-
公开(公告)号：US20220147848A1
公开(公告)日：2022-05-12
申请号：US17577713
申请日：2022-01-18
Applicant: Huawei Technologies Co., Ltd.
Inventor： Lifeng Shang , Zhengdong Lu , Hang LI
Abstract: A method includes: obtaining a text entered by a user; determining at least one topic related to the text; determining a target dialogue robot from the plurality of dialogue robots based on the at least one topic related to the text and a predefined mapping relationship between a dialogue robot and a topic, where a target topic corresponding to the target dialogue robot is some or all of the at least one topic related to the text; allocating the text to the target dialogue robot; and obtaining a reply for the text from the target dialogue robot, where the reply is generated by the target dialogue robot based on at least one semantic understanding of the text.
-
公开(公告)号：US20200250377A1
公开(公告)日：2020-08-06
申请号：US16856450
申请日：2020-04-23
Applicant: Huawei Technologies Co., Ltd.
Inventor： Xin Jiang , Lifeng Shang , Hang Li , Zichao Li
IPC: G06F40/289
Abstract: A paraphrase sentence generation method and apparatus relating to the research field of natural language processing include generating m second sentences based on a first sentence and a paraphrase generation model, determining a matching degree between each of the m second sentences and the first sentence based on a paraphrase matching model, and determining n second sentences from the m second sentences based on matching degrees among the m second sentences and the first sentence, where the paraphrase generation model is obtained through reinforcement learning-based training based on a reward of the paraphrase matching model.
-
公开(公告)号：US11308405B2
公开(公告)日：2022-04-19
申请号：US16514683
申请日：2019-07-17
Applicant: Huawei Technologies Co., Ltd.
Inventor： Lifeng Shang , Zhengdong Lu , Hang Li
Abstract: An apparatus is pre-equipped with a plurality of dialogue robots, and each dialogue robot is configured to conduct a human-computer dialogue based on at least one topic. The method includes: obtaining a text entered by a user; determining at least one topic related to the text, and determining a target dialogue robot from the plurality of dialogue robots based on the at least one topic related to the text and a predefined mapping relationship between a dialogue robot and a topic, where a target topic corresponding to the target dialogue robot is some or all of the at least one topic related to the text; and allocating the text to the target dialogue robot and obtaining a reply for the text from the target dialogue robot, where the reply is generated by the target dialogue robot based on at least one semantic understanding of the text.
-
公开(公告)号：US11132516B2
公开(公告)日：2021-09-28
申请号：US16396172
申请日：2019-04-26
Applicant: Huawei Technologies Co., Ltd.
Inventor： Zhaopeng Tu , Lifeng Shang , Xiaohua Liu , Hang Li
Abstract: A sequence conversion method includes receiving a source sequence, converting the source sequence into a source vector representation sequence, obtaining at least two candidate target sequences and a translation probability value of each of the at least two candidate target sequences according to the source vector representation sequence, adjusting the translation probability value of each candidate target sequence, selecting an output target sequence from the at least two candidate target sequences according to an adjusted translation probability value of each candidate target sequence, and outputting the output target sequence. Hence, loyalty of a target sequence to a source sequence can be improved during sequence conversion.
-
公开(公告)号：US20220180202A1
公开(公告)日：2022-06-09
申请号：US17682145
申请日：2022-02-28
Applicant: HUAWEI TECHNOLOGIES CO., LTD.
Inventor： Yichun Yin , Lifeng Shang , Xin Jiang , Xiao Chen
IPC: G06N3/08 , G06N3/04 , G06F40/30 , G06F40/166 , G06F40/279
Abstract: A text processing model training method, and a text processing method and apparatus in the natural language processing field in the artificial intelligence field are disclosed. The training method includes: obtaining training text; separately inputting the training text into a teacher model and a student model to obtain sample data output by the teacher model and prediction data output by the student model; the sample data includes a sample semantic feature and a sample label; the prediction data includes a prediction semantic feature and a prediction label; and the teacher model is a pre-trained language model used for text classification; and training a model parameter of the student model based on the sample data and the prediction data, to obtain a target student model. The method enables the student model to effectively perform knowledge transfer, thereby improving accuracy of a text processing result of the student model.
-
Patent Agency Ranking
公开(公告)号：US20200264923A1
公开(公告)日：2020-08-20
申请号：US16868970
申请日：2020-05-07
Applicant: Huawei Technologies Co., Ltd.
Inventor： Zhefeng Yan , Lifeng Shang , Tao Cai , Li Qian
IPC: G06F9/48
Abstract: An information processing method includes receiving first request information entered by a user, determining a first task engine for the first request information, where a first slot is set in the first task engine, extracting key information from the first request information based on the first slot, and if the key information fails to be extracted from the first request information based on the first slot, or if the key information is extracted from the first request information based on the first slot, but the extracted key information does not meet a condition, obtaining target key information from a shared parameter list of the user.
-
公开(公告)号：US20190251178A1
公开(公告)日：2019-08-15
申请号：US16396172
申请日：2019-04-26
Applicant: Huawei Technologies Co., Ltd.
Inventor： Zhaopeng Tu , Lifeng Shang , Xiaohua Liu , Hang Li
CPC classification number: G06F17/289 , G06F17/27 , G06F17/28 , G06F17/2818 , G06N3/02 , G06N3/08
Abstract: A sequence conversion method includes receiving a source sequence, converting the source sequence into a source vector representation sequence, obtaining at least two candidate target sequences and a translation probability value of each of the at least two candidate target sequences according to the source vector representation sequence, adjusting the translation probability value of each candidate target sequence, selecting an output target sequence from the at least two candidate target sequences according to an adjusted translation probability value of each candidate target sequence, and outputting the output target sequence. Hence, loyalty of a target sequence to a source sequence can be improved during sequence conversion.
-
公开(公告)号：US12182507B2
公开(公告)日：2024-12-31
申请号：US17682145
申请日：2022-02-28
Applicant: HUAWEI TECHNOLOGIES CO., LTD.
Inventor： Yichun Yin , Lifeng Shang , Xin Jiang , Xiao Chen
IPC: G06F40/216 , G06F40/166 , G06F40/279 , G06F40/30 , G06N3/045 , G06N3/084
Abstract: A text processing model training method, and a text processing method and apparatus in the natural language processing field in the artificial intelligence field are disclosed. The training method includes: obtaining training text; separately inputting the training text into a teacher model and a student model to obtain sample data output by the teacher model and prediction data output by the student model; the sample data includes a sample semantic feature and a sample label; the prediction data includes a prediction semantic feature and a prediction label; and the teacher model is a pre-trained language model used for text classification; and training a model parameter of the student model based on the sample data and the prediction data, to obtain a target student model. The method enables the student model to effectively perform knowledge transfer, thereby improving accuracy of a text processing result of the student model.
-
公开(公告)号：US20240185086A1
公开(公告)日：2024-06-06
申请号：US18443052
申请日：2024-02-15
Applicant: HUAWEI TECHNOLOGIES CO., LTD.
Inventor： Lu HOU , Haoli Bai , Lifeng Shang , Xin Jiang , Li Qian
Abstract: This disclosure relates to the field of artificial intelligence, and provides model distillation methods and apparatuses. In an implementation, a method including: obtaining first input data and second input data from a second computing node, wherein the first input data is output data of the third sub-model, and the second input data is output data processed by the fourth sub-model, processing the first input data by using the first sub-model, to obtain a first intermediate output, processing the second input data by using the second sub-model, to obtain a second intermediate output, wherein the first intermediate output and the second intermediate output are used to determine a first gradient, and distilling the first sub-model based on the first gradient, to obtain an updated first sub-model.
-
公开(公告)号：US20240127000A1
公开(公告)日：2024-04-18
申请号：US17958080
申请日：2022-09-30
Applicant: HUAWEI TECHNOLOGIES CO., LTD.
Inventor： Yichun Yin , Lifeng Shang , Cheng Chen , Xin Jiang , Xiao Chen , Qun Liu
Abstract: A computer-implemented method is provided for model training performed by a processing system. The method comprises determining a set of first weights based on a first matrix associated with a source model, determining a set of second weights based on the set of first weights, forming a second matrix associated with a target model based on the set of first weights and the set of second weights, initializing the target model based on the second matrix, and training the target model.
-
-
-
-
-
-
-
-
-
Search Results
16
records
(took 0.015 seconds)
