CN114365141B - 使用可生性对抗网络训练对话系统的语义解析器 - Google Patents

使用可生性对抗网络训练对话系统的语义解析器 Download PDF

Info

Publication number
CN114365141B
CN114365141B CN202080063344.0A CN202080063344A CN114365141B CN 114365141 B CN114365141 B CN 114365141B CN 202080063344 A CN202080063344 A CN 202080063344A CN 114365141 B CN114365141 B CN 114365141B
Authority
CN
China
Prior art keywords
seed
discriminator
training
tuple
semantic
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
CN202080063344.0A
Other languages
English (en)
Chinese (zh)
Other versions
CN114365141A (zh
Inventor
T·L·董
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
Priority to CN202411731914.5A priority Critical patent/CN119670726A/zh
Publication of CN114365141A publication Critical patent/CN114365141A/zh
Application granted granted Critical
Publication of CN114365141B publication Critical patent/CN114365141B/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
    • G06F40/20—Natural language analysis
    • G06F40/205—Parsing
    • 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
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/205—Parsing
    • G06F40/226—Validation
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/30—Semantic analysis
    • 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
    • G10L15/16—Speech classification or search using artificial neural networks
    • 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
    • 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
    • G10L15/26—Speech to text systems

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Theoretical Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Acoustics & Sound (AREA)
  • Human Computer Interaction (AREA)
  • Multimedia (AREA)
  • General Health & Medical Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Machine Translation (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
CN202080063344.0A 2019-09-11 2020-08-13 使用可生性对抗网络训练对话系统的语义解析器 Active CN114365141B (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202411731914.5A CN119670726A (zh) 2019-09-11 2020-08-13 使用可生性对抗网络训练对话系统的语义解析器

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
US201962898682P 2019-09-11 2019-09-11
US62/898,682 2019-09-11
PCT/US2020/046072 WO2021050197A1 (en) 2019-09-11 2020-08-13 Using a generative adversarial network to train a semantic parser of a dialog system

Related Child Applications (1)

Application Number Title Priority Date Filing Date
CN202411731914.5A Division CN119670726A (zh) 2019-09-11 2020-08-13 使用可生性对抗网络训练对话系统的语义解析器

Publications (2)

Publication Number Publication Date
CN114365141A CN114365141A (zh) 2022-04-15
CN114365141B true CN114365141B (zh) 2024-12-17

Family

ID=72235013

Family Applications (2)

Application Number Title Priority Date Filing Date
CN202080063344.0A Active CN114365141B (zh) 2019-09-11 2020-08-13 使用可生性对抗网络训练对话系统的语义解析器
CN202411731914.5A Pending CN119670726A (zh) 2019-09-11 2020-08-13 使用可生性对抗网络训练对话系统的语义解析器

Family Applications After (1)

Application Number Title Priority Date Filing Date
CN202411731914.5A Pending CN119670726A (zh) 2019-09-11 2020-08-13 使用可生性对抗网络训练对话系统的语义解析器

Country Status (5)

Country Link
US (2) US11908460B2 (https=)
EP (1) EP4028930B1 (https=)
JP (2) JP7597796B2 (https=)
CN (2) CN114365141B (https=)
WO (1) WO2021050197A1 (https=)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11908460B2 (en) 2019-09-11 2024-02-20 Oracle International Corporation Using a generative adversarial network to train a semantic parser of a dialog system
CN116072144B (zh) * 2021-11-01 2025-08-15 北京猿力未来科技有限公司 模型训练方法及装置
WO2023192766A1 (en) * 2022-03-31 2023-10-05 D5Ai Llc Generation and discrimination training as a variable resolution game

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8447611B2 (en) * 2006-09-05 2013-05-21 Fortemedia, Inc. Pen-type voice computer and method thereof
JP6649210B2 (ja) * 2016-08-30 2020-02-19 日本電信電話株式会社 音声合成学習装置、方法、及びプログラム
KR20190004525A (ko) * 2017-07-04 2019-01-14 주식회사 마인즈랩 문장 학습 시스템 및 문장 학습 방법
US10643320B2 (en) 2017-11-15 2020-05-05 Toyota Research Institute, Inc. Adversarial learning of photorealistic post-processing of simulation with privileged information
US20190163691A1 (en) * 2017-11-30 2019-05-30 CrowdCare Corporation Intent Based Dynamic Generation of Personalized Content from Dynamic Sources
JP6959152B2 (ja) * 2018-01-19 2021-11-02 ヤフー株式会社 情報処理装置、情報処理方法、及び情報処理プログラム
CN108962224B (zh) * 2018-07-19 2020-06-26 苏州思必驰信息科技有限公司 口语理解和语言模型联合建模方法、对话方法及系统
US11908460B2 (en) 2019-09-11 2024-02-20 Oracle International Corporation Using a generative adversarial network to train a semantic parser of a dialog system

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
"Dialogue Generation with GAN";Hui Su 等;《The Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18)》;20180429;第8163-8164页 *
"Generative Adversarial Nets";Ian J. Goodfellow 等;《arXiv:1406.2661》;20140610;第1-9页 *

Also Published As

Publication number Publication date
CN114365141A (zh) 2022-04-15
EP4028930B1 (en) 2025-07-16
US20210074274A1 (en) 2021-03-11
US12482457B2 (en) 2025-11-25
WO2021050197A1 (en) 2021-03-18
JP2022547998A (ja) 2022-11-16
EP4028930A1 (en) 2022-07-20
JP2025032163A (ja) 2025-03-11
JP7597796B2 (ja) 2024-12-10
US20240144923A1 (en) 2024-05-02
US11908460B2 (en) 2024-02-20
CN119670726A (zh) 2025-03-21

Similar Documents

Publication Publication Date Title
EP4028932B1 (en) Reduced training intent recognition techniques
US11935521B2 (en) Real-time feedback for efficient dialog processing
CN114365215A (zh) 动态上下文对话会话扩展
CN112487783B (zh) 用于自然语言理解的神经网络的压缩
US11810553B2 (en) Using backpropagation to train a dialog system
US12340172B2 (en) Semantic parser including a coarse semantic parser and a fine semantic parser
US11574636B2 (en) Task-oriented dialog suitable for a standalone device
US12482457B2 (en) Using a generative adversarial network to train a semantic parser of a dialog system
US11462208B2 (en) Implementing a correction model to reduce propagation of automatic speech recognition errors
EP3792912B1 (en) Improved wake-word recognition in low-power devices

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