-
公开(公告)号：US20230073835A1
公开(公告)日：2023-03-09
申请号：US17900126
申请日：2022-08-31
Applicant: Samsung Electronics Co., Ltd.
Inventor： Miao Yin , Burak Uzkent , Yilin Shen , Hongxia Jin
IPC: G06V10/70 , G06V10/774 , G06V10/776 , G06V10/74
Abstract: In one embodiment, a method includes accessing a batch B of a plurality of images, wherein each image in the batch is part of a training set of images used to train a vision transformer comprising a plurality of attention heads. The method further includes determining, for each attention head A, a similarity between (1) the output of the attention head evaluated using each image in the batch and the (2) output of each attention head evaluated using each image in the batch. The method further includes determining, based on the determined similarities, an importance score for each attention head; and pruning, based on the importance scores, one or more attention heads from the vision transformer.
-
62.发明授权公开(公告)号：US11501753B2
公开(公告)日：2022-11-15
申请号：US16728672
申请日：2019-12-27
Applicant: Samsung Electronics Co., Ltd.
Inventor： Yilin Shen , Avik Ray , Hongxia Jin
Abstract: A method includes receiving, from an electronic device, information defining a user utterance associated with a skill to be performed, where the skill is not recognized by a natural language understanding (NLU) engine. The method also includes receiving, from the electronic device, information defining one or more actions for performing the skill. The method further includes identifying, using at least one processor, one or more known skills having one or more slots that map to at least one word or phrase in the user utterance. The method also includes creating, using the at least one processor, a plurality of additional utterances based on the one or more mapped slots. In addition, the method includes training, using the at least one processor, the NLU engine using the plurality of additional utterances.
-
公开(公告)号：US11423225B2
公开(公告)日：2022-08-23
申请号：US16946746
申请日：2020-07-02
Applicant: Samsung Electronics Co., Ltd.
Inventor： Yilin Shen , Xiangyu Zeng , Hongxia Jin
IPC: G10L15/16 , G06F40/30 , G06N3/04 , G06F40/279
Abstract: A method includes obtaining, using at least one processor of an electronic device, a base model trained to perform natural language understanding. The method also includes generating, using the at least one processor, a first model expansion based on knowledge from the base model. The method further includes training, using the at least one processor, the first model expansion based on first utterances without modifying parameters of the base model. The method also includes receiving, using the at least one processor, an additional utterance from a user. In addition, the method includes determining, using the at least one processor, a meaning of the additional utterance using the base model and the first model expansion.
-
公开(公告)号：US11410220B2
公开(公告)日：2022-08-09
申请号：US16814241
申请日：2020-03-10
Applicant: Samsung Electronics Co., Ltd.
Inventor： Tong Yu , Yilin Shen , Hongxia Jin
Abstract: Described is a system for providing improved exploration for an interactive recommendation system by leveraging intuitive user feedback. The recommendation system may provide images of recommend items and receive user feedback preferences in the form of a natural language expression. Traditional techniques for interactive recommendation systems typically rely on restricted forms of user feedback such as binary relevance responses, or feedback based on a fixed set of relative attributes. In contrast, the recommendation system described herein introduces a new approach to interactive image recommendation (or image search) that enables users to provide feedback via natural language, allowing for a more natural and effective interaction. The recommendation system may be based on formulating the task of natural-language-based interactive image recommendation as a reinforcement learning problem, and reward the recommendation system for improving the rank of the target image during each iterative interaction.
-
65.发明申请公开(公告)号：US20220199070A1
公开(公告)日：2022-06-23
申请号：US17402045
申请日：2021-08-13
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： Yen-Chang Hsu , Yilin Shen , Avik Ray , Hongxia JIN
Abstract: An apparatus for detecting unsupported utterances in natural language understanding, includes a memory storing instructions, and at least one processor configured to execute the instructions to classify a feature that is extracted from an input utterance of a user, as one of in-domain and out-of-domain (OOD) for a response to the input utterance, obtain an OOD score of the extracted feature, and identify whether the feature is classified as OOD. The at least one processor is further configured to executed the instructions to, based on the feature being identified to be classified as in-domain, identify whether the obtained OOD score is greater than a predefined threshold, and based on the OOD score being identified to be greater than the predefined threshold, re-classify the feature as OOD.
-
Patent Agency Ranking
公开(公告)号：US20220114479A1
公开(公告)日：2022-04-14
申请号：US17090542
申请日：2020-11-05
Applicant: Samsung Electronics Co., Ltd.
Inventor： Changsheng Zhao , Yilin Shen , Hongxia Jin
Abstract: A machine learning method using a trained machine learning model residing on an electronic device includes receiving an inference request by the electronic device. The method also includes determining, using the trained machine learning model, an inference result for the inference request using a selected inference path in the trained machine learning model. The selected inference path is selected based on a highest probability for each layer of the trained machine learning model. A size of the trained machine learning model is reduced corresponding to constraints imposed by the electronic device. The method further includes executing an action in response to the inference result.
-
公开(公告)号：US11094317B2
公开(公告)日：2021-08-17
申请号：US16404012
申请日：2019-05-06
Applicant: Samsung Electronics Co., Ltd.
Inventor： Yilin Shen , Xiangyu Zeng , Yu Wang , Hongxia Jin
IPC: G10L15/22 , G10L15/18 , G10L15/06 , G10L15/183 , G10L15/16
Abstract: An electronic device for training a machine learning model includes at least one memory and at least one processor coupled to the at least one memory. The at least one processor is configured to train a classification layer of the model. To train the classification layer, the at least one processor is configured to receive, by the classification layer, one or more language contexts from an utterance encoder layer and to classify, by the classification layer, at least one portion of an utterance into an information type among a plurality of information types. The at least one processor may be further configured to jointly train a slot filling layer and an intent detection layer of the model.
-
公开(公告)号：US20200257962A1
公开(公告)日：2020-08-13
申请号：US16273973
申请日：2019-02-12
Applicant: Samsung Electronics Co., Ltd.
Inventor： Yue Deng , KaWai Chen , Yilin Shen , Hongxia Jin
Abstract: Systems and methods are described for converting input content. A first model may convert input content to an output content that exhibits one or more desired properties. A second model may determine if the conversion meets a desired quality of conversion using a discriminating function. The discriminating function may determine a difference between properties of the output content and properties of desired content, where the difference corresponds to the success of the conversion applying the desired properties. Updated control data may be generated by a third model using information from the second model, where the updated control data may be used by the first model to reduce the determined difference. After updated control data has been generated, the foregoing steps may be repeated based upon the updated control data. One of a plurality of different actions may be determined in response to the difference.
-
公开(公告)号：US20200043480A1
公开(公告)日：2020-02-06
申请号：US16404012
申请日：2019-05-06
Applicant: Samsung Electronics Co., Ltd.
Inventor： Yilin Shen , Xiangyu Zeng , Yu Wang , Hongxia Jin
IPC: G10L15/18 , G10L15/06 , G10L15/183 , G10L15/22
Abstract: An electronic device for training a machine learning model includes at least one memory and at least one processor coupled to the at least one memory. The at least one processor is configured to train a classification layer of the model. To train the classification layer, the at least one processor is configured to receive, by the classification layer, one or more language contexts from an utterance encoder layer and to classify, by the classification layer, at least one portion of an utterance into an information type among a plurality of information types. The at least one processor may be further configured to jointly train a slot filling layer and an intent detection layer of the model.
-
公开(公告)号：US20190354578A1
公开(公告)日：2019-11-21
申请号：US16236886
申请日：2018-12-31
Applicant: Samsung Electronics Co., Ltd.
Inventor： Yilin Shen , Avik Ray , Hongxia Jin
Abstract: A system receives a phrase that includes at least one tagged object and generates instantiated phrases by instantiations of each tagged object in the phrase. The system generates lists of natural language phrases by corresponding paraphrases of each of the instantiated phrases. The system generates ordered lists of natural language phrases by ordering natural language phrases in each list of natural language phrases based on occurrences of each natural language phrase. The system generates annotated natural language phrases by using each tagged object in the phrase to annotate the ordered lists of natural language phrases or an enhanced set of natural language phrases that is based on the ordered lists of natural language phrases.
-
-
-
-
-
-
-
-
-
Search Results
74
records
(took 0.033 seconds)
