Chinese word vector modeling method

Chinese word vector modeling method

The invention discloses a Chinese word vector modeling method. The invention relates to a Chinese word vector modeling method, which comprises the following steps: carrying out adaptive combination onChinese strokes by utilizing a BPE algorithm, constructing a Chinese character sub-block, and finish...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: KANG QI, MA LU, XU BINCHEN
Format: Patent
Sprache:chi ; eng
Schlagworte:
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
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 KANG QI
MA LU
XU BINCHEN
description The invention discloses a Chinese word vector modeling method. The invention relates to a Chinese word vector modeling method, which comprises the following steps: carrying out adaptive combination onChinese strokes by utilizing a BPE algorithm, constructing a Chinese character sub-block, and finishing combination and representation of an internal structure of a Chinese character by utilizing anattention mechanism; carrying out information extraction on the completed Chinese character representation through a CNN structure, and carrying out fine-grained information enhancement by utilizing high-power network; considering the complexity of Chinese grammar, a bidirectional LSTM structure is constructed at a semantic extraction stage for semantic coding, and an end-to-end deep neural language model taking a Chinese character adaptive combination layer, a morphological information extraction layer, a fine-grained information enhancement layer and a semantic information extraction layer as basic components is cons
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN109992783A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN109992783A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN109992783A3</originalsourceid><addsrcrecordid>eNrjZFB2zsjMSy1OVSjPL0pRKEtNLskvUsjNT0nNycxLV8hNLcnIT-FhYE1LzClO5YXS3AyKbq4hzh66qQX58anFBYnJqXmpJfHOfoYGlpaWRuYWxo7GxKgBAOKvJog</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Chinese word vector modeling method</title><source>esp@cenet</source><creator>KANG QI ; MA LU ; XU BINCHEN</creator><creatorcontrib>KANG QI ; MA LU ; XU BINCHEN</creatorcontrib><description>The invention discloses a Chinese word vector modeling method. The invention relates to a Chinese word vector modeling method, which comprises the following steps: carrying out adaptive combination onChinese strokes by utilizing a BPE algorithm, constructing a Chinese character sub-block, and finishing combination and representation of an internal structure of a Chinese character by utilizing anattention mechanism; carrying out information extraction on the completed Chinese character representation through a CNN structure, and carrying out fine-grained information enhancement by utilizing high-power network; considering the complexity of Chinese grammar, a bidirectional LSTM structure is constructed at a semantic extraction stage for semantic coding, and an end-to-end deep neural language model taking a Chinese character adaptive combination layer, a morphological information extraction layer, a fine-grained information enhancement layer and a semantic information extraction layer as basic components is cons</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; PHYSICS</subject><creationdate>2019</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20190709&amp;DB=EPODOC&amp;CC=CN&amp;NR=109992783A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20190709&amp;DB=EPODOC&amp;CC=CN&amp;NR=109992783A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>KANG QI</creatorcontrib><creatorcontrib>MA LU</creatorcontrib><creatorcontrib>XU BINCHEN</creatorcontrib><title>Chinese word vector modeling method</title><description>The invention discloses a Chinese word vector modeling method. The invention relates to a Chinese word vector modeling method, which comprises the following steps: carrying out adaptive combination onChinese strokes by utilizing a BPE algorithm, constructing a Chinese character sub-block, and finishing combination and representation of an internal structure of a Chinese character by utilizing anattention mechanism; carrying out information extraction on the completed Chinese character representation through a CNN structure, and carrying out fine-grained information enhancement by utilizing high-power network; considering the complexity of Chinese grammar, a bidirectional LSTM structure is constructed at a semantic extraction stage for semantic coding, and an end-to-end deep neural language model taking a Chinese character adaptive combination layer, a morphological information extraction layer, a fine-grained information enhancement layer and a semantic information extraction layer as basic components is cons</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>ELECTRIC DIGITAL DATA PROCESSING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2019</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZFB2zsjMSy1OVSjPL0pRKEtNLskvUsjNT0nNycxLV8hNLcnIT-FhYE1LzClO5YXS3AyKbq4hzh66qQX58anFBYnJqXmpJfHOfoYGlpaWRuYWxo7GxKgBAOKvJog</recordid><startdate>20190709</startdate><enddate>20190709</enddate><creator>KANG QI</creator><creator>MA LU</creator><creator>XU BINCHEN</creator><scope>EVB</scope></search><sort><creationdate>20190709</creationdate><title>Chinese word vector modeling method</title><author>KANG QI ; MA LU ; XU BINCHEN</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN109992783A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2019</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>KANG QI</creatorcontrib><creatorcontrib>MA LU</creatorcontrib><creatorcontrib>XU BINCHEN</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>KANG QI</au><au>MA LU</au><au>XU BINCHEN</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Chinese word vector modeling method</title><date>2019-07-09</date><risdate>2019</risdate><abstract>The invention discloses a Chinese word vector modeling method. The invention relates to a Chinese word vector modeling method, which comprises the following steps: carrying out adaptive combination onChinese strokes by utilizing a BPE algorithm, constructing a Chinese character sub-block, and finishing combination and representation of an internal structure of a Chinese character by utilizing anattention mechanism; carrying out information extraction on the completed Chinese character representation through a CNN structure, and carrying out fine-grained information enhancement by utilizing high-power network; considering the complexity of Chinese grammar, a bidirectional LSTM structure is constructed at a semantic extraction stage for semantic coding, and an end-to-end deep neural language model taking a Chinese character adaptive combination layer, a morphological information extraction layer, a fine-grained information enhancement layer and a semantic information extraction layer as basic components is cons</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language chi ; eng
recordid cdi_epo_espacenet_CN109992783A
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
title Chinese word vector modeling method
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-02T00%3A02%3A08IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=KANG%20QI&rft.date=2019-07-09&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN109992783A%3C/epo_EVB%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