CN115989490A - 用于为文本分类提供解释的技术 - Google Patents

用于为文本分类提供解释的技术 Download PDF

Info

Publication number
CN115989490A
CN115989490A CN202180051353.2A CN202180051353A CN115989490A CN 115989490 A CN115989490 A CN 115989490A CN 202180051353 A CN202180051353 A CN 202180051353A CN 115989490 A CN115989490 A CN 115989490A
Authority
CN
China
Prior art keywords
utterance
utterances
intent
anchor
robot
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
CN202180051353.2A
Other languages
English (en)
Chinese (zh)
Inventor
G·辛格拉朱
V·比什诺伊
M·帕雷克
A·王
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 CN115989490A publication Critical patent/CN115989490A/zh
Pending legal-status Critical Current

Links

Images

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
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/40—Processing or translation of natural language
    • 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
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/04—Inference or reasoning models
    • G06N5/045—Explanation of inference; Explainable artificial intelligence [XAI]; Interpretable artificial intelligence
    • 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
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/08—Speech classification or search
    • G10L15/18—Speech classification or search using natural language modelling
    • G10L15/1815—Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • General Health & Medical Sciences (AREA)
  • Software Systems (AREA)
  • Computing Systems (AREA)
  • Medical Informatics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Mathematical Physics (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Machine Translation (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
CN202180051353.2A 2020-08-21 2021-08-20 用于为文本分类提供解释的技术 Pending CN115989490A (zh)

Applications Claiming Priority (5)

Application Number Priority Date Filing Date Title
US202063068608P 2020-08-21 2020-08-21
US63/068,608 2020-08-21
US202163174336P 2021-04-13 2021-04-13
US63/174,336 2021-04-13
PCT/US2021/046938 WO2022040547A1 (en) 2020-08-21 2021-08-20 Techniques for providing explanations for text classification

Publications (1)

Publication Number Publication Date
CN115989490A true CN115989490A (zh) 2023-04-18

Family

ID=80269614

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202180051353.2A Pending CN115989490A (zh) 2020-08-21 2021-08-20 用于为文本分类提供解释的技术

Country Status (4)

Country Link
US (2) US12106055B2 (https=)
JP (1) JP7851913B2 (https=)
CN (1) CN115989490A (https=)
WO (1) WO2022040547A1 (https=)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117112256A (zh) * 2023-08-09 2023-11-24 哈尔滨工程大学 一种适用于反应堆分析程序不确定性分析的通用接口方法

Families Citing this family (30)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9465833B2 (en) 2012-07-31 2016-10-11 Veveo, Inc. Disambiguating user intent in conversational interaction system for large corpus information retrieval
ES2751484T3 (es) * 2013-05-07 2020-03-31 Veveo Inc Interfaz de entrada de voz incremental con retroalimentación en tiempo real
US9946757B2 (en) 2013-05-10 2018-04-17 Veveo, Inc. Method and system for capturing and exploiting user intent in a conversational interaction based information retrieval system
US9852136B2 (en) 2014-12-23 2017-12-26 Rovi Guides, Inc. Systems and methods for determining whether a negation statement applies to a current or past query
US12431149B2 (en) * 2020-03-24 2025-09-30 Evident Canada, Inc. Compressive sensing for full matrix capture
US20220318679A1 (en) * 2021-03-31 2022-10-06 Jio Platforms Limited Multi-faceted bot system and method thereof
US12340792B2 (en) * 2021-05-17 2025-06-24 Salesforce, Inc. Systems and methods for few-shot intent classifier models
US20220398524A1 (en) * 2021-06-11 2022-12-15 Aktify, Inc. Consumer interaction agent management platform
EP4150536B1 (en) * 2021-07-29 2025-09-03 Google LLC Providing certain reasoning with respect to fulfillment of an assistant command
US12223955B2 (en) 2021-07-29 2025-02-11 Google Llc Providing certain reasoning with respect to fulfillment of an assistant command
US12250180B1 (en) * 2021-08-03 2025-03-11 Amazon Technologies, Inc. Dynamically selectable automated speech recognition using a custom vocabulary
US12052274B2 (en) 2021-09-23 2024-07-30 Armis Security Ltd. Techniques for enriching device profiles and mitigating cybersecurity threats using enriched device profiles
US20250014698A1 (en) * 2021-11-17 2025-01-09 Eyetelligence Limited Method and system for analysing medical images to generate a medical report
WO2023158076A1 (ko) * 2022-02-16 2023-08-24 삼성전자주식회사 전자 장치 및 전자 장치의 발화 처리 방법
US12572846B2 (en) 2022-03-22 2026-03-10 Armis Security Ltd. System and method for device attribute identification based on host configuration protocols
US12494191B2 (en) * 2022-03-28 2025-12-09 Capital One Services, Llc Flexible text-to-speech for screen readers
US20230394136A1 (en) * 2022-06-01 2023-12-07 Armis Security Ltd. System and method for device attribute identification based on queries of interest
US12468895B2 (en) 2022-06-21 2025-11-11 Kore.Ai, Inc. Systems and methods for training a virtual assistant
WO2023250201A1 (en) 2022-06-24 2023-12-28 Celligence International Llc Using a conversation interface to transfer digital assets
US12470593B2 (en) 2022-07-11 2025-11-11 Armis Security Ltd. Malicious lateral movement detection using remote system protocols
KR20240067149A (ko) * 2022-11-04 2024-05-16 삼성전자주식회사 자동 레이블링을 위한 트레이닝 방법 및 자동 레이블링 장치
US20240333612A1 (en) * 2023-03-31 2024-10-03 Atlassian Pty Ltd Apparatuses, methods, and computer program products for processing multi-channel service data objects to initiate automated resolution actions via an intent engine
US12602842B2 (en) 2023-04-18 2026-04-14 Snap Inc. Texture generation using multimodal embeddings
US12561920B2 (en) 2023-04-18 2026-02-24 Snap Inc. Dynamic model adaptation customized for individual users
US20240362507A1 (en) * 2023-04-28 2024-10-31 Red Hat, Inc. Automatic insight into ticket support processes via xai explanation of prediction models
JPWO2025004959A1 (https=) * 2023-06-27 2025-01-02
US20250008021A1 (en) * 2023-06-28 2025-01-02 Jpmorgan Chase Bank, N.A. Systems and methods for artificial intelligence-based coaching using microlearning
US12537825B2 (en) * 2023-07-17 2026-01-27 Bank Of America Corporation Securing interactive response systems from infiltration of artificial intelligence programs
US20250036695A1 (en) * 2023-07-30 2025-01-30 Microsoft Technology Licensing, Llc Generating enhanced output of generative models using intent-specific grounding
US20250063003A1 (en) * 2023-08-14 2025-02-20 Paypal, Inc. Multi-agent computer software framework for a conversational artificial intelligence system

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130311271A1 (en) * 2012-05-17 2013-11-21 Microsoft Corporation Structured relevant keyword and intent suggestion with bid and other auction parameters based on advertiser specific context
CN103473317A (zh) * 2013-09-12 2013-12-25 百度在线网络技术（北京）有限公司 提取关键词的方法和设备
CN103744843A (zh) * 2013-12-25 2014-04-23 北京百度网讯科技有限公司 一种在线语音翻译方法及装置
CN104516986A (zh) * 2015-01-16 2015-04-15 青岛理工大学 一种语句识别方法及装置
CN110837835A (zh) * 2019-10-29 2020-02-25 华中科技大学 一种基于边界点检测的场景文本端到端识别方法

Family Cites Families (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2010078614A1 (en) * 2009-01-08 2010-07-15 Relevancenow Pty Limited Chatbots
US20130066632A1 (en) * 2011-09-14 2013-03-14 At&T Intellectual Property I, L.P. System and method for enriching text-to-speech synthesis with automatic dialog act tags
US8700398B2 (en) * 2011-11-29 2014-04-15 Nuance Communications, Inc. Interface for setting confidence thresholds for automatic speech recognition and call steering applications
WO2014144579A1 (en) * 2013-03-15 2014-09-18 Apple Inc. System and method for updating an adaptive speech recognition model
US9805718B2 (en) * 2013-04-19 2017-10-31 Sri Internaitonal Clarifying natural language input using targeted questions
US10614799B2 (en) * 2014-11-26 2020-04-07 Voicebox Technologies Corporation System and method of providing intent predictions for an utterance prior to a system detection of an end of the utterance
US9978374B2 (en) * 2015-09-04 2018-05-22 Google Llc Neural networks for speaker verification
US20190188317A1 (en) 2017-12-15 2019-06-20 International Business Machines Corporation Automatic seeding of an application programming interface (api) into a conversational interface
JP7234926B2 (ja) 2018-01-16 2023-03-08 ソニーグループ株式会社 情報処理装置、情報処理システム、および情報処理方法、並びにプログラム
US11625630B2 (en) 2018-01-26 2023-04-11 International Business Machines Corporation Identifying intent in dialog data through variant assessment
US10878817B2 (en) * 2018-02-24 2020-12-29 Twenty Lane Media, LLC Systems and methods for generating comedy
KR102047385B1 (ko) * 2018-09-21 2019-11-21 삼성생명보험주식회사 챗봇 구동 방법, 장치 및 컴퓨터 판독가능 매체
WO2020163627A1 (en) * 2019-02-07 2020-08-13 Clinc, Inc. Systems and methods for machine learning-based multi-intent segmentation and classification
US11182242B2 (en) * 2019-06-21 2021-11-23 Intel Corporation Technologies for preserving error correction capability in compute-in-memory operations
US11626106B1 (en) * 2020-02-25 2023-04-11 Amazon Technologies, Inc. Error attribution in natural language processing systems
US11341339B1 (en) * 2020-05-14 2022-05-24 Amazon Technologies, Inc. Confidence calibration for natural-language understanding models that provides optimal interpretability
US11941367B2 (en) * 2021-05-29 2024-03-26 International Business Machines Corporation Question generation by intent prediction

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130311271A1 (en) * 2012-05-17 2013-11-21 Microsoft Corporation Structured relevant keyword and intent suggestion with bid and other auction parameters based on advertiser specific context
CN103473317A (zh) * 2013-09-12 2013-12-25 百度在线网络技术（北京）有限公司 提取关键词的方法和设备
CN103744843A (zh) * 2013-12-25 2014-04-23 北京百度网讯科技有限公司 一种在线语音翻译方法及装置
CN104516986A (zh) * 2015-01-16 2015-04-15 青岛理工大学 一种语句识别方法及装置
CN110837835A (zh) * 2019-10-29 2020-02-25 华中科技大学 一种基于边界点检测的场景文本端到端识别方法

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117112256A (zh) * 2023-08-09 2023-11-24 哈尔滨工程大学 一种适用于反应堆分析程序不确定性分析的通用接口方法
CN117112256B (zh) * 2023-08-09 2025-06-06 哈尔滨工程大学 一种适用于反应堆分析程序不确定性分析的通用接口方法

Also Published As

Publication number Publication date
JP7851913B2 (ja) 2026-04-27
US20220058347A1 (en) 2022-02-24
JP2023538923A (ja) 2023-09-12
US20240338531A1 (en) 2024-10-10
US12106055B2 (en) 2024-10-01
WO2022040547A1 (en) 2022-02-24

Similar Documents

Publication Publication Date Title
JP7851913B2 (ja) テキスト分類についての説明を与えるための技術
US12566982B2 (en) Chatbot for defining a machine learning (ML) solution
CN111857794B (zh) 机器人可扩展性基础设施
US11775572B2 (en) Directed acyclic graph based framework for training models
CN114424185B (zh) 用于自然语言处理的停用词数据扩充
US20230267374A1 (en) Machine learning (ml) infrastructure techniques
US20250013884A1 (en) Techniques for adaptive pipelining composition for machine learning (ml)
US11475374B2 (en) Techniques for automated self-adjusting corporation-wide feature discovery and integration
CN116547676B (zh) 用于自然语言处理的增强型logit
CN115917553A (zh) 在聊天机器人中实现稳健命名实体识别的实体级数据扩充
EP4028874A1 (en) Techniques for adaptive and context-aware automated service composition for machine learning (ml)
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
US12518129B2 (en) Method and system for over-prediction in neural networks
CN118202344A (zh) 用于从文档中提取嵌入式数据的深度学习技术
KR20240101703A (ko) 사전-트레이닝된 언어 모델들에 대한 긴 텍스트를 핸들링하기 위한 시스템 및 기술들
CN118251668A (zh) 用于从数据中提取问题答案对的基于规则的技术
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
CN120092248A (zh) 基于目标的超参数调谐中的目标函数优化

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