CN116724306A - 用于自然语言处理器的多特征平衡 - Google Patents

用于自然语言处理器的多特征平衡 Download PDF

Info

Publication number
CN116724306A
CN116724306A CN202280011027.3A CN202280011027A CN116724306A CN 116724306 A CN116724306 A CN 116724306A CN 202280011027 A CN202280011027 A CN 202280011027A CN 116724306 A CN116724306 A CN 116724306A
Authority
CN
China
Prior art keywords
natural language
features
dataset
contextual
machine learning
Prior art date
Legal status (The legal status 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 status listed.)
Pending
Application number
CN202280011027.3A
Other languages
English (en)
Chinese (zh)
Inventor
T·L·杜翁
V·比什诺伊
M·E·约翰逊
E·L·贾拉勒丁
T·Q·范
C·D·V·黄
P·扎雷穆迪
S·P·K·加德
A·D·卡努加
李子恺
Y·吴
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Oracle International Corp
Original Assignee
Oracle International Corp
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 Oracle International Corp filed Critical Oracle International Corp
Publication of CN116724306A publication Critical patent/CN116724306A/zh
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/279—Recognition of textual entities
    • G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/10—Text processing
    • G06F40/166—Editing, e.g. inserting or deleting
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/279—Recognition of textual entities
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/279—Recognition of textual entities
    • G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
    • G06F40/295—Named entity recognition
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/0464—Convolutional networks [CNN, ConvNet]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06N3/09—Supervised learning
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
    • H04L51/02—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/205—Parsing
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/263—Language identification
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Software Systems (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Evolutionary Computation (AREA)
  • Data Mining & Analysis (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Molecular Biology (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Machine Translation (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
CN202280011027.3A 2021-01-20 2022-01-20 用于自然语言处理器的多特征平衡 Pending CN116724306A (zh)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
US202163139695P 2021-01-20 2021-01-20
US63/139,695 2021-01-20
PCT/US2022/013060 WO2022159544A1 (en) 2021-01-20 2022-01-20 Multi-feature balancing for natural language processors

Publications (1)

Publication Number Publication Date
CN116724306A true CN116724306A (zh) 2023-09-08

Family

ID=82406292

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202280011027.3A Pending CN116724306A (zh) 2021-01-20 2022-01-20 用于自然语言处理器的多特征平衡

Country Status (5)

Country Link
US (2) US12153885B2 (https=)
EP (1) EP4281880A4 (https=)
JP (2) JP7771196B2 (https=)
CN (1) CN116724306A (https=)
WO (1) WO2022159544A1 (https=)

Families Citing this family (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2022047214A2 (en) * 2020-08-27 2022-03-03 Carnelian Laboratories Llc Digital assistant control of applications
US12175968B1 (en) * 2021-03-26 2024-12-24 Amazon Technologies, Inc. Skill selection for responding to natural language inputs
JP2024517656A (ja) * 2021-04-28 2024-04-23 コーニンクレッカ フィリップス エヌ ヴェ 医用イメージングシステム用のチャットボット
US11729121B2 (en) * 2021-04-29 2023-08-15 Bank Of America Corporation Executing a network of chatbots using a combination approach
US11914644B2 (en) * 2021-10-11 2024-02-27 Microsoft Technology Licensing, Llc Suggested queries for transcript search
US20230401385A1 (en) * 2022-06-13 2023-12-14 Oracle International Corporation Hierarchical named entity recognition with multi-task setup
US12511140B2 (en) * 2022-11-28 2025-12-30 Sap Se Performance controller for machine learning based digital assistant
US12608562B2 (en) * 2023-09-21 2026-04-21 Google Llc Providing personalized prompts to users based on documents in cloud storage
TWI897448B (zh) * 2024-05-29 2025-09-11 神通資訊科技股份有限公司 提供多模態人機交互導引的多媒體事務機之系統及其方法
US12314305B1 (en) * 2024-11-24 2025-05-27 Signet Health Corporation System and method for generating an updated terminal node projection

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109783337A (zh) * 2018-12-19 2019-05-21 北京达佳互联信息技术有限公司 模型服务方法、系统、装置和计算机可读存储介质
CN109858018A (zh) * 2018-12-25 2019-06-07 中国科学院信息工程研究所 一种面向威胁情报的实体识别方法及系统
CN109918648A (zh) * 2019-01-31 2019-06-21 内蒙古工业大学 一种基于动态滑动窗口特征评分的谣言深度检测方法
CN109918503A (zh) * 2019-01-29 2019-06-21 华南理工大学 基于动态窗口自注意力机制提取语义特征的槽填充方法
CN111949770A (zh) * 2020-08-24 2020-11-17 国网浙江省电力有限公司信息通信分公司 一种文档分类方法及装置

Family Cites Families (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160293167A1 (en) * 2013-10-10 2016-10-06 Google Inc. Speaker recognition using neural networks
US9715660B2 (en) * 2013-11-04 2017-07-25 Google Inc. Transfer learning for deep neural network based hotword detection
US9672814B2 (en) * 2015-05-08 2017-06-06 International Business Machines Corporation Semi-supervised learning of word embeddings
US10373612B2 (en) 2016-03-21 2019-08-06 Amazon Technologies, Inc. Anchored speech detection and speech recognition
US11694072B2 (en) * 2017-05-19 2023-07-04 Nvidia Corporation Machine learning technique for automatic modeling of multiple-valued outputs
US10453454B2 (en) * 2017-10-26 2019-10-22 Hitachi, Ltd. Dialog system with self-learning natural language understanding
US10579733B2 (en) * 2018-05-10 2020-03-03 Google Llc Identifying codemixed text
US11625620B2 (en) 2018-08-16 2023-04-11 Oracle International Corporation Techniques for building a knowledge graph in limited knowledge domains
US10861439B2 (en) 2018-10-22 2020-12-08 Ca, Inc. Machine learning model for identifying offensive, computer-generated natural-language text or speech
WO2020219203A1 (en) 2019-04-26 2020-10-29 Oracle International Corporation Insights into performance of a bot system
US11481388B2 (en) * 2019-12-18 2022-10-25 Roy Fugère SIANEZ Methods and apparatus for using machine learning to securely and efficiently retrieve and present search results
US11250839B2 (en) * 2020-04-16 2022-02-15 Microsoft Technology Licensing, Llc Natural language processing models for conversational computing
US11450310B2 (en) * 2020-08-10 2022-09-20 Adobe Inc. Spoken language understanding
US11893354B2 (en) * 2021-03-25 2024-02-06 Cognizant Technology Solutions India Pvt. Ltd. System and method for improving chatbot training dataset

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109783337A (zh) * 2018-12-19 2019-05-21 北京达佳互联信息技术有限公司 模型服务方法、系统、装置和计算机可读存储介质
CN109858018A (zh) * 2018-12-25 2019-06-07 中国科学院信息工程研究所 一种面向威胁情报的实体识别方法及系统
CN109918503A (zh) * 2019-01-29 2019-06-21 华南理工大学 基于动态窗口自注意力机制提取语义特征的槽填充方法
CN109918648A (zh) * 2019-01-31 2019-06-21 内蒙古工业大学 一种基于动态滑动窗口特征评分的谣言深度检测方法
CN111949770A (zh) * 2020-08-24 2020-11-17 国网浙江省电力有限公司信息通信分公司 一种文档分类方法及装置

Also Published As

Publication number Publication date
US12153885B2 (en) 2024-11-26
JP7771196B2 (ja) 2025-11-17
US20220229991A1 (en) 2022-07-21
JP2024503519A (ja) 2024-01-25
JP2026027326A (ja) 2026-02-18
EP4281880A4 (en) 2024-12-18
EP4281880A1 (en) 2023-11-29
US20240419910A1 (en) 2024-12-19
WO2022159544A1 (en) 2022-07-28

Similar Documents

Publication Publication Date Title
CN116724305B (zh) 上下文标签与命名实体识别模型的集成
CN114424185B (zh) 用于自然语言处理的停用词数据扩充
CN115398437B (zh) 改进的域外(ood)检测技术
CN116802629B (zh) 用于自然语言处理的多因素建模
CN115398436B (zh) 用于自然语言处理的噪声数据扩充
CN116583837B (zh) 用于自然语言处理的基于距离的logit值
CN116547676B (zh) 用于自然语言处理的增强型logit
US12153885B2 (en) Multi-feature balancing for natural language processors
CN116635862A (zh) 用于自然语言处理的域外数据扩充
CN112487157A (zh) 用于聊天机器人的基于模板的意图分类
CN118140230A (zh) 对经预训练的语言模型的单个转换器层的多头网络进行微调
CN118265981B (zh) 用于为预训练的语言模型处置长文本的系统和技术
CN116615727A (zh) 用于自然语言处理的关键词数据扩充工具
CN118202344A (zh) 用于从文档中提取嵌入式数据的深度学习技术
JP2024543062A (ja) 自然言語処理のパスのドロップアウト
CN118215920A (zh) 用于使用散列嵌入进行语言检测的宽深网络
CN119183573A (zh) 实体感知数据增强技术
CN118251668A (zh) 用于从数据中提取问题答案对的基于规则的技术
CN116235164B (zh) 聊天机器人的范围外自动转变
CN120092248A (zh) 基于目标的超参数调谐中的目标函数优化
CN119768794A (zh) 自适应训练数据扩充以促进命名实体识别模型的训练
CN116235164A (zh) 聊天机器人的范围外自动转变
WO2023091436A1 (en) System and techniques for handling long text for pre-trained language models

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination