-
公开(公告)号：US10353905B2
公开(公告)日：2019-07-16
申请号：US14695996
申请日：2015-04-24
Applicant: salesforce.com, inc.
Inventor： Govardana Sachithanandam Ramachandran , Hawro Mustafa
Abstract: Identifying entities in semi-structured content is described. A system assigns a corresponding entity type based on a corresponding entity type score for each token in a sequence of tokens in semi-structured content, based on multiple entity types, wherein each token is a corresponding character set. The system assigns a corresponding boundary type based on a corresponding boundary type score for each token in the sequence of tokens, based on a begin boundary type or a continue boundary type. The system identifies an entity based on a corresponding entity type score and a corresponding boundary type for each token in the sequence of tokens. The system outputs the sequence of tokens as an identified set of entities based on the identified entity.
-
公开(公告)号：US20160140355A1
公开(公告)日：2016-05-19
申请号：US14548027
申请日：2014-11-19
Applicant: salesforce.com, inc.
Inventor： Arun Jagota , Gregory Haardt , Govardana Sachithanandam Ramachandran , Stanislav Georgiev , Matthew Fuchs Fuchs
CPC classification number: G06F21/6218 , G06F2221/2117
Abstract: User trust scores based on registration features is described. A system identifies registration features associated with a user registered to interact with a database. The system calculates a registration trust score for the user based on a comparison of multiple registration features associated with the user to corresponding registration features associated with previous users who are restricted from interacting with the database and/or corresponding registration features associated with previous users who are enabled to interact with the database. The system restricts the user from interacting with the database if the registration trust score is above a registration threshold.
Abstract translation: 描述基于注册功能的用户信任评分。 系统识别与注册为与数据库交互的用户相关联的注册特征。 该系统基于与用户相关联的多个注册特征与与先前用户相关联的对应注册特征的比较来计算用户的注册信任分数，所述注册特征与被限制在与数据库交互的先前用户和/或与先前用户相关联的相应注册特征 启用与数据库交互。 如果注册信任分数高于注册阈值，则系统限制用户与数据库交互。
-
公开(公告)号：US11481636B2
公开(公告)日：2022-10-25
申请号：US16877325
申请日：2020-05-18
Applicant: salesforce.com, inc.
Inventor： Govardana Sachithanandam Ramachandran , Ka Chun Au , Shashank Harinath , Wenhao Liu , Alexis Roos , Caiming Xiong
Abstract: An embodiment provided herein preprocesses the input samples to the classification neural network, e.g., by adding Gaussian noise to word/sentence representations to make the function of the neural network satisfy Lipschitz property such that a small change in the input does not cause much change to the output if the input sample is in-distribution. Method to induce properties in the feature representation of neural network such that for out-of-distribution examples the feature representation magnitude is either close to zero or the feature representation is orthogonal to all class representations. Method to generate examples that are structurally similar to in-domain and semantically out-of domain for use in out-of-domain classification training. Method to prune feature representation dimension to mitigate long tail error of unused dimension in out-of-domain classification. Using these techniques, the accuracy of both in-domain and out-of-distribution identification can be improved.
-
公开(公告)号：US11436481B2
公开(公告)日：2022-09-06
申请号：US16134957
申请日：2018-09-18
Applicant: salesforce.com, inc.
Inventor： Govardana Sachithanandam Ramachandran , Michael Machado , Shashank Harinath , Linwei Zhu , Yufan Xue , Abhishek Sharma , Jean-Marc Soumet , Bryan McCann
Abstract: A method for natural language processing includes receiving, by one or more processors, an unstructured text input. An entity classifier is used to identify entities in the unstructured text input. The identifying the entities includes generating, using a plurality of sub-classifiers of a hierarchical neural network classifier of the entity classifier, a plurality of lower-level entity identifications associated with the unstructured text input. The identifying the entities further includes generating, using a combiner of the hierarchical neural network classifier, a plurality of higher-level entity identifications associated with the unstructured text input based on the plurality of lower-level entity identifications. Identified entities are provided based on the plurality of higher-level entity identifications.
-
公开(公告)号：US20210150365A1
公开(公告)日：2021-05-20
申请号：US16877325
申请日：2020-05-18
Applicant: salesforce.com, inc.
Inventor： Govardana Sachithanandam Ramachandran , Ka Chun Au , Shashank Harinath , Wenhao Liu , Alexis Roos , Caiming Xiong
Abstract: An embodiment provided herein preprocesses the input samples to the classification neural network, e.g., by adding Gaussian noise to word/sentence representations to make the function of the neural network satisfy Lipschitz property such that a small change in the input does not cause much change to the output if the input sample is in-distribution. Method to induce properties in the feature representation of neural network such that for out-of-distribution examples the feature representation magnitude is either close to zero or the feature representation is orthogonal to all class representations. Method to generate examples that are structurally similar to in-domain and semantically out-of domain for use in out-of-domain classification training. Method to prune feature representation dimension to mitigate long tail error of unused dimension in out-of-domain classification. Using these techniques, the accuracy of both in-domain and out-of-distribution identification can be improved.
-
Patent Agency Ranking
公开(公告)号：US11922303B2
公开(公告)日：2024-03-05
申请号：US16877339
申请日：2020-05-18
Applicant: Salesforce.com, Inc.
Inventor： Wenhao Liu , Ka Chun Au , Shashank Harinath , Bryan McCann , Govardana Sachithanandam Ramachandran , Alexis Roos , Caiming Xiong
Abstract: Embodiments described herein provides a training mechanism that transfers the knowledge from a trained BERT model into a much smaller model to approximate the behavior of BERT. Specifically, the BERT model may be treated as a teacher model, and a much smaller student model may be trained using the same inputs to the teacher model and the output from the teacher model. In this way, the student model can be trained within a much shorter time than the BERT teacher model, but with comparable performance with BERT.
-
公开(公告)号：US20220036884A1
公开(公告)日：2022-02-03
申请号：US17500855
申请日：2021-10-13
Applicant: salesforce.com, inc.
Abstract: Embodiments described herein provide safe policy improvement (SPI) in a batch reinforcement learning framework for a task-oriented dialogue. Specifically, a batch reinforcement learning framework for dialogue policy learning is provided, which improves the performance of the dialogue and learns to shape a reward that reasons the invention behind human response rather than just imitating the human demonstration.
-
公开(公告)号：US20230229957A1
公开(公告)日：2023-07-20
申请号：US17576724
申请日：2022-01-14
Applicant: salesforce.com, inc.
Inventor： Shuyang Li , Yingbo Zhou , Semih Yavuz , Govardana Sachithanandam Ramachandran
IPC: G06N20/00
CPC classification number: G06N20/00
Abstract: Methods, apparatuses, and computer-program products are disclosed. The method may include inputting one or more subcomponent training datasets into the plurality of subcomponent models of the machine learning model, the machine learning model may be configured to perform a final task, and the plurality of subcomponent models may be configured to perform sequential subtasks that result in the final task. The method may include computing one or more weights for data points of the one or more subcomponent training datasets and the one or more weights may be based on a contribution of the data points to an end-to-end error loss measurement associated with performing the final task of the machine learning model. The method may include training the plurality of subcomponent models based on the one or more weights for the data points of the one or more subcomponent training datasets.
-
公开(公告)号：US20210383212A1
公开(公告)日：2021-12-09
申请号：US17105262
申请日：2020-11-25
Applicant: salesforce.com, inc.
Abstract: Embodiments described herein provide safe policy improvement (SPI) in a batch reinforcement learning framework for a task-oriented dialogue. Specifically, a batch reinforcement learning framework for dialogue policy learning is provided, which improves the performance of the dialogue and learns to shape a reward that reasons the invention behind human response rather than just imitating the human demonstration.
-
公开(公告)号：US20160314123A1
公开(公告)日：2016-10-27
申请号：US14695996
申请日：2015-04-24
Applicant: salesforce.com, inc.
Inventor： Govardana Sachithanandam Ramachandran , Hawro Mustafa
CPC classification number: G06F16/24578 , G06F16/81 , G06F17/277 , G06N7/005 , G06N20/00 , G06N20/20
Abstract: Identifying entities in semi-structured content is described. A system assigns a corresponding entity type based on a corresponding entity type score for each token in a sequence of tokens in semi-structured content, based on multiple entity types, wherein each token is a corresponding character set. The system assigns a corresponding boundary type based on a corresponding boundary type score for each token in the sequence of tokens, based on a begin boundary type or a continue boundary type. The system identifies an entity based on a corresponding entity type score and a corresponding boundary type for each token in the sequence of tokens. The system outputs the sequence of tokens as an identified set of entities based on the identified entity.
Abstract translation: 描述半结构化内容中识别实体。 系统基于多个实体类型，在半结构化内容中的令牌序列中基于每个令牌的相应实体类型分数分配对应的实体类型，其中每个令牌是对应的字符集。 基于开始边界类型或继续边界类型，系统基于令牌序列中的每个令牌的相应边界类型分数来分配相应的边界类型。 该系统基于相应的实体类型分数和令牌序列中的每个令牌的对应边界类型来识别实体。 该系统基于所识别的实体将令牌序列作为确定的一组实体输出。
-
-
-
-
-
-
-
-
-
Search Results
17
records
(took 0.018 seconds)
