公开(公告)号：US12288039B1

公开(公告)日：2025-04-29

申请号：US16744537

申请日：2020-01-16

Applicant: Salesforce, Inc.

Inventor： Michael Justin Smathers ,  Daniel Joseph Platt ,  Nathan D. Nichols ,  Jared Lorince

IPC: G06F40/56 ,  G06F18/214

Abstract: Disclosed herein is computer technology that provides adaptive mechanisms for learning concepts that are expressed by natural language sentences, and then applies this learning to appropriately classify new natural language sentences with the relevant concept that they express.

公开(公告)号：US11989519B2

公开(公告)日：2024-05-21

申请号：US16916248

申请日：2020-06-30

Applicant: Salesforce, Inc.

Inventor： Daniel Joseph Platt ,  Nathan D. Nichols ,  Michael Justin Smathers ,  Jared Lorince

IPC: G06F40/20 ,  G06F16/33 ,  G06F18/214 ,  G06F40/205 ,  G06F40/211 ,  G06F40/253 ,  G06F40/295 ,  G06F40/30 ,  G06F40/56 ,  G06N20/00 ,  G06F40/268 ,  G06F40/279 ,  G10L15/06 ,  G10L15/18 ,  G10L15/22

CPC classification number: G06F40/30 ,  G06F16/3344 ,  G06F18/214 ,  G06F40/205 ,  G06F40/211 ,  G06F40/253 ,  G06F40/295 ,  G06N20/00 ,  G06F40/268 ,  G06F40/279 ,  G06F40/56 ,  G10L15/063 ,  G10L15/1822 ,  G10L15/22

Abstract: Disclosed herein is computer technology that applies natural language processing (NLP) techniques to training data to generate information used to train a natural language generation (NLG) system to produce output that stylistically resembles the training data. In this fashion, the NLG system can be readily trained with training data supplied by a user so that the NLG system is adapted to produce output that stylistically resembles such training data. In an example, an NLP system detects a plurality of linguistic features in the training data. These detected linguistic features are then aggregated into a specification data structure that is arranged for training the NLG system to produce natural language output that stylistically resembles the training data. Parameters in the specification data structure can be linked to objects in an ontology used by the NLG system to facilitate the training of the NLG system based on the detected linguistic features.