjun</creator><scope>AKY</scope><scope>ALC</scope><scope>GOX</scope></search><sort><creationdate>20200518</creationdate><title>Human-like general language processing</title><author>Qi, Feng ; Jiang, Guanjun</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a675-6d6810a8e8ca3431139086a9d0b45fa4e9844b329455ae66bf56e17ffa56085f3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Computer Science - Artificial Intelligence</topic><topic>Computer Science - Learning</topic><topic>Quantitative Biology - Neurons and Cognition</topic><toplevel>online_resources</toplevel><creatorcontrib>Qi, Feng</creatorcontrib><creatorcontrib>Jiang, Guanjun</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv Quantitative Biology</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Qi, Feng</au><au>Jiang, Guanjun</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Human-like general language processing</atitle><date>2020-05-18</date><risdate>2020</risdate><abstract>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.</abstract><doi>10.48550/arxiv.2005.09175</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2005.09175
ispartof
issn
language eng
recordid cdi_arxiv_primary_2005_09175
source arXiv.org
subjects Computer Science - Artificial Intelligence
Computer Science - Learning
Quantitative Biology - Neurons and Cognition
title Human-like general language processing
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-17T21%3A21%3A15IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Human-like%20general%20language%20processing&rft.au=Qi,%20Feng&rft.date=2020-05-18&rft_id=info:doi/10.48550/arxiv.2005.09175&rft_dat=%3Carxiv_GOX%3E2005_09175%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true