Text abstract automatic generation method based on XLNet
The invention discloses a text abstract automatic generation method based on XLNet, and mainly solves the problems of low sentence fluency and accuracy in the text abstract automatic generation process. The method comprises the following steps: obtaining paired text and abstract data, and constructi...
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 | ZHANG HUAIYU LIU HONGYING SHANG FANHUA SHEN XIONGJIE WANG ZHONGSHU CHEN SUNHU |
| description | The invention discloses a text abstract automatic generation method based on XLNet, and mainly solves the problems of low sentence fluency and accuracy in the text abstract automatic generation process. The method comprises the following steps: obtaining paired text and abstract data, and constructing a training set; constructing a dictionary containing all common vocabularies and characters; building a backbone network by taking the pre-trained XLNet as an encoder and the Transformer-XL as a decoder; performing word segmentation on the text data in the training set and encoding the text datainto vectors to obtain network input, and finely tuning the network; and performing word segmentation and coding on the test text, and sending the test text to the trained network N to obtain an abstract result. The abstract generated by the method has good accuracy and language fluency, and has a certain practical value.
本发明公开了一种基于XLNet的文本摘要自动生成方法，主要解决文本摘要自动生成过程中，句子流畅性和准确性不高的问题。其实现过程是：获取成对的文本、摘要数据，构建训练集；构建一个包含所有常见词汇和字符的词 |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN111061861A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN111061861A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN111061861A3</originalsourceid><addsrcrecordid>eNrjZLAISa0oUUhMKi4pSkwGMkpL8nMTSzKTFdJT81KLgKz8PIXc1JKM_BSFpMTi1BQFID_Cxy-1hIeBNS0xpziVF0pzMyi6uYY4e-imFuTHpxYXJCYDDSiJd_YzNDQ0MDO0MDN0NCZGDQD9SS4F</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Text abstract automatic generation method based on XLNet</title><source>esp@cenet</source><creator>ZHANG HUAIYU ; LIU HONGYING ; SHANG FANHUA ; SHEN XIONGJIE ; WANG ZHONGSHU ; CHEN SUNHU</creator><creatorcontrib>ZHANG HUAIYU ; LIU HONGYING ; SHANG FANHUA ; SHEN XIONGJIE ; WANG ZHONGSHU ; CHEN SUNHU</creatorcontrib><description>The invention discloses a text abstract automatic generation method based on XLNet, and mainly solves the problems of low sentence fluency and accuracy in the text abstract automatic generation process. The method comprises the following steps: obtaining paired text and abstract data, and constructing a training set; constructing a dictionary containing all common vocabularies and characters; building a backbone network by taking the pre-trained XLNet as an encoder and the Transformer-XL as a decoder; performing word segmentation on the text data in the training set and encoding the text datainto vectors to obtain network input, and finely tuning the network; and performing word segmentation and coding on the test text, and sending the test text to the trained network N to obtain an abstract result. The abstract generated by the method has good accuracy and language fluency, and has a certain practical value.
本发明公开了一种基于XLNet的文本摘要自动生成方法，主要解决文本摘要自动生成过程中，句子流畅性和准确性不高的问题。其实现过程是：获取成对的文本、摘要数据，构建训练集；构建一个包含所有常见词汇和字符的词</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; HANDLING RECORD CARRIERS ; PHYSICS ; PRESENTATION OF DATA ; RECOGNITION OF DATA ; RECORD CARRIERS</subject><creationdate>2020</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=20200424&DB=EPODOC&CC=CN&NR=111061861A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25563,76318</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20200424&DB=EPODOC&CC=CN&NR=111061861A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>ZHANG HUAIYU</creatorcontrib><creatorcontrib>LIU HONGYING</creatorcontrib><creatorcontrib>SHANG FANHUA</creatorcontrib><creatorcontrib>SHEN XIONGJIE</creatorcontrib><creatorcontrib>WANG ZHONGSHU</creatorcontrib><creatorcontrib>CHEN SUNHU</creatorcontrib><title>Text abstract automatic generation method based on XLNet</title><description>The invention discloses a text abstract automatic generation method based on XLNet, and mainly solves the problems of low sentence fluency and accuracy in the text abstract automatic generation process. The method comprises the following steps: obtaining paired text and abstract data, and constructing a training set; constructing a dictionary containing all common vocabularies and characters; building a backbone network by taking the pre-trained XLNet as an encoder and the Transformer-XL as a decoder; performing word segmentation on the text data in the training set and encoding the text datainto vectors to obtain network input, and finely tuning the network; and performing word segmentation and coding on the test text, and sending the test text to the trained network N to obtain an abstract result. The abstract generated by the method has good accuracy and language fluency, and has a certain practical value.
本发明公开了一种基于XLNet的文本摘要自动生成方法，主要解决文本摘要自动生成过程中，句子流畅性和准确性不高的问题。其实现过程是：获取成对的文本、摘要数据，构建训练集；构建一个包含所有常见词汇和字符的词</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>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>2020</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZLAISa0oUUhMKi4pSkwGMkpL8nMTSzKTFdJT81KLgKz8PIXc1JKM_BSFpMTi1BQFID_Cxy-1hIeBNS0xpziVF0pzMyi6uYY4e-imFuTHpxYXJCYDDSiJd_YzNDQ0MDO0MDN0NCZGDQD9SS4F</recordid><startdate>20200424</startdate><enddate>20200424</enddate><creator>ZHANG HUAIYU</creator><creator>LIU HONGYING</creator><creator>SHANG FANHUA</creator><creator>SHEN XIONGJIE</creator><creator>WANG ZHONGSHU</creator><creator>CHEN SUNHU</creator><scope>EVB</scope></search><sort><creationdate>20200424</creationdate><title>Text abstract automatic generation method based on XLNet</title><author>ZHANG HUAIYU ; LIU HONGYING ; SHANG FANHUA ; SHEN XIONGJIE ; WANG ZHONGSHU ; CHEN SUNHU</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN111061861A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2020</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>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>ZHANG HUAIYU</creatorcontrib><creatorcontrib>LIU HONGYING</creatorcontrib><creatorcontrib>SHANG FANHUA</creatorcontrib><creatorcontrib>SHEN XIONGJIE</creatorcontrib><creatorcontrib>WANG ZHONGSHU</creatorcontrib><creatorcontrib>CHEN SUNHU</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>ZHANG HUAIYU</au><au>LIU HONGYING</au><au>SHANG FANHUA</au><au>SHEN XIONGJIE</au><au>WANG ZHONGSHU</au><au>CHEN SUNHU</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Text abstract automatic generation method based on XLNet</title><date>2020-04-24</date><risdate>2020</risdate><abstract>The invention discloses a text abstract automatic generation method based on XLNet, and mainly solves the problems of low sentence fluency and accuracy in the text abstract automatic generation process. The method comprises the following steps: obtaining paired text and abstract data, and constructing a training set; constructing a dictionary containing all common vocabularies and characters; building a backbone network by taking the pre-trained XLNet as an encoder and the Transformer-XL as a decoder; performing word segmentation on the text data in the training set and encoding the text datainto vectors to obtain network input, and finely tuning the network; and performing word segmentation and coding on the test text, and sending the test text to the trained network N to obtain an abstract result. The abstract generated by the method has good accuracy and language fluency, and has a certain practical value.
本发明公开了一种基于XLNet的文本摘要自动生成方法，主要解决文本摘要自动生成过程中，句子流畅性和准确性不高的问题。其实现过程是：获取成对的文本、摘要数据，构建训练集；构建一个包含所有常见词汇和字符的词</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN111061861A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING HANDLING RECORD CARRIERS PHYSICS PRESENTATION OF DATA RECOGNITION OF DATA RECORD CARRIERS |
| title | Text abstract automatic generation method based on XLNet |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-13T02%3A51%3A04IST&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=ZHANG%20HUAIYU&rft.date=2020-04-24&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN111061861A%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 |