SG11201906524TA - Word vector processing method and apparatus - Google Patents

Word vector processing method and apparatus

Info

Publication number
SG11201906524TA
SG11201906524TA SG11201906524TA SG11201906524TA SG11201906524TA SG 11201906524T A SG11201906524T A SG 11201906524TA SG 11201906524T A SG11201906524T A SG 11201906524TA SG 11201906524T A SG11201906524T A SG 11201906524TA SG 11201906524T A SG11201906524T A SG 11201906524TA
Authority
SG
Singapore
Prior art keywords
word
international
vectors
words
stroke
Prior art date
Application number
SG11201906524TA
Other languages
English (en)
Inventor
Shaosheng Cao
Xiaolong Li
Original Assignee
Alibaba Group Holding Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Alibaba Group Holding Ltd filed Critical Alibaba Group Holding Ltd
Publication of SG11201906524TA publication Critical patent/SG11201906524TA/en

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/279—Recognition of textual entities
    • G06F40/284—Lexical analysis, e.g. tokenisation or collocates
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/30—Semantic analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/40—Processing or translation of natural language
    • G06F40/53—Processing of non-Latin text
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Software Systems (AREA)
  • Computing Systems (AREA)
  • Evolutionary Computation (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Molecular Biology (AREA)
  • Biomedical Technology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biophysics (AREA)
  • Medical Informatics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Machine Translation (AREA)
  • Character Discrimination (AREA)
  • Document Processing Apparatus (AREA)
SG11201906524TA 2017-01-22 2018-01-22 Word vector processing method and apparatus SG11201906524TA (en)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
CN201710045459.7A CN108345580B (zh) 2017-01-22 2017-01-22 一种词向量处理方法及装置
US15/874,725 US10430518B2 (en) 2017-01-22 2018-01-18 Word vector processing for foreign languages
PCT/US2018/014680 WO2018136870A1 (en) 2017-01-22 2018-01-22 Word vector processing method and apparatus

Publications (1)

Publication Number Publication Date
SG11201906524TA true SG11201906524TA (en) 2019-08-27

Family

ID=62906491

Family Applications (1)

Application Number Title Priority Date Filing Date
SG11201906524TA SG11201906524TA (en) 2017-01-22 2018-01-22 Word vector processing method and apparatus

Country Status (9)

Country Link
US (2) US10430518B2 (ja)
EP (1) EP3559823A1 (ja)
JP (1) JP6742653B2 (ja)
KR (1) KR102117799B1 (ja)
CN (2) CN111611798B (ja)
PH (1) PH12019501675A1 (ja)
SG (1) SG11201906524TA (ja)
TW (1) TWI685761B (ja)
WO (1) WO2018136870A1 (ja)

Families Citing this family (22)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111611798B (zh) 2017-01-22 2023-05-16 创新先进技术有限公司 一种词向量处理方法及装置
CN110119507A (zh) * 2018-02-05 2019-08-13 阿里巴巴集团控股有限公司 词向量生成方法、装置以及设备
CN109271622B (zh) * 2018-08-08 2021-05-14 山西大学 一种基于频次分布校正的低维词表征学习方法
CN110929508B (zh) * 2018-09-20 2023-05-02 阿里巴巴集团控股有限公司 词向量的生成方法、装置和系统
CN110956034B (zh) * 2018-09-21 2023-04-11 阿里巴巴集团控股有限公司 词语的获取方法及装置、商品搜索方法
CN111274793B (zh) * 2018-11-19 2023-04-28 阿里巴巴集团控股有限公司 一种文本处理方法、装置以及计算设备
CN110059155A (zh) * 2018-12-18 2019-07-26 阿里巴巴集团控股有限公司 文本相似度的计算、智能客服系统的实现方法和装置
CN109657062A (zh) * 2018-12-24 2019-04-19 万达信息股份有限公司 一种基于大数据技术的电子病历文本解析闭环方法
CN111353016B (zh) * 2018-12-24 2023-04-18 阿里巴巴集团控股有限公司 文本处理方法及装置
CN109933686B (zh) * 2019-03-18 2023-02-03 创新先进技术有限公司 歌曲标签预测方法、装置、服务器及存储介质
CN110222144B (zh) * 2019-04-17 2023-03-28 深圳壹账通智能科技有限公司 文本内容提取方法、装置、电子设备及存储介质
CN111295670A (zh) * 2019-04-25 2020-06-16 阿里巴巴集团控股有限公司 电子病历中实体的识别
CN110334196B (zh) * 2019-06-28 2023-06-27 同济大学 基于笔画和自注意力机制的神经网络中文问题生成系统
US10909317B2 (en) * 2019-07-26 2021-02-02 Advanced New Technologies Co., Ltd. Blockchain-based text similarity detection method, apparatus and electronic device
CN110619120B (zh) * 2019-08-12 2021-03-02 北京航空航天大学 语言模型的训练方法及装置
CN110765230B (zh) * 2019-09-03 2022-08-09 平安科技（深圳）有限公司 一种法律文本存储方法、装置、可读存储介质及终端设备
CN111221960A (zh) * 2019-10-28 2020-06-02 支付宝(杭州)信息技术有限公司 文本检测方法、相似度计算方法、模型训练方法及装置
EP4127969A4 (en) * 2020-03-23 2024-05-01 Sorcero Inc ONTOLOGY EXTENDED INTERFACE
JP7416665B2 (ja) 2020-06-12 2024-01-17 株式会社日立製作所 対話システム、及び対話システムの制御方法
RU2763921C1 (ru) * 2021-02-10 2022-01-11 Акционерное общество "Лаборатория Касперского" Система и способ создания эвристических правил для обнаружения мошеннических писем, относящихся к категории ВЕС-атак
CN114997162A (zh) * 2022-05-26 2022-09-02 中国工商银行股份有限公司 一种训练数据提取方法和装置
TWI827409B (zh) * 2022-12-20 2023-12-21 綺源碼有限公司 自動化組織值域映射方法、電子裝置及電腦可讀媒介

Family Cites Families (29)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5577135A (en) * 1994-03-01 1996-11-19 Apple Computer, Inc. Handwriting signal processing front-end for handwriting recognizers
CN1061449C (zh) 1997-11-26 2001-01-31 张立龙 一种四倍键盘
CN1187677C (zh) * 2002-03-18 2005-02-02 郑方 计算机整句汉字局部笔划输入方法
CN1203389C (zh) * 2002-05-24 2005-05-25 郑方 计算机整句汉字起始四笔划输入方法
US8392446B2 (en) 2007-05-31 2013-03-05 Yahoo! Inc. System and method for providing vector terms related to a search query
CN101593270B (zh) * 2008-05-29 2012-01-25 汉王科技股份有限公司 一种手绘形状识别的方法及装置
US8175389B2 (en) * 2009-03-30 2012-05-08 Synaptics Incorporated Recognizing handwritten words
US8909514B2 (en) * 2009-12-15 2014-12-09 Microsoft Corporation Unsupervised learning using global features, including for log-linear model word segmentation
KR101252397B1 (ko) 2011-06-02 2013-04-08 포항공과대학교 산학협력단 웹을 이용한 정보 검색 방법 및 이를 사용하는 음성 대화 방법
CN103164865B (zh) * 2011-12-12 2016-01-27 北京三星通信技术研究有限公司 一种对手写输入进行美化的方法和装置
CN102750556A (zh) * 2012-06-01 2012-10-24 山东大学 一种脱机手写体汉字识别方法
CN103970798B (zh) * 2013-02-04 2019-05-28 商业对象软件有限公司 数据的搜索和匹配
CN103390358B (zh) * 2013-07-03 2015-08-19 广东小天才科技有限公司 对电子设备的字符书写操作进行规范性判断的方法及装置
JPWO2015145981A1 (ja) 2014-03-28 2017-04-13 日本電気株式会社 多言語文書類似度学習装置、多言語文書類似度判定装置、多言語文書類似度学習方法、多言語文書類似度判定方法、および、多言語文書類似度学習プログラム
US9524440B2 (en) 2014-04-04 2016-12-20 Myscript System and method for superimposed handwriting recognition technology
CN103971097B (zh) * 2014-05-15 2015-05-13 武汉睿智视讯科技有限公司 一种基于多尺度笔画模型的车牌识别方法与系统
KR102396250B1 (ko) 2015-07-31 2022-05-09 삼성전자주식회사 대역 어휘 결정 장치 및 방법
US10387464B2 (en) * 2015-08-25 2019-08-20 Facebook, Inc. Predicting labels using a deep-learning model
CN105183844A (zh) * 2015-09-06 2015-12-23 国家基础地理信息中心 一种基础地理信息数据中生僻字库实现方法
US20170139899A1 (en) * 2015-11-18 2017-05-18 Le Holdings (Beijing) Co., Ltd. Keyword extraction method and electronic device
CN105488031B (zh) * 2015-12-09 2018-10-19 北京奇虎科技有限公司 一种检测相似短信的方法及装置
US9792534B2 (en) 2016-01-13 2017-10-17 Adobe Systems Incorporated Semantic natural language vector space
CN105678339B (zh) * 2016-01-15 2018-10-02 合肥工业大学 一种具有仿反馈调整机制的脱机手写体汉字认知方法
CN105740349B (zh) * 2016-01-25 2019-03-08 重庆邮电大学 一种结合Doc2vec和卷积神经网络的情感分类方法
CN105786782B (zh) * 2016-03-25 2018-10-19 北京搜狗信息服务有限公司 一种词向量的训练方法和装置
CN106095736A (zh) * 2016-06-07 2016-11-09 华东师范大学 一种领域新词抽取的方法
US9594741B1 (en) * 2016-06-12 2017-03-14 Apple Inc. Learning new words
CN106295796B (zh) * 2016-07-22 2018-12-25 浙江大学 基于深度学习的实体链接方法
CN111611798B (zh) 2017-01-22 2023-05-16 创新先进技术有限公司 一种词向量处理方法及装置

Also Published As

Publication number Publication date
TWI685761B (zh) 2020-02-21
EP3559823A1 (en) 2019-10-30
CN108345580B (zh) 2020-05-15
US10430518B2 (en) 2019-10-01
US20200134262A1 (en) 2020-04-30
TW201828105A (zh) 2018-08-01
CN111611798A (zh) 2020-09-01
US10878199B2 (en) 2020-12-29
CN111611798B (zh) 2023-05-16
CN108345580A (zh) 2018-07-31
JP6742653B2 (ja) 2020-08-19
KR102117799B1 (ko) 2020-06-02
PH12019501675A1 (en) 2020-03-02
JP2020507155A (ja) 2020-03-05
WO2018136870A1 (en) 2018-07-26
US20180210876A1 (en) 2018-07-26
KR20190107033A (ko) 2019-09-18

Similar Documents

Publication Publication Date Title
SG11201906524TA (en) Word vector processing method and apparatus
SG11201909950QA (en) Identifying entities in electronic medical records
SG11201903895XA (en) Blockchain data processing method and apparatus
SG11201903137XA (en) Three-dimensional graphical user interface for informational input in virtual reality environment
SG11201906476TA (en) Login information processing method and device
SG11201903141QA (en) Business processing method and apparatus
SG11201907679TA (en) Business verification method and apparatus
SG11201903310UA (en) Service control and user identity authentication based on virtual reality
SG11201901138XA (en) Facial recognition-based authentication
SG11201903582UA (en) Settlement method, entrance control method, and apparatus
SG11201903108UA (en) Order information determination method and apparatus
SG11201810678WA (en) Glucocorticoid receptor agonist and immunoconjugates thereof
SG11201806541RA (en) Image classification and labeling
SG11201903286RA (en) User identity authentication using virtual reality
SG11201907912YA (en) An appliance operation signal processing system and method
SG11201901550WA (en) Method and apparatus for data processing
SG11201908886TA (en) Consensus node selection method and apparatus, and server
SG11201906395PA (en) Blockchain based data processing method and device
SG11201907243UA (en) Parallel execution of transactions in a blockchain network based on smart contract whitelists
SG11201906755VA (en) Digital certificate management method, apparatus, and system
SG11201809343RA (en) Systems and methods for correcting error in a first classifier by evaluating classifier output in parallel
SG11201903452SA (en) User location determination based on augmented reality
SG11201906240RA (en) Narrowband time-division duplex frame structure for narrowband communications
SG11201900293PA (en) Method and device for displaying application information
SG11201804556YA (en) System, method, and device for generating a geographic area heat map