公开(公告)号：US11669699B2

公开(公告)日：2023-06-06

申请号：US17010465

申请日：2020-09-02

Applicant: salesforce.com, inc.

Inventor： Congying Xia ,  Caiming Xiong

IPC: G06F40/56 ,  G06F16/9032 ,  G06F40/284 ,  G06N20/00 ,  G06F40/30 ,  G06N7/01

CPC classification number: G06F40/56 ,  G06F16/90332 ,  G06F40/284 ,  G06F40/30 ,  G06N7/01 ,  G06N20/00

Abstract: Embodiments described herein provide a composed variational natural language generation (CLANG) model that is configured to generate training samples for few-shot intents. Specifically, the CLANG model may build connections between existing training samples of many-shot intents and new training samples of few-shot intents by modeling an intent as a combination of a domain and an action. In this way, the CLANG model transfers knowledge from existing many-shot intents to few-shot intents in natural language generation by learning how to compose utterances with many-shot intents and transferring such knowledge to few-shot intents.

公开(公告)号：US20210374358A1

公开(公告)日：2021-12-02

申请号：US17010459

申请日：2020-09-02

Applicant: salesforce.com, inc.

Inventor： Congying Xia ,  Caiming Xiong

IPC: G06F40/56 ,  G06F40/284 ,  G06N7/00 ,  G06F16/9032

Abstract: Embodiments described herein provide a composed variational natural language generation (CLANG) model that is configured to generate training samples for few-shot intents. Specifically, the CLANG model may build connections between existing training samples of many-shot intents and new training samples of few-shot intents by modeling an intent as a combination of a domain and an action. In this way, the CLANG model transfers knowledge from existing many-shot intents to few-shot intents in natural language generation by learning how to compose utterances with many-shot intents and transferring such knowledge to few-shot intents.

公开(公告)号：US11625543B2

公开(公告)日：2023-04-11

申请号：US17010459

申请日：2020-09-02

Applicant: salesforce.com, inc.

Inventor： Congying Xia ,  Caiming Xiong

IPC: G06F16/9032 ,  G06F40/56 ,  G06F40/284 ,  G06N20/00 ,  G06N7/00 ,  G06F40/30

Abstract: Embodiments described herein provide a composed variational natural language generation (CLANG) model that is configured to generate training samples for few-shot intents. Specifically, the CLANG model may build connections between existing training samples of many-shot intents and new training samples of few-shot intents by modeling an intent as a combination of a domain and an action. In this way, the CLANG model transfers knowledge from existing many-shot intents to few-shot intents in natural language generation by learning how to compose utterances with many-shot intents and transferring such knowledge to few-shot intents.

公开(公告)号：US20210374603A1

公开(公告)日：2021-12-02

申请号：US17010465

申请日：2020-09-02

Applicant: salesforce.com, Inc.

Inventor： Congying Xia ,  Caiming Xiong

IPC: G06N20/00 ,  G06F40/30 ,  G06F40/284

Abstract: Embodiments described herein provide a composed variational natural language generation (CLANG) model that is configured to generate training samples for few-shot intents. Specifically, the CLANG model may build connections between existing training samples of many-shot intents and new training samples of few-shot intents by modeling an intent as a combination of a domain and an action. In this way, the CLANG model transfers knowledge from existing many-shot intents to few-shot intents in natural language generation by learning how to compose utterances with many-shot intents and transferring such knowledge to few-shot intents.