Patents by Inventor Shuohuan WANG
Shuohuan WANG has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11995405Abstract: The present disclosure provides a multi-lingual model training method, apparatus, electronic device and readable storage medium and relates to the technical field of deep learning and natural language processing. A technical solution of the present disclosure when training the multi-lingual model is: obtaining training corpuses comprising a plurality of bilingual corpuses and a plurality of monolingual corpuses; training a multi-lingual model with a first training task by using the plurality of bilingual corpuses; training the multi-lingual model with a second training task by using the plurality of monolingual corpuses; and completing the training of the multi-lingual model in a case of determining that loss functions of the first training task and second training task converge.Type: GrantFiled: June 15, 2021Date of Patent: May 28, 2024Assignee: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.Inventors: Xuan Ouyang, Shuohuan Wang, Chao Pang, Yu Sun, Hao Tian, Hua Wu, Haifeng Wang
-
Patent number: 11914964Abstract: The present application discloses a method and apparatus for training a semantic representation model, a device and a computer storage medium, which relates to the field of natural language processing technologies in artificial intelligence.Type: GrantFiled: March 22, 2021Date of Patent: February 27, 2024Assignee: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.Inventors: Shuohuan Wang, Jiaxiang Liu, Xuan Ouyang, Yu Sun, Hua Wu, Haifeng Wang
-
Publication number: 20230252354Abstract: A method for pre-training a language model includes: constructing a pre-training language data set, in which the pre-training language data set comprises unsupervised language data and supervised language data; generating a hierarchical multi-template and multi-task language data set based on the pre-training language data set; and pre-training the language model based on the hierarchical multi-template and multi-task language data set.Type: ApplicationFiled: March 7, 2023Publication date: August 10, 2023Inventors: Junyuan SHANG, Shuohuan WANG, Siyu DING, Yanbin ZHAO, Chao PANG, Yu SUN, Hao TIAN, Hua WU, Haifeng WANG
-
Publication number: 20230222344Abstract: A method for determining a prompt vector of a pre-trained model, includes: obtaining a first one of prompt vectors and a first vector corresponding to sample data; obtaining N pruned models by N different pruning processing on the pre-trained model, where N is any integer greater than 1; obtaining a first score corresponding to the first one of the prompt vectors by fusing the first vector and the first one of the prompt vectors and inputting the fused first vector and first one of the prompt vectors into the N pruned models respectively; determining a second one of the prompt vectors by modifying, based on the first score, the first one of the prompt vectors; and based on the second one of the prompt vectors, returning to obtaining the first score until determining a target prompt vector corresponding to the sample data.Type: ApplicationFiled: March 8, 2023Publication date: July 13, 2023Inventors: Yekun Chai, Shuohuan Wang, Yu Sun
-
Publication number: 20230206080Abstract: A model training system includes at least one first cluster and a second cluster communicating with the at least first cluster. The at least one first cluster is configured to acquire a sample data set, generate training data according to the sample data set, and send the training data to the second cluster; and the second cluster is configured to train a pre-trained model according to the training data sent by the at least one first cluster.Type: ApplicationFiled: March 7, 2023Publication date: June 29, 2023Inventors: Shuohuan WANG, Weibao GONG, Zhihua WU, Yu SUN, Siyu DING, Yaqian HAN, Yanbin ZHAO, Yuang LIU, Dianhai YU
-
Patent number: 11687718Abstract: A method, an apparatus, a device and a storage medium for learning a knowledge representation are provided. The method can include: sampling a sub-graph of a knowledge graph from a knowledge base; serializing the sub-graph of the knowledge graph to obtain a serialized text; and reading using a pre-trained language model the serialized text in an order in the sub-graph of the knowledge graph, to perform learning to obtain a knowledge representation of each word in the serialized text. The knowledge representation learning in this embodiment is performed for entity and relationship representation learning in the knowledge base.Type: GrantFiled: December 9, 2020Date of Patent: June 27, 2023Assignee: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.Inventors: Chao Pang, Shuohuan Wang, Yu Sun, Hua Wu, Haifeng Wang
-
Patent number: 11663404Abstract: The disclosure provides a text recognition method, an electronic device, and a storage medium. The method includes: obtaining N segments of a sample text; inputting each of the N segments into a preset initial language model in sequence, to obtain first text vector information corresponding to the N segments; inputting each of the N segments into the initial language model in sequence again, to obtain second text vector information corresponding to a currently input segment; in response to determining that the currently input segment has the mask, predicting the mask according to the second text vector information and the first text vector information to obtain a predicted word at a target position corresponding to the mask; training the initial language model according to an original word and the predicted word to generate a long text language model; and recognizing an input text through the long text language model.Type: GrantFiled: November 23, 2020Date of Patent: May 30, 2023Assignee: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.Inventors: Shuohuan Wang, Siyu Ding, Yu Sun, Hua Wu, Haifeng Wang
-
Publication number: 20230080904Abstract: A method for generating a cross-lingual textual semantic model includes: acquiring a set of training data that includes pieces of monolingual non-parallel text and pieces of bilingual parallel text; determining a semantic vector of each piece of text in the set of training data by inputting each piece of text into an initial textual semantic model; determining a distance between semantic vectors of each two pieces of text in the set of training data based on the semantic vector of each piece of text in the set of training data; determining a gradient modification based on a parallel relationship between each two pieces of text in the set of training data and the distance between the semantic vectors of each two pieces of text in the set of training data; and acquiring a modified textual semantic model by modifying the initial textual semantic model based on the gradient modification.Type: ApplicationFiled: November 11, 2022Publication date: March 16, 2023Inventors: Yaqian HAN, Shuohuan WANG, Yu SUN
-
Publication number: 20230040095Abstract: A method and apparatus for pre-training a model, a device, a storage medium, and a program product. An embodiment of the method includes: acquiring a sample natural language text; generating N types of prompt words based on the sample natural language text, where N is a positive integer; generating sample input data based on the sample natural language text and the N types of prompt words; and training an initial language model based on the sample input data, to obtain a pre-trained language model.Type: ApplicationFiled: August 16, 2022Publication date: February 9, 2023Inventors: Junyuan SHANG, Shuohuan WANG, Siyu DING, Yanbin ZHAO, Chao PANG, Yu Sun
-
Patent number: 11520991Abstract: The present disclosure provides a method, apparatus, electronic device and storage medium for processing a semantic representation model, and relates to the field of artificial intelligence technologies. A specific implementation solution is: collecting a training corpus set including a plurality of training corpuses; training the semantic representation model using the training corpus set based on at least one of lexicon, grammar and semantics. In the present disclosure, by building the unsupervised or weakly-supervised training task at three different levels, namely, lexicon, grammar and semantics, the semantic representation model is enabled to learn knowledge at levels of lexicon, grammar and semantics from massive data, enhance the capability of universal semantic representation and improve the processing effect of the NLP task.Type: GrantFiled: May 28, 2020Date of Patent: December 6, 2022Assignee: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.Inventors: Yu Sun, Haifeng Wang, Shuohuan Wang, Yukun Li, Shikun Feng, Hao Tian, Hua Wu
-
Publication number: 20220327290Abstract: There is provided a method of training a feature determination model, which relates to a field of deep learning and natural language processing. The method is implemented to include: determining, by a plurality of feature determination layers arranged in stages, a feature vector for each segment in a pre-training text; and pre-training the feature determination model according to the feature vector. A current stage feature vector is determined by a feature determination layer of a current stage according to a preceding segment feature vector determined for a preceding segment, and a preceding stage feature vector determined by a feature determination layer of a preceding stage. A method of training a feature determination model for a target task, a method of performing semantic analysis for a target task, an electronic device, and a computer storage medium are also provided.Type: ApplicationFiled: June 29, 2022Publication date: October 13, 2022Inventors: Junyuan SHANG, Shuohuan WANG, Siyu DING
-
Publication number: 20220293092Abstract: The present application provides a method of training a natural language processing model, which relates to a field of artificial intelligence, and in particular to a field of natural language processing. A specific implementation scheme includes: performing a semantic learning for multi-tasks on an input text, so as to obtain a semantic feature for the multi-tasks, wherein the multi-tasks include a plurality of branch tasks; performing a feature learning for each branch task based on the semantic feature, so as to obtain a first output result for each branch task; calculating a loss for each branch task according to the first output result for the branch task; and adjusting a parameter of the natural language processing model according to the loss for each branch task. The present application further provides a method of processing a natural language, an electronic device, and a storage medium.Type: ApplicationFiled: May 31, 2022Publication date: September 15, 2022Inventors: Siyu DING, Chao PANG, Shuohuan WANG, Yanbin ZHAO, Junyuan SHANG, Yu SUN, Shikun FENG, Hao TIAN, Hua WU, Haifeng WANG
-
Patent number: 11403468Abstract: A method for generating a vector representation of a text includes dividing the text into text segments. Each text segment is represented as a segment vector corresponding to the respective text segment by employing a first-level semantic model. The segment vector is configured to indicate a semantics of the text segment. Text semantics recognition is performed on the segment vector of each text segment by employing a second-level semantic model to obtain a text vector for indicating a topic of the text.Type: GrantFiled: July 27, 2020Date of Patent: August 2, 2022Assignee: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.Inventors: Chao Pang, Shuohuan Wang, Yu Sun, Zhi Li
-
Publication number: 20220198327Abstract: The present disclosure provides a method, apparatus, device and storage medium for training a dialogue understanding model, and relates to technical field of computers, and specifically to the technical field of artificial intelligence such as natural language processing and deep learning. The method for training a dialogue understanding model includes: obtaining dialogue understanding training data; performing joint training for a dialogue understanding pre-training task and a general pre-training task by using the dialogue understanding training data, to obtain a dialogue understanding model. According to the present disclosure, a model specially adapted for a dialogue understanding task may be obtained by training.Type: ApplicationFiled: June 15, 2021Publication date: June 23, 2022Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.Inventors: Shuohuan WANG, Chao PANG, Yu SUN
-
Publication number: 20220171941Abstract: The present disclosure provides a multi-lingual model training method, apparatus, electronic device and readable storage medium and relates to the technical field of deep learning and natural language processing. A technical solution of the present disclosure when training the multi-lingual model is: obtaining training corpuses comprising a plurality of bilingual corpuses and a plurality of monolingual corpuses; training a multi-lingual model with a first training task by using the plurality of bilingual corpuses; training the multi-lingual model with a second training task by using the plurality of monolingual corpuses; and completing the training of the multi-lingual model in a case of determining that loss functions of the first training task and second training task converge.Type: ApplicationFiled: June 15, 2021Publication date: June 2, 2022Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.Inventors: Xuan OUYANG, Shuohuan WANG, Chao PANG, Yu SUN, Hao TIAN, Hua WU, Haifeng WANG
-
Publication number: 20220129753Abstract: A pre-training method of a neural network model, an electronic device, and a medium. The pre-training data is inputted to the initial neural network model, and the initial neural network model is pre-trained in the first training mode, in the first training mode, the plurality of hidden layers share one hidden layer parameter, and the loss value of the initial neural network model is obtained, if the loss value of the initial neural network model is less than a preset threshold, the initial neural network model continues to be pre-trained in the second training mode, in the second training mode, each of the plurality of hidden layers has its own hidden layer parameter.Type: ApplicationFiled: January 11, 2022Publication date: April 28, 2022Inventors: Yuxiang LU, Jiaxiang LIU, Xuyi CHEN, Shikun FENG, Shuohuan WANG, Yu SUN, Shiwei HUANG, Jingzhou HE
-
Patent number: 11232140Abstract: Embodiments of the present disclosure disclose a method and apparatus for processing information. A specific implementation of the method includes: acquiring a search result set related to a search statement inputted by a user; parsing the search statement to generate a first syntax tree, and parsing a search result in the search result set to generate a second syntax tree set; calculating a similarity between the search statement and the search result in the search result set using a pre-trained semantic matching model on the basis of the first syntax tree and the second syntax tree set, the semantic matching model being used to determine the similarity between the syntax trees; and sorting the search result in the search result set on the basis of the similarity between the search statement and the search result in the search result set, and pushing the sorted search result set to the user.Type: GrantFiled: August 3, 2018Date of Patent: January 25, 2022Assignee: Beijing Baidu Netcom Science and Technology Co., Ltd.Inventors: Shuohuan Wang, Yu Sun, Dianhai Yu
-
Publication number: 20220019743Abstract: Technical solutions relate to the natural language processing field based on artificial intelligence. According to an embodiment, a multilingual semantic representation model is trained using a plurality of training language materials represented in a plurality of languages respectively, such that the multilingual semantic representation model learns the semantic representation capability of each language; a corresponding mixed-language language material is generated for each of the plurality of training language materials, and the mixed-language language material includes language materials in at least two languages; and the multilingual semantic representation model is trained using each mixed-language language material and the corresponding training language material, such that the multilingual semantic representation model learns semantic alignment information of different languages.Type: ApplicationFiled: May 12, 2021Publication date: January 20, 2022Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.Inventors: Xuan OUYANG, Shuohuan WANG, Yu SUN
-
Publication number: 20220019736Abstract: The present application discloses a method and apparatus for training a natural language processing model, a device and a storage medium, which relates to the natural language processing field based on artificial intelligence. An implementation includes: constructing training language material pairs of a coreference resolution task based on a preset language material set, wherein each training language material pair includes a positive sample and a negative sample; training the natural language processing model with the training language material pair to enable the natural language processing model to learn the capability of recognizing corresponding positive samples and negative samples; and training the natural language processing model with the positive samples of the training language material pairs to enable the natural language processing model to learn the capability of the coreference resolution task.Type: ApplicationFiled: March 24, 2021Publication date: January 20, 2022Inventors: Xuan Ouyang, Shuohuan Wang, Yu Sun
-
Publication number: 20220004716Abstract: The present application discloses a method and apparatus for training a semantic representation model, a device and a computer storage medium, which relates to the field of natural language processing technologies in artificial intelligence.Type: ApplicationFiled: March 22, 2021Publication date: January 6, 2022Inventors: Shuohuan Wang, Jiaxiang Liu, Xuan Ouyang, Yu Sun, Hua Wu, Haifeng Wang