CN115220875A - 利用连续适配来执行多个任务 - Google Patents

利用连续适配来执行多个任务 Download PDF

Info

Publication number
CN115220875A
CN115220875A CN202110404714.9A CN202110404714A CN115220875A CN 115220875 A CN115220875 A CN 115220875A CN 202110404714 A CN202110404714 A CN 202110404714A CN 115220875 A CN115220875 A CN 115220875A
Authority
CN
China
Prior art keywords
task
specific
representations
shared
encoder
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
CN202110404714.9A
Other languages
English (en)
Chinese (zh)
Inventor
王安
马永亮
唐都钰
姜大昕
段楠
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.)
Microsoft Technology Licensing LLC
Original Assignee
Microsoft Technology Licensing LLC
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 Microsoft Technology Licensing LLC filed Critical Microsoft Technology Licensing LLC
Priority to CN202110404714.9A priority Critical patent/CN115220875A/zh
Priority to PCT/US2022/022234 priority patent/WO2022221045A1/fr
Publication of CN115220875A publication Critical patent/CN115220875A/zh
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/205—Parsing
    • G06F40/216—Parsing using statistical methods
    • 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
    • G06F40/30—Semantic analysis
    • G06F40/35—Discourse or dialogue representation
    • 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
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Software Systems (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Biomedical Technology (AREA)
  • Computing Systems (AREA)
  • Molecular Biology (AREA)
  • Evolutionary Computation (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • Biophysics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Probability & Statistics with Applications (AREA)
  • Machine Translation (AREA)
CN202110404714.9A 2021-04-15 2021-04-15 利用连续适配来执行多个任务 Pending CN115220875A (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN202110404714.9A CN115220875A (zh) 2021-04-15 2021-04-15 利用连续适配来执行多个任务
PCT/US2022/022234 WO2022221045A1 (fr) 2021-04-15 2022-03-29 Réalisation de tâches multiples avec adaptation continue

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110404714.9A CN115220875A (zh) 2021-04-15 2021-04-15 利用连续适配来执行多个任务

Publications (1)

Publication Number Publication Date
CN115220875A true CN115220875A (zh) 2022-10-21

Family

ID=81384732

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110404714.9A Pending CN115220875A (zh) 2021-04-15 2021-04-15 利用连续适配来执行多个任务

Country Status (2)

Country Link
CN (1) CN115220875A (fr)
WO (1) WO2022221045A1 (fr)

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR102492318B1 (ko) * 2015-09-18 2023-01-26 삼성전자주식회사 모델 학습 방법 및 장치, 및 데이터 인식 방법
US12008459B2 (en) * 2019-04-19 2024-06-11 Microsoft Technology Licensing, Llc Multi-task machine learning architectures and training procedures

Also Published As

Publication number Publication date
WO2022221045A1 (fr) 2022-10-20

Similar Documents

Publication Publication Date Title
US10817650B2 (en) Natural language processing using context specific word vectors
Wang et al. Morphological segmentation with window LSTM neural networks
WO2023160472A1 (fr) Procédé de formation de modèle et dispositif associé
CN111460807A (zh) 序列标注方法、装置、计算机设备和存储介质
WO2023236977A1 (fr) Procédé de traitement de données et dispositif associé
KR102315830B1 (ko) 반지도 학습 기반 단어 단위 감정 임베딩과 lstm 모델을 이용한 대화 내에서 발화의 감정 분류 방법
WO2022253074A1 (fr) Procédé de traitement de données et dispositif associé
EP4361843A1 (fr) Procédé de recherche de réseau neuronal et dispositif associé
CN110851594A (zh) 一种基于多通道深度学习模型的文本分类方法及其装置
CN113553418B (zh) 一种基于多模态学习的视觉对话生成方法及装置
CN113723105A (zh) 语义特征提取模型的训练方法、装置、设备及存储介质
CN111653275A (zh) 基于lstm-ctc尾部卷积的语音识别模型的构建方法及装置、语音识别方法
CN115951883B (zh) 分布式微服务架构的服务组件管理系统及其方法
CN114360502A (zh) 语音识别模型的处理方法、语音识别方法及装置
CN112232070A (zh) 自然语言处理模型构建方法、系统、电子设备及存储介质
CN111597816A (zh) 一种自注意力命名实体识别方法、装置、设备及存储介质
Chowdhury et al. A cascaded long short-term memory (LSTM) driven generic visual question answering (VQA)
CN113887169A (zh) 文本处理方法、电子设备、计算机存储介质及程序产品
CN116484224A (zh) 一种多模态预训练模型的训练方法、装置、介质及设备
CN111368532A (zh) 一种基于lda的主题词嵌入消歧方法及系统
CN112949284A (zh) 一种基于Transformer模型的文本语义相似度预测方法
CN115220875A (zh) 利用连续适配来执行多个任务
Chauhan et al. PsuedoProp at SemEval-2020 Task 11: Propaganda span detection using BERT-CRF and ensemble sentence level classifier
Islam et al. Bengali caption generation for images using deep learning
Yap et al. Enhancing BISINDO Recognition Accuracy Through Comparative Analysis of Three CNN Architecture 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