公开(公告)号：US20250139359A1

公开(公告)日：2025-05-01

申请号：US18943845

申请日：2024-11-11

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：US12204859B2

公开(公告)日：2025-01-21

申请号：US17526832

申请日：2021-11-15

Applicant: Huawei Technologies Co., Ltd. ,  TSINGHUA UNIVERSITY

Inventor： Yasheng Wang ,  Xin Jiang ,  Xiao Chen ,  Qun Liu ,  Zhengyan Zhang ,  Fanchao Qi ,  Zhiyuan Liu

IPC: G06F40/295 ,  G06F40/211 ,  G06F40/30 ,  G06F40/237 ,  G06F40/279 ,  G06F40/284

Abstract: A text processing method, a model training method, and an apparatus related to the field of artificial intelligence is provided. The method includes: obtaining target knowledge data; processing the target knowledge data to obtain a target knowledge vector; processing to-be-processed text to obtain a target text vector; fusing the target text vector and the target knowledge vector based on a target fusion model, to obtain a fused target text vector and a fused target knowledge vector; and processing the fused target text vector and/or the fused target knowledge vector based on a target processing model, to obtain a processing result corresponding to a target task. The foregoing technical solution can improve accuracy of a result of processing a target task by the target processing model.

公开(公告)号：US12131128B2

公开(公告)日：2024-10-29

申请号：US17479420

申请日：2021-09-20

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Meng Zhang ,  Qun Liu ,  Xin Jiang

IPC: G06F40/58

CPC classification number: G06F40/58

Abstract: A translation quality detection method includes obtaining a source text and a machine translation of the source text. The machine translation is obtained after a machine translation system translates the source text. The method also includes determining a translation quality of the machine translation based on the source text, the machine translation, and an application scenario of the machine translation.

公开(公告)号：US11734319B2

公开(公告)日：2023-08-22

申请号：US16544267

申请日：2019-08-19

Applicant: Huawei Technologies Co., Ltd.

Inventor： Xin Jiang ,  Hang Li

IPC: G06F16/332 ,  G10L15/06 ,  G10L15/197 ,  G10L15/22

CPC classification number: G06F16/3329 ,  G10L15/063 ,  G10L15/197 ,  G10L15/22 ,  G10L2015/0636 ,  G10L2015/225

Abstract: A question answering method includes obtaining target question information; determining a candidate question and answer pair based on the target question information; calculating a confidence of answer information in the candidate question and answer pair, where the confidence is used to indicate a probability that question information in the candidate question and answer pair belongs to an answer database or an adversarial database; determining whether the confidence is less than a first preset threshold; and when the confidence is less than the first preset threshold, outputting information indicating incapable of answering.

公开(公告)号：US20220004721A1

公开(公告)日：2022-01-06

申请号：US17479420

申请日：2021-09-20

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Meng Zhang ,  Qun Liu ,  Xin Jiang

IPC: G06F40/58

Abstract: A translation quality detection method includes obtaining a source text and a machine translation of the source text. The machine translation is obtained after a machine translation system translates the source text. The method also includes determining a translation quality of the machine translation based on the source text, the machine translation, and an application scenario of the machine translation.

公开(公告)号：US20190303768A1

公开(公告)日：2019-10-03

申请号：US16444618

申请日：2019-06-18

Applicant: Huawei Technologies Co., Ltd.

Inventor： Xi Zhang ,  Lin Ma ,  Xin Jiang ,  Hang Li

IPC: G06N5/02 ,  G06N20/00

Abstract: A community question answering-based article recommendation system, user device, and method includes obtaining text information of a question for a target article; constructing 2-tuple information using the text information of the question and modal content information of each of a plurality of preset articles in a preset article set; inputting each piece of 2-tuple information into a preset matching model; calculating, with reference to a preset matching model parameter, a score of matching between each preset article and the question; and outputting an article recommendation list for the question for the target article based on the scores of matching between the plurality of preset articles and the question for the target article.

公开(公告)号：US11640515B2

公开(公告)日：2023-05-02

申请号：US15993619

申请日：2018-05-31

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Xin Jiang ,  Zhengdong Lu ,  Hang Li

IPC: G06N3/00 ,  G06N3/04 ,  G06F16/332 ,  G06N3/08 ,  G06F40/30 ,  G06F40/216 ,  G06N3/006 ,  G06N3/084

Abstract: A method and neural network system for human-computer interaction, and user equipment are disclosed. According to the method for human-computer interaction, a natural language question and a knowledge base are vectorized, and an intermediate result vector that is based on the knowledge base and that represents a similarity between a natural language question and a knowledge base answer is obtained by means of vector calculation, and then a fact-based correct natural language answer is obtained by means of calculation according to the question vector and the intermediate result vector. By means of this method, a dialog and knowledge base-based question-answering are combined by means of vector calculation, so that natural language interaction can be performed with a user, and a fact-based correct natural language answer can be given according to the knowledge base.

公开(公告)号：US11080347B2

公开(公告)日：2021-08-03

申请号：US16292992

申请日：2019-03-05

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Dawei Huo ,  Li Qian ,  Xin Jiang

IPC: G06F16/95 ,  G06F16/9532 ,  H04L29/08 ,  G06F16/9032 ,  G06F16/9538 ,  G06F17/18

Abstract: Sending a search request includes: during a running procedure of a search engine client, generating a forged search request, where the forged search request carries a forged search word; and sending the forged search request to the search engine server. The forged search request is sent to the search engine server, to serve as a factor interfering with an analysis of a user behavior by the search engine server based on a true search request, to prevent the search engine server from analyzing the user behavior based on a search word entered by a user, thereby improving user experience.

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：US20220215159A1

公开(公告)日：2022-07-07

申请号：US17701775

申请日：2022-03-23

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Lihua Qian ,  Yinpeng Guo ,  Lin Qiu ,  Weinan Zhang ,  Xin Jiang ,  Yong Yu

IPC: G06F40/166 ,  G06F40/20 ,  G06F40/40

Abstract: This disclosure relates to a natural language processing technology, and provides a sentence paraphrase method and apparatus. The method includes: paraphrasing an input sentence by using a sentence paraphrase model, to generate a plurality of candidate paraphrased sentences; and determining a similarity between each of the plurality of candidate paraphrased sentences and the input sentence, to obtain an output sentence whose similarity to the input sentence is greater than or equal to a preset threshold, where each of a plurality of paraphrased sentence generators in the sentence paraphrase model includes one neural network, the plurality of paraphrased sentence generators are trained by using source information and similarity information as a first reward, and the paraphrased sentence is obtained by paraphrasing the training sentence by using the plurality of paraphrased sentence generators. In the sentence paraphrase method, diversity of a paraphrased sentence and quality of the paraphrased sentence can be improved.