公开(公告)号：US12073178B2

公开(公告)日：2024-08-27

申请号：US17586504

申请日：2022-01-27

Applicant: salesforce.com, inc.

Inventor： Zahra Fatemi ,  Caiming Xiong ,  Wenhao Liu ,  Chen Xing

IPC: G06F40/279 ,  G06F40/35 ,  G06F40/56 ,  G06N3/045 ,  G06N3/08

CPC classification number: G06F40/279 ,  G06F40/35 ,  G06F40/56 ,  G06N3/045 ,  G06N3/08

Abstract: Embodiments are directed to a training framework for reducing gender bias in a pre-trained language model. To reduce gender bias a gender neutral dataset is generated. Next, parameters of the pre-trained language model are frozen and do not change during a subsequent training phase. As all the pre-trained parameters are frozen, forgetting of information from the original training data is minimized. New parameters are added to the language model. The new parameters may be associated with gender related terms, such as profession names. In a subsequent training phase the new parameters of the language model are trained using a gender neutral dataset.

公开(公告)号：US11763090B2

公开(公告)日：2023-09-19

申请号：US16718186

申请日：2019-12-18

Applicant: salesforce.com, inc.

Inventor： Tian Xie ,  Kazuma Hashimoto ,  Xinyi Yang ,  Caiming Xiong

IPC: G06F40/00 ,  G06F40/30 ,  G06F40/216 ,  G06N5/04 ,  G06F18/2413 ,  G06F18/214

CPC classification number: G06F40/30 ,  G06F18/2148 ,  G06F18/2413 ,  G06F40/216 ,  G06N5/04

Abstract: An online system that allows users to interact with it using expressions in natural language form includes an intent inference module allowing it to infer an intent represented by a user expression. The intent inference module has a set of possible intents, along with a small set of example natural language expressions known to represent that intent. When a user interacts with the system using a natural language expression for which the intent is not already known, the intent inference module applies a natural language inference model to compute scores indicating whether the user expression textually entails the various example natural language expressions. Based on the scores, the intent inference module determines an intent that is most applicable for the expression. If an intent cannot be determined with sufficient confidence, the intent inference module may further attempt to determine whether the various example natural language expressions textually entail the user expression.

公开(公告)号：US20230252345A1

公开(公告)日：2023-08-10

申请号：US17827334

申请日：2022-05-27

Applicant: salesforce.com, inc.

Inventor： Yongjun Chen ,  Jia LI ,  Nitish Shirish Keskar ,  Caiming Xiong

IPC: G06N20/00

CPC classification number: G06N20/00

Abstract: Embodiments described herein provide methods and systems for training a sequential recommendation model. A system receives a plurality of user behavior sequences, and encodes those sequences into a plurality of user interest representations. The system predicts a next item using a sequential recommendation model, producing a probability distribution over a set of items. The next interacted item in a sequence is selected as a positive sample, and a negative sample is selected based on the generated probability distribution. The positive and negative samples are used to compute a contrastive loss and update the sequential recommendation model.

公开(公告)号：US11710077B2

公开(公告)日：2023-07-25

申请号：US17457163

申请日：2021-12-01

Applicant: Salesforce.com, Inc.

Inventor： Ankit Chadha ,  Caiming Xiong ,  Ran Xu

IPC: G06N20/00 ,  G06T3/40 ,  G06T3/60 ,  G06N3/04 ,  G06N3/08 ,  G06T3/20 ,  G06F18/21 ,  G06F18/214 ,  G06V10/764 ,  G06V10/80 ,  G06V10/82 ,  G06V10/20

CPC classification number: G06N20/00 ,  G06F18/217 ,  G06F18/2148 ,  G06N3/04 ,  G06N3/08 ,  G06T3/20 ,  G06T3/40 ,  G06T3/60 ,  G06V10/20 ,  G06V10/764 ,  G06V10/809 ,  G06V10/82

Abstract: Computing systems may support image classification and image detection services, and these services may utilize object detection/image classification machine learning models. The described techniques provide for normalization of confidence scores corresponding to manipulated target images and for non-max suppression within the range of confidence scores for manipulated images. In one example, the techniques provide for generating different scales of a test image, and the system performs normalization of confidence scores corresponding to each scaled image and non-max suppression per scaled image These techniques may be used to provide more accurate image detection (e.g., object detection and/or image classification) and may be used with models that are not trained on modified image sets. The model may be trained on a standard (e.g. non-manipulated) image set but used with manipulated target images and the described techniques to provide accurate object detection.

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：US11599730B2

公开(公告)日：2023-03-07

申请号：US16870568

申请日：2020-05-08

Applicant: salesforce.com, inc.

Inventor： Chien-Sheng Wu ,  Chu Hong Hoi ,  Caiming Xiong

IPC: G06F17/00 ,  G06F40/35 ,  G06N5/04 ,  G06N3/08 ,  G06K9/62 ,  G10L15/16 ,  G10L15/22 ,  G10L15/30

Abstract: Embodiments described in this disclosure illustrate the use of self-/semi supervised approaches for label-efficient DST in task-oriented dialogue systems. Conversational behavior is modeled by next response generation and turn utterance generation tasks. Prediction consistency is strengthened by augmenting data with stochastic word dropout and label guessing. Experimental results show that by exploiting self-supervision the joint goal accuracy can be boosted with limited labeled data.

公开(公告)号：US11580445B2

公开(公告)日：2023-02-14

申请号：US16653890

申请日：2019-10-15

Applicant: salesforce.com, inc.

Inventor： Hao Liu ,  Richard Socher ,  Caiming Xiong

IPC: G06N20/00 ,  G06N5/02

Abstract: Systems and methods are provided for efficient off-policy credit assignment (ECA) in reinforcement learning. ECA allows principled credit assignment for off-policy samples, and therefore improves sample efficiency and asymptotic performance. One aspect of ECA is to formulate the optimization of expected return as approximate inference, where policy is approximating a learned prior distribution, which leads to a principled way of utilizing off-policy samples. Other features are also provided.

公开(公告)号：US11568306B2

公开(公告)日：2023-01-31

申请号：US16398757

申请日：2019-04-30

Applicant: salesforce.com, inc.

Inventor： Lichao Sun ,  Caiming Xiong ,  Jia Li ,  Richard Socher

IPC: G06K9/62 ,  G06N20/00 ,  G06F21/62 ,  G06N3/08

Abstract: Approaches for private and interpretable machine learning systems include a system for processing a query. The system includes one or more teacher modules for receiving a query and generating a respective output, one or more privacy sanitization modules for privacy sanitizing the respective output of each of the one or more teacher modules, and a student module for receiving a query and the privacy sanitized respective output of each of the one or more teacher modules and generating a result. Each of the one or more teacher modules is trained using a respective private data set. The student module is trained using a public data set. In some embodiments, human understandable interpretations of an output from the student module is provided to a model user.

公开(公告)号：US11501076B2

公开(公告)日：2022-11-15

申请号：US15974075

申请日：2018-05-08

Applicant: salesforce.com, inc.

Inventor： Nitish Shirish Keskar ,  Bryan McCann ,  Caiming Xiong ,  Richard Socher

IPC: G06F40/30 ,  G06N3/08 ,  G06N5/04 ,  G06N3/04 ,  G06F40/56 ,  G06F16/242 ,  G06F16/33 ,  G06F16/332 ,  G06N20/20 ,  G06N20/10 ,  G06N20/00

Abstract: Approaches for multitask learning as question answering include a method for training that includes receiving a plurality of training samples including training samples from a plurality of task types, presenting the training samples to a neural model to generate an answer, determining an error between the generated answer and the natural language ground truth answer for each training sample presented, and adjusting parameters of the neural model based on the error. Each of the training samples includes a natural language context, question, and ground truth answer. An order in which the training samples are presented to the neural model includes initially selecting the training samples according to a first training strategy and switching to selecting the training samples according to a second training strategy. In some embodiments the first training strategy is a sequential training strategy and the second training strategy is a joint training strategy.

公开(公告)号：US20220335257A1

公开(公告)日：2022-10-20

申请号：US17231015

申请日：2021-04-15

Applicant: salesforce.com, inc.

Inventor： Devansh Arpit ,  Huan Wang ,  Caiming Xiong

IPC: G06K9/62 ,  G06N3/08

Abstract: A system uses a neural network to detect anomalies in time series data. The system trains the neural network for a fixed number of iterations using data from a time window of the time series. The system uses the loss value at the end of the fixed number of iterations for identifying anomalies in the time series data. For a time window, the system initializes the neural network to random values and trains the neural network for a fixed number of iterations using the data of the time window. After the fixed number of iterations, the system compares the loss values for various data points to a threshold value. Data points having loss value exceeding a threshold are identified as anomalous data points.