公开(公告)号：US20250005283A1

公开(公告)日：2025-01-02

申请号：US18742040

申请日：2024-06-13

Applicant: Meta Platforms, Inc.

Inventor： Akshat Shrivastava ,  Pierce I-Jen Chuang ,  Arun Babu ,  Shrey Desai ,  Abhinav Arora ,  Alexander Kolmykov-Zotov ,  Ahmed Aly

IPC: G06F40/284 ,  G06F40/205 ,  G06F40/30 ,  G10L15/18 ,  G10L15/22 ,  G10L15/30

Abstract: A method includes receiving from a client system a user input having input tokens and generating a span-based frame representation based on the input tokens. The span-based frame representation may include intents, slots, and a span. The span may include a first index endpoint associated with a first token and a second index endpoint associated with a second token. The method further includes encoding the user input, based on an encoder of a natural language understanding module, to generate a feature vector for the user input, and determining, by a length module of the natural language understanding module, a length of the span-based frame representation based on the feature vector for the user input. Generating the span-based frame representation may be further based on the length of the span-based frame representation. The method further includes, responsive to the user input, executing tasks based on the span-based frame representation.

公开(公告)号：US12045568B1

公开(公告)日：2024-07-23

申请号：US17525510

申请日：2021-11-12

Applicant: Meta Platforms, Inc.

Inventor： Akshat Shrivastava ,  Pierce I-Jen Chuang ,  Arun Babu ,  Shrey Desai ,  Abhinav Arora ,  Alexander Kolmykov-Zotov ,  Ahmed Aly

IPC: G06F40/284 ,  G06F40/205 ,  G06F40/30 ,  G10L15/18 ,  G10L15/22 ,  G10L15/30

CPC classification number: G06F40/284 ,  G06F40/205 ,  G06F40/30 ,  G10L15/1815 ,  G10L15/1822 ,  G10L15/22 ,  G10L15/30 ,  G10L2015/223

Abstract: In one embodiment, a method includes receiving a user input comprising input tokens from a client system, parsing the user input to determine ontology tokens and utterance tokens corresponding to the input tokens, decoding the ontology tokens and the utterance tokens to generate a span-based frame representation comprising intents, slots, and a span, wherein the ontology tokens are decoded into the intents and slots, and wherein the utterance tokens are decoded to determine the span comprising one or more tokens of the input tokens, wherein the span comprises a first index endpoint associated with a first token of the one or more tokens and a second index endpoint associated with a second token of the one or more tokens, and executing, responsive to the user input, one or more tasks based on the span-based frame representation.