公开(公告)号：US12032627B2

公开(公告)日：2024-07-09

申请号：US17526806

申请日：2021-11-15

Applicant: Microsoft Technology Licensing, LLC

Inventor： Jinchao Li ,  Lars H. Liden ,  Baolin Peng ,  Thomas Park ,  Swadheen Kumar Shukla ,  Jianfeng Gao

IPC: G06F16/60 ,  G06F16/63 ,  G06N20/00

CPC classification number: G06F16/63 ,  G06N20/00

Abstract: Systems and methods are provided for determining a response to a query in a dialog. An entity extractor extracts rules and conditions associated with the query and determines a particular task. The disclosed technology generates a transformer-based dialog embedding by pre-training a transformer using dialog corpora including a plurality of tasks. A task-specific classifier generates a first set of candidate responses based on rules and conditions associated with the task. The transformer-based dialog embedding generates a second set of candidate responses to the query. The classifier accommodates changes made to a task by an interactive dialog editor as machine teaching. A response generator generates a response based on the first and second sets of candidate responses using an optimization function. The disclosed technology leverages both a data-driven, generative model (a transformer) based on dialog corpora and a user-driven, task-specific rule-based classifier that accommodating updates in rules and conditions associated with a particular task.

公开(公告)号：US20220084510A1

公开(公告)日：2022-03-17

申请号：US17021892

申请日：2020-09-15

Applicant: Microsoft Technology Licensing, LLC

Inventor： Baolin Peng ,  Chenguang Zhu ,  Chunyuan Li ,  Xiujun Li ,  Jinchao Li ,  Nanshan Zeng ,  Jianfeng Gao

IPC: G10L15/18 ,  G10L15/08 ,  G10L15/22

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.

公开(公告)号：US11875787B2

公开(公告)日：2024-01-16

申请号：US17963766

申请日：2022-10-11

Applicant: Microsoft Technology Licensing, LLC

Inventor： Baolin Peng ,  Chenguang Zhu ,  Chunyuan Li ,  Xiujun Li ,  Jinchao Li ,  Nanshan Zeng ,  Jianfeng Gao

IPC: G10L15/18 ,  G10L15/22 ,  G10L15/08

CPC classification number: G10L15/18 ,  G10L15/083 ,  G10L15/22

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-semantically-conditioned generative model that has been pretrained based at least on a first training data set having unlabeled training examples and semantically conditioned based at least on a second training data set having dialog act-labeled utterances. The method or technique can also include inputting dialog acts into the semantically-conditioned generative model and obtaining synthetic utterances that are output by the semantically-conditioned generative model. The method or technique can also include outputting the synthetic utterances.

公开(公告)号：US20230076095A1

公开(公告)日：2023-03-09

申请号：US17963766

申请日：2022-10-11

Applicant: Microsoft Technology Licensing, LLC

Inventor： Baolin Peng ,  Chenguang Zhu ,  Chunyuan Li ,  Xiujun Li ,  Jinchao Li ,  Nanshan Zeng ,  Jianfeng Gao

IPC: G10L15/18 ,  G10L15/22 ,  G10L15/08

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.

公开(公告)号：US11508360B2

公开(公告)日：2022-11-22

申请号：US17021892

申请日：2020-09-15

Applicant: Microsoft Technology Licensing, LLC

Inventor： Baolin Peng ,  Chenguang Zhu ,  Chunyuan Li ,  Xiujun Li ,  Jinchao Li ,  Nanshan Zeng ,  Jianfeng Gao

IPC: G10L15/18 ,  G10L15/22 ,  G10L15/08

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.