Language model training method and device, electronic equipment and storage medium
The invention provides a language model training method and device, electronic equipment and a computer readable storage medium. The language model training method and device are used for training a plurality of N-element models according to a preset training corpus set; according to an expectation...
Gespeichert in:
Hauptverfasser: | , , |
---|---|
Format: | Patent |
Sprache: | chi ; 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 | CHEN YINGWEN JIAN RENXIAN LIN CHANGZHOU |
description | The invention provides a language model training method and device, electronic equipment and a computer readable storage medium. The language model training method and device are used for training a plurality of N-element models according to a preset training corpus set; according to an expectation maximization algorithm, determining an optimal weight coefficient corresponding to each N-element model when the plurality of N-element models process a preset target corpus set; and according to the optimal weight coefficient corresponding to each N-element model, performing interpolation processing on the plurality of N-element models to obtain a language model. Herein, the optimal weight coefficient of each N-element model during processing of the target corpus set is determined through an expectation maximization algorithm, and after interpolation processing is conducted on the N-element models through the optimal weight coefficients, the language model with the optimal overall processing result can be obtained |
format | Patent |
fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN113761901A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN113761901A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN113761901A3</originalsourceid><addsrcrecordid>eNqNzDsKAjEURuE0FqLu4dorGAYUSxkUC7EQ-yEkv5lAchPzcP3C4AKsTvNx5uJxU2ybsqAQDTzVrBw7thRQx2hIsSGDj9PYEDx0zZGdJrybSwFcJ1BqzNMCxrWwFLOX8gWrXxdifTk_--sWKQ4oSWkw6tDfpewOe3ncyVP3j_kCDCo3_Q</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Language model training method and device, electronic equipment and storage medium</title><source>esp@cenet</source><creator>CHEN YINGWEN ; JIAN RENXIAN ; LIN CHANGZHOU</creator><creatorcontrib>CHEN YINGWEN ; JIAN RENXIAN ; LIN CHANGZHOU</creatorcontrib><description>The invention provides a language model training method and device, electronic equipment and a computer readable storage medium. The language model training method and device are used for training a plurality of N-element models according to a preset training corpus set; according to an expectation maximization algorithm, determining an optimal weight coefficient corresponding to each N-element model when the plurality of N-element models process a preset target corpus set; and according to the optimal weight coefficient corresponding to each N-element model, performing interpolation processing on the plurality of N-element models to obtain a language model. Herein, the optimal weight coefficient of each N-element model during processing of the target corpus set is determined through an expectation maximization algorithm, and after interpolation processing is conducted on the N-element models through the optimal weight coefficients, the language model with the optimal overall processing result can be obtained</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; HANDLING RECORD CARRIERS ; PHYSICS ; PRESENTATION OF DATA ; RECOGNITION OF DATA ; RECORD CARRIERS</subject><creationdate>2021</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&date=20211207&DB=EPODOC&CC=CN&NR=113761901A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20211207&DB=EPODOC&CC=CN&NR=113761901A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>CHEN YINGWEN</creatorcontrib><creatorcontrib>JIAN RENXIAN</creatorcontrib><creatorcontrib>LIN CHANGZHOU</creatorcontrib><title>Language model training method and device, electronic equipment and storage medium</title><description>The invention provides a language model training method and device, electronic equipment and a computer readable storage medium. The language model training method and device are used for training a plurality of N-element models according to a preset training corpus set; according to an expectation maximization algorithm, determining an optimal weight coefficient corresponding to each N-element model when the plurality of N-element models process a preset target corpus set; and according to the optimal weight coefficient corresponding to each N-element model, performing interpolation processing on the plurality of N-element models to obtain a language model. Herein, the optimal weight coefficient of each N-element model during processing of the target corpus set is determined through an expectation maximization algorithm, and after interpolation processing is conducted on the N-element models through the optimal weight coefficients, the language model with the optimal overall processing result can be obtained</description><subject>CALCULATING</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>ELECTRIC DIGITAL DATA PROCESSING</subject><subject>HANDLING RECORD CARRIERS</subject><subject>PHYSICS</subject><subject>PRESENTATION OF DATA</subject><subject>RECOGNITION OF DATA</subject><subject>RECORD CARRIERS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2021</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNzDsKAjEURuE0FqLu4dorGAYUSxkUC7EQ-yEkv5lAchPzcP3C4AKsTvNx5uJxU2ybsqAQDTzVrBw7thRQx2hIsSGDj9PYEDx0zZGdJrybSwFcJ1BqzNMCxrWwFLOX8gWrXxdifTk_--sWKQ4oSWkw6tDfpewOe3ncyVP3j_kCDCo3_Q</recordid><startdate>20211207</startdate><enddate>20211207</enddate><creator>CHEN YINGWEN</creator><creator>JIAN RENXIAN</creator><creator>LIN CHANGZHOU</creator><scope>EVB</scope></search><sort><creationdate>20211207</creationdate><title>Language model training method and device, electronic equipment and storage medium</title><author>CHEN YINGWEN ; JIAN RENXIAN ; LIN CHANGZHOU</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN113761901A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2021</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>HANDLING RECORD CARRIERS</topic><topic>PHYSICS</topic><topic>PRESENTATION OF DATA</topic><topic>RECOGNITION OF DATA</topic><topic>RECORD CARRIERS</topic><toplevel>online_resources</toplevel><creatorcontrib>CHEN YINGWEN</creatorcontrib><creatorcontrib>JIAN RENXIAN</creatorcontrib><creatorcontrib>LIN CHANGZHOU</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>CHEN YINGWEN</au><au>JIAN RENXIAN</au><au>LIN CHANGZHOU</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Language model training method and device, electronic equipment and storage medium</title><date>2021-12-07</date><risdate>2021</risdate><abstract>The invention provides a language model training method and device, electronic equipment and a computer readable storage medium. The language model training method and device are used for training a plurality of N-element models according to a preset training corpus set; according to an expectation maximization algorithm, determining an optimal weight coefficient corresponding to each N-element model when the plurality of N-element models process a preset target corpus set; and according to the optimal weight coefficient corresponding to each N-element model, performing interpolation processing on the plurality of N-element models to obtain a language model. Herein, the optimal weight coefficient of each N-element model during processing of the target corpus set is determined through an expectation maximization algorithm, and after interpolation processing is conducted on the N-element models through the optimal weight coefficients, the language model with the optimal overall processing result can be obtained</abstract><oa>free_for_read</oa></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | |
ispartof | |
issn | |
language | chi ; eng |
recordid | cdi_epo_espacenet_CN113761901A |
source | esp@cenet |
subjects | CALCULATING COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING HANDLING RECORD CARRIERS PHYSICS PRESENTATION OF DATA RECOGNITION OF DATA RECORD CARRIERS |
title | Language model training method and device, electronic equipment and storage medium |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T14%3A24%3A24IST&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=CHEN%20YINGWEN&rft.date=2021-12-07&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN113761901A%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 |