Search

Xiujun Li

from Redmond, WA
Get Report
Related to:
Lijen A Tseng, 67Li Qiao, 55Francis Wong, 42Guohua Chen, 45Yu Lee, 53Yu-Huang Li, 54Wen Y Huang, 56Hsuan Y Huang, 54Xian Huang, 70
Connected to:
Ai Q Li, 63Ai H Li, 80Aida Li, 67Aijun Li, 64Aiwen Q Li, 56Aiyan Li, 61Alan Li, 80Alice Li, 45Alida Li, 58Alisha Li, 30

Xiujun Li Phones & Addresses

  • Redmond, WA
  • Seattle, WA
  • Bellevue, WA
  • Madison, WI
  • San Jose, CA

Publications

Us Patents

Synthetic Data Generation For Training Of Natural Language Understanding Models

View page
US Patent:
20230076095, Mar 9, 2023
Filed:
Oct 11, 2022
Appl. No.:
17/963766
Inventors:
- Redmond WA, US
Chenguang Zhu - Sammamish WA, US
Chunyuan Li - Issaquah WA, US
Xiujun Li - Seattle WA, US
Jinchao Li - Redmond WA, US
Nanshan Zeng - Bellevue WA, US
Jianfeng Gao - Woodinville WA, US
Assignee:
Microsoft Technology Licensing, LLC - Redmond WA
International Classification:
G10L 15/18
G10L 15/22
G10L 15/08
Abstract:
This document relates to machine learning. One example includes a method or technique that can be performed on a computing device. The method or technique can include obtaining a task-adapted generative model that has been tuned using one or more task-specific seed examples. The method or technique can also include inputting dialog acts into the task-adapted generative model and obtaining synthetic utterances that are output by the task-adapted generative model. The method or technique can also include populating a synthetic training corpus with synthetic training examples that include the synthetic utterances. The synthetic training corpus may be suitable for training a natural language understanding model.

Composite Task Execution

View page
US Patent:
20190324795, Oct 24, 2019
Filed:
Apr 24, 2018
Appl. No.:
15/960809
Inventors:
- Redmond WA, US
Xiujun LI - Bellevue WA, US
Lihong LI - Redmond WA, US
Da TANG - New York NY, US
Chong WANG - Bellevue WA, US
Tony JEBARA - Los Gatos CA, US
Assignee:
Microsoft Technology Licensing, LLC - Redmond WA
International Classification:
G06F 9/48
G06F 9/50
G06F 17/30
G06F 17/28
G06N 3/02
G10L 15/22
Abstract:
A system for executing composite tasks can include a processor to detect a composite task from a user. The processor can also detect a plurality of subtasks corresponding to the composite task based on unsupervised data without a label, wherein the plurality of subtasks are identified by a top-level dialog policy. The processor can also detect a plurality of actions, wherein each action is to complete one of the subtasks, and wherein each action is identified by a low-level dialog policy corresponding to the subtasks identified by the top-level dialog policy. The processor can also update a dialog manager based on a completion of each action corresponding to the subtasks and execute instructions based on a policy identified by the dialog manager, wherein the executed instructions implement the policy with a lowest global cost corresponding to the composite task provided by the user.

Efficient Dialogue Policy Learning

View page
US Patent:
20180052825, Feb 22, 2018
Filed:
Jun 9, 2017
Appl. No.:
15/619314
Inventors:
- Redmond WA, US
Jianfeng GAO - Redmond WA, US
Lihong LI - Redmond WA, US
Xiujun LI - Redmond WA, US
Faisal AHMED - Redmond WA, US
Li Chase DENG - Redmond WA, US
International Classification:
G06F 17/27
Abstract:
Efficient exploration of natural language conversations associated with dialogue policy learning may be performed using probabilistic distributions. Exploration may comprise identifying key terms associated with the received natural language input utilizing the structured representation. Identifying key terms may include converting raw text of the received natural language input into a structured representation. Exploration may also comprise mapping at least one of the key terms to an action to be performed by the computer system in response to receiving natural language input associated with the at least one key term. Mapping may then be performed using a probabilistic distribution. The action may then be performed by the computer system. A replay buffer may also be utilized by the computer system to track what has occurred in previous conversations. The replay buffer may then be pre-filled with one or more successful dialogues to jumpstart exploration.

Isbn (Books And Publications)

Low-Cost Smart Capacitive Sensors for Position & Speed Measurement

View page
Author

Xiujun Li

ISBN #

9040714541

Control profile
Xiujun Li from Redmond, WA Get Report