CN116583837B - 用于自然语言处理的基于距离的logit值 - Google Patents

用于自然语言处理的基于距离的logit值

Info

Publication number
CN116583837B
CN116583837B CN202180080516.XA CN202180080516A CN116583837B CN 116583837 B CN116583837 B CN 116583837B CN 202180080516 A CN202180080516 A CN 202180080516A CN 116583837 B CN116583837 B CN 116583837B
Authority
CN
China
Prior art keywords
classification
probability
training
utterance
loss
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.)
Active
Application number
CN202180080516.XA
Other languages
English (en)
Chinese (zh)
Other versions
CN116583837A (zh
Inventor
徐莹
P·扎雷穆迪
T·T·乌
C·D·V·黄
V·布利诺夫
洪宇衡
Y·D·T·S·达摩西里
V·比什诺伊
E·L·贾拉勒丁
M·帕雷克
T·L·杜翁
M·E·约翰逊
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 CN116583837A publication Critical patent/CN116583837A/zh
Application granted granted Critical
Publication of CN116583837B publication Critical patent/CN116583837B/zh
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/30—Semantic analysis
    • G06F40/35—Discourse or dialogue representation
    • 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
    • G06N3/004—Artificial life, i.e. computing arrangements simulating life
    • G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
    • 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
    • G06N3/048—Activation functions
    • 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
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • 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
    • G06F40/253—Grammatical analysis; Style critique

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • General Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Data Mining & Analysis (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Biomedical Technology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biophysics (AREA)
  • Molecular Biology (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Machine Translation (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
CN202180080516.XA 2020-11-30 2021-11-30 用于自然语言处理的基于距离的logit值 Active CN116583837B (zh)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
US202063119459P 2020-11-30 2020-11-30
US63/119,459 2020-11-30
PCT/US2021/061081 WO2022115736A1 (en) 2020-11-30 2021-11-30 Distance-based logit values for natural language processing

Publications (2)

Publication Number Publication Date
CN116583837A CN116583837A (zh) 2023-08-11
CN116583837B true CN116583837B (zh) 2025-12-16

Family

ID=79171079

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202180080516.XA Active CN116583837B (zh) 2020-11-30 2021-11-30 用于自然语言处理的基于距离的logit值

Country Status (5)

Country Link
US (3) US12019994B2 (https=)
EP (1) EP4252143A1 (https=)
JP (1) JP7843760B2 (https=)
CN (1) CN116583837B (https=)
WO (1) WO2022115736A1 (https=)

Families Citing this family (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB2569335B (en) * 2017-12-13 2022-07-27 Sage Global Services Ltd Chatbot system
US12431149B2 (en) * 2020-03-24 2025-09-30 Evident Canada, Inc. Compressive sensing for full matrix capture
US11550605B2 (en) * 2020-06-30 2023-01-10 Kasisto, Inc. Building and managing cohesive interaction for virtual assistants
EP4268118A1 (en) * 2020-12-22 2023-11-01 Liveperson, Inc. Conversational bot evaluation and reinforcement using meaningful automated connection scores
US12340792B2 (en) * 2021-05-17 2025-06-24 Salesforce, Inc. Systems and methods for few-shot intent classifier models
EP4363965A1 (en) * 2021-08-06 2024-05-08 Siemens Aktiengesellschaft Source code synthesis for domain specific languages from natural language text
US12019984B2 (en) * 2021-09-20 2024-06-25 Salesforce, Inc. Multi-lingual intent model with out-of-domain detection
US20230169362A1 (en) * 2021-11-30 2023-06-01 Sap France Shared network learning for machine learning enabled text classification
US12204857B2 (en) * 2022-06-24 2025-01-21 Salesforce, Inc. Systems and methods for text classification using label modular prompts
US12170097B2 (en) * 2022-08-17 2024-12-17 Caterpillar Inc. Detection of audio communication signals present in a high noise environment
US12141536B1 (en) * 2023-03-16 2024-11-12 Amazon Technologies, Inc. Chatbot utterance routing in a provider network
US20250245445A1 (en) * 2024-01-31 2025-07-31 Genpact Usa, Inc. Enhanced domain-specific language learning models
US20260037359A1 (en) * 2024-08-05 2026-02-05 Interdigital Patent Holdings, Inc. Methods for Error Cause Determination for Two-Sided Models Independently Trained by Different Vendors
US12367342B1 (en) * 2025-01-15 2025-07-22 Conversational AI Ltd Automated analysis of computerized conversational agent conversational data

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105393252A (zh) * 2013-04-18 2016-03-09 数字标记公司 生理数据采集和分析
CN110458249A (zh) * 2019-10-10 2019-11-15 点内（上海）生物科技有限公司 一种基于深度学习与概率影像组学的病灶分类系统

Family Cites Families (30)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9575963B2 (en) * 2012-04-20 2017-02-21 Maluuba Inc. Conversational agent
US9547471B2 (en) * 2014-07-03 2017-01-17 Microsoft Technology Licensing, Llc Generating computer responses to social conversational inputs
US20160253597A1 (en) * 2015-02-27 2016-09-01 Xerox Corporation Content-aware domain adaptation for cross-domain classification
WO2018029679A1 (en) * 2016-08-07 2018-02-15 Hadasit Medical Research Services And Development Ltd. Methods and system for assessing a cognitive function
US20200342003A1 (en) * 2016-09-27 2020-10-29 Opro Co., Ltd. Synchronization program and connection program for cloud service
US10796217B2 (en) * 2016-11-30 2020-10-06 Microsoft Technology Licensing, Llc Systems and methods for performing automated interviews
US10685293B1 (en) * 2017-01-20 2020-06-16 Cybraics, Inc. Methods and systems for analyzing cybersecurity threats
US10530795B2 (en) * 2017-03-17 2020-01-07 Target Brands, Inc. Word embeddings for anomaly classification from event logs
US11373632B2 (en) * 2017-05-10 2022-06-28 Oracle International Corporation Using communicative discourse trees to create a virtual persuasive dialogue
US10817670B2 (en) 2017-05-10 2020-10-27 Oracle International Corporation Enabling chatbots by validating argumentation
EP3711031A4 (en) * 2017-11-17 2021-01-13 Facebook, Inc. ANALYSIS OF SPATIAL DISTRIBUTED DATA BASED ON DISTRIBUTED NEURAL FOLDING NETWORKS WITH SUBCOLLECTOR
US11200506B2 (en) * 2017-12-15 2021-12-14 Microsoft Technology Licensing, Llc Chatbot integrating derived user intent
US20190205939A1 (en) * 2017-12-31 2019-07-04 OneMarket Network LLC Using Machine Learned Visitor Intent Propensity to Greet and Guide a Visitor at a Physical Venue
US12387131B2 (en) * 2018-05-31 2025-08-12 Microsoft Technology Licensing, Llc Enhanced pipeline for the generation, validation, and deployment of machine-based predictive models
US11423330B2 (en) * 2018-07-16 2022-08-23 Invoca, Inc. Performance score determiner for binary signal classifiers
US11625620B2 (en) 2018-08-16 2023-04-11 Oracle International Corporation Techniques for building a knowledge graph in limited knowledge domains
US11061955B2 (en) * 2018-09-21 2021-07-13 Salesforce.Com, Inc. Intent classification system
US11257496B2 (en) * 2018-09-26 2022-02-22 [24]7.ai, Inc. Method and apparatus for facilitating persona-based agent interactions with online visitors
US11194973B1 (en) * 2018-11-12 2021-12-07 Amazon Technologies, Inc. Dialog response generation
US11574144B2 (en) 2019-01-07 2023-02-07 Microsoft Technology Licensing, Llc Performance of a computer-implemented model that acts as a multi-class classifier
KR102204740B1 (ko) * 2019-02-28 2021-01-19 네이버 주식회사 대화 시스템에서의 의도 불분명 질의를 처리하는 방법 및 시스템
CA3074675A1 (en) * 2019-03-04 2020-09-04 Royal Bank Of Canada System and method for machine learning with long-range dependency
US11978452B2 (en) 2019-04-26 2024-05-07 Oracle International Corportion Handling explicit invocation of chatbots
US11657797B2 (en) 2019-04-26 2023-05-23 Oracle International Corporation Routing for chatbots
US11206229B2 (en) 2019-04-26 2021-12-21 Oracle International Corporation Directed acyclic graph based framework for training models
US11775770B2 (en) * 2019-05-23 2023-10-03 Capital One Services, Llc Adversarial bootstrapping for multi-turn dialogue model training
CN110738239A (zh) * 2019-09-20 2020-01-31 浙江大学 一种基于鼠标交互序列区域行为联合建模的搜索引擎用户满意度评估方法
US10825449B1 (en) * 2019-09-27 2020-11-03 CrowdAround Inc. Systems and methods for analyzing a characteristic of a communication using disjoint classification models for parsing and evaluation of the communication
CN111598830A (zh) * 2020-02-18 2020-08-28 天津大学 一种基于无监督学习的皮肤癌疾病检测方法
JP7080276B2 (ja) * 2020-05-12 2022-06-03 ヤフー株式会社 分類システム、分類方法、およびプログラム

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105393252A (zh) * 2013-04-18 2016-03-09 数字标记公司 生理数据采集和分析
CN110458249A (zh) * 2019-10-10 2019-11-15 点内（上海）生物科技有限公司 一种基于深度学习与概率影像组学的病灶分类系统

Also Published As

Publication number Publication date
US20220171947A1 (en) 2022-06-02
CN116583837A (zh) 2023-08-11
JP7843760B2 (ja) 2026-04-14
US20240126999A1 (en) 2024-04-18
US12019994B2 (en) 2024-06-25
US12210842B2 (en) 2025-01-28
WO2022115736A1 (en) 2022-06-02
JP2023551861A (ja) 2023-12-13
EP4252143A1 (en) 2023-10-04
US20250117591A1 (en) 2025-04-10

Similar Documents

Publication Publication Date Title
CN115398437B (zh) 改进的域外(ood)检测技术
US12361219B2 (en) Context tag integration with named entity recognition models
CN116583837B (zh) 用于自然语言处理的基于距离的logit值
CN114424185B (zh) 用于自然语言处理的停用词数据扩充
US12099816B2 (en) Multi-factor modelling for natural language processing
CN115398436B (zh) 用于自然语言处理的噪声数据扩充
CN116547676B (zh) 用于自然语言处理的增强型logit
CN116635862A (zh) 用于自然语言处理的域外数据扩充
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
CN116615727A (zh) 用于自然语言处理的关键词数据扩充工具
CN118265981B (zh) 用于为预训练的语言模型处置长文本的系统和技术
US12518098B2 (en) Fusion of word embeddings and word scores for text classification
US20260065171A1 (en) Adaptive training data augmentation to facilitate training named entity recognition 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
GR01 Patent grant
GR01 Patent grant