Patents by Inventor Xinyan Xiao
Xinyan Xiao 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).
-
Publication number: 20220179889Abstract: The disclosure provides a method for generating a query statement. The method includes: determining a first vector representation based on known nodes in a first syntax tree corresponding to a query statement to be generated; determining a target generation strategy corresponding to a target node to be generated based on the first vector representation and a preset copy reference matrix; generating the target node based on the first vector representation or a second vector representation by performing the target generation strategy, in which the second vector representation is a vector representation corresponding to an adjacent query statement prior to the query statement to be generated; and generating the query statement based on the known nodes and a terminator in response to the target node being the terminator.Type: ApplicationFiled: February 24, 2022Publication date: June 9, 2022Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.Inventors: Ao ZHANG, Lijie WANG, Xinyan XIAO, Tingting LI
-
Patent number: 11341366Abstract: A cross-modality processing method is related to a field of natural language processing technologies. The method includes: obtaining a sample set, wherein the sample set includes a plurality of corpus and a plurality of images; generating a plurality of training samples according to the sample set, in which each of the plurality of the training samples is a combination of at least one of the plurality of the corpus and at least one of the plurality of the images corresponding to the at least one of the plurality of the corpus; adopting the plurality of the training samples to train a semantic model, so that the semantic model learns semantic vectors containing combinations of the corpus and the images.Type: GrantFiled: August 10, 2020Date of Patent: May 24, 2022Assignee: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.Inventors: Guocheng Niu, Bolei He, Xinyan Xiao
-
Publication number: 20220092252Abstract: A method for generating a summary, an electronic device and a storage medium thereof, which relate to the natural language processing field, the deep learning field and the knowledge graph field, are disclosed. The method may include: acquiring a knowledge graph corresponding to a text to be processed, in the graph, nodes represent semantic concepts, and sides represent semantic relationships among the semantic concepts; encoding the text at a token level to obtain a context encoded representation of each token; determining an initial representation of each node in the knowledge graph according to the context encoded representation of each token; performing an encoding operation according to the initial representation of each node and the connection relationships among the nodes to obtain a node representation of each node; and performing a decoding operation according to the node representation of each node to obtain the summary of the text to be processed.Type: ApplicationFiled: March 25, 2021Publication date: March 24, 2022Inventors: Wenhao Wu, Wei Li, Xinyan Xiao
-
Patent number: 11216504Abstract: A document recommendation method based on a semantic tag and a document recommendation device. The method includes: for each document, acquiring a first candidate tag set corresponding to the document, and processing each first candidate tag in the first candidate tag set corresponding to the document to obtain a second candidate tag set corresponding to the document; performing normalization processing on each second candidate tag in the second candidate tag set corresponding to the document to obtain a third candidate tag set corresponding to the document; performing expanding process on each third candidate tag in the third candidate tag set corresponding to the document, and acquiring a fourth candidate tag set corresponding to the document, to form a document library having semantic tags; and recommending a target document obtained from the document library having semantic tags to the user, according to historical semantic tag.Type: GrantFiled: December 6, 2019Date of Patent: January 4, 2022Assignee: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.Inventors: Guocheng Niu, Bolei He, Chengxiang Liu, Xinyan Xiao, Yajuan Lyu
-
Publication number: 20210374349Abstract: A method for text generation, relates to a field of natural language processing, including: obtaining corpus data; labeling the corpus data to obtain a first constraint element; obtaining a first generation target; and generating a first text matching the first generation target by inputting the corpus data and the first constraint element into a generation model.Type: ApplicationFiled: August 9, 2021Publication date: December 2, 2021Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.Inventors: Jiachen LIU, Xinyan XIAO, Hua WU, Haifeng WANG
-
Publication number: 20210374359Abstract: The disclosure may provide a method for obtaining a document layout, an electronic device, and a storage medium. The method may include: obtaining a plurality of pieces of first sample data; extracting structured information from each of the plurality of pieces of first sample data as target structured information corresponding to each of the plurality of pieces of first sample data; inputting the plurality of pieces of first sample data into an initial text generation model to generate predicted structured information corresponding to each of the plurality of pieces of first sample data; generating a first loss value based on a difference between the predicted structured information corresponding to each of the plurality of pieces of first sample data and the corresponding target structured information; and training a phrase generation ability of the initial text generation model based on the first loss value to generate the text generation model.Type: ApplicationFiled: December 23, 2020Publication date: December 2, 2021Inventors: Wei LI, Xinyan XIAO, Hua WU, Haifeng WANG
-
Publication number: 20210342379Abstract: The disclosure discloses a method and a device for processing a sentence, and a storage medium. The detailed implementation includes: during processing a sentence, obtaining a dependency tree graph among respective segmented words in the sequence of segmented words by performing a dependency parsing on a sequence of segmented words of the sentence, inputting the dependency tree graph and a word vector corresponding to each segmented word into a preset graph neural network to obtain an intermediate word vector of each segmented word in the sequence of segmented words, and obtaining a processing result of the sentence by performing the downstream task on the intermediate word vector of each segmented word.Type: ApplicationFiled: July 14, 2021Publication date: November 4, 2021Inventors: Shuai ZHANG, Lijie WANG, Ao ZHANG, Xinyan XIAO, Yue CHANG
-
Publication number: 20210303921Abstract: A cross-modality processing method is related to a field of natural language processing technologies. The method includes: obtaining a sample set, wherein the sample set includes a plurality of corpus and a plurality of images; generating a plurality of training samples according to the sample set, in which each of the plurality of the training samples is a combination of at least one of the plurality of the corpus and at least one of the plurality of the images corresponding to the at least one of the plurality of the corpus; adopting the plurality of the training samples to train a semantic model, so that the semantic model learns semantic vectors containing combinations of the corpus and the images.Type: ApplicationFiled: August 10, 2020Publication date: September 30, 2021Inventors: Guocheng NIU, Bolei HE, Xinyan XIAO
-
Publication number: 20210286934Abstract: A method for implementing text generation, a device and a medium are provided. The method includes: determining a target task type of a target text generation task from multiple task types supported by a pre-trained general text generation model; determining, based on a requirement of the target text generation task for a target output text, a first target output text attribute for the target text generation task from multiple output text attributes supported by the general text generation model; and fine tuning the general text generation model based on a target training data set associated with the target text generation task to obtain a task-specific text generation model, by taking task indication information for the target task type and first attribute indication information for the first target output text attribute as at least part of an input of the general text generation model.Type: ApplicationFiled: May 26, 2021Publication date: September 16, 2021Inventors: Jiachen LIU, Zhe HU, Xinyan XIAO, Hua WU
-
Publication number: 20210200958Abstract: The present disclosure discloses a comment information processing method and apparatus, and a medium. The specific implementation solution is: in response to a user operation, determining an opinion category corresponding to each opinion phrase in a comment opinion dictionary; obtaining a target corpus matching each opinion phrase from a plurality of comment corpora; for each opinion phrase, using a corresponding opinion category to label the target corpus matching each opinion phrase to obtain a first training sample; and training a classification model with the first training sample to identify the opinion category of a comment by using a trained classification model.Type: ApplicationFiled: July 24, 2020Publication date: July 1, 2021Inventors: Hao LIU, Bolei HE, Xinyan XIAO
-
Publication number: 20210200951Abstract: Embodiments of the present disclosure provide methods and apparatus for outputting information. The method may include: obtaining a sentence to be identified; Performing word segmentation on the to be identified sentence to obtain a word sequence; Inputting a word sequence into a pre-trained multi-task element recognition model based on sequence labeling and entity word prediction, and outputting the identified entity words, entity categories and entity word positions, where the multi-task element recognition model includes a sequence labeling network for performing sequence labeling tasks and an entity word predicting network for performing entity word predicting task, and the sequence labeling network is fused with the entity word predicting network through a fusion module.Type: ApplicationFiled: June 9, 2020Publication date: July 1, 2021Inventors: Yuan GAO, Dai DAI, Xinyan XIAO
-
Publication number: 20210200949Abstract: The present disclosure provides a pre-training method for a sentiment analysis model and an electronic device, which relates to a field of artificial intelligence technologies. The method includes: based on a given seed sentiment dictionary, performing sentimental knowledge detection on a training corpus in a training corpus set, and determining a detection sentiment word and a detection word pair of the training corpus; according to preset mask processing rules, performing mask process on the training corpus to generate a masked corpus; performing encoding and decoding on the masked corpus by using a preset encoder and decoder to determine the detection sentiment word and the detection word pair of the training corpus; and updating the preset encoder and decoder according to a difference between prediction sentiment word and the detection sentiment word, and a difference between prediction word pair and the detection word pair.Type: ApplicationFiled: July 21, 2020Publication date: July 1, 2021Inventors: Can GAO, Hao LIU, Bolei HE, Xinyan XIAO, Hao TIAN
-
Publication number: 20210191937Abstract: A method and an apparatus for structuring data are related to information processing technologies in the field of natural language processing. By acquiring an unstructured text and inputting the unstructured text into an encoder-decoder model, an output sequence is obtained. The encoder-decoder model is trained using a training text marked with the attribute value of each attribute. A structured representation is generated based on the attributes corresponding to the attribute elements included in the output sequence and the attribute values comprised in the attribute elements.Type: ApplicationFiled: July 28, 2020Publication date: June 24, 2021Inventors: Wei JIA, Dai DAI, Xinyan XIAO
-
Publication number: 20210182491Abstract: Embodiments of the application disclose a summary generation method and apparatus. A specific embodiment of the method comprises: acquiring a target article including a headline and a body of the article; determining whether a question is included in the headline; determining, in the body of the article, an information-satisfied-paragraph including an answer to the question, in response to determining that the question is included in the headline; and generating a summary of the target article based on the determined information-satisfied-paragraph. The above embodiment may generate a summary that directly satisfies the users' demand for information.Type: ApplicationFiled: June 2, 2020Publication date: June 17, 2021Inventors: Moye CHEN, Wei XU, Jiachen LIU, Xinyan XIAO, Qiaoqiao SHE
-
Patent number: 10838997Abstract: The present disclosure provides a method and a device for generating a text tag. The method includes: performing keyword extraction using strategies corresponding to respective tag types on a target text, to obtain one or more candidate tags of the respective tag types for the target text, wherein the tag type includes at least one of an entity word, a segment text and a topic; performing reduplication removing between different tag types on the one or more candidate tags of the respective tag types to obtain one or more validated candidate tags; and determining one or more target tags of the target text based on the one or more validated candidate tags.Type: GrantFiled: June 26, 2018Date of Patent: November 17, 2020Assignee: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.Inventors: Jiachen Liu, Bolei He, Xinyan Xiao, Yajuan Lyu, Xiaoxu Fei
-
Publication number: 20200210468Abstract: The present disclosure provides a document recommendation method based on a semantic tag and a document recommendation device. The method includes: for each document, acquiring a first candidate tag set corresponding to the document, and processing each first candidate tag in the first candidate tag set corresponding to the document to obtain a second candidate tag set corresponding to the document; performing normalization processing on each second candidate tag in the second candidate tag set corresponding to the document to obtain a third candidate tag set corresponding to the document; performing expanding process on each third candidate tag in the third candidate tag set corresponding to the document, and acquiring a fourth candidate tag set corresponding to the document, to form a document library having semantic tags; and recommending a target document obtained from the document library having semantic tags to the user, according to historical semantic tag.Type: ApplicationFiled: December 6, 2019Publication date: July 2, 2020Inventors: Guocheng NIU, Bolei HE, Chengxiang LIU, Xinyan XIAO, Yajuan LYU
-
Patent number: 10671656Abstract: A method for recommending a text content based on a concern, a computer device, and a non-transitory computer readable storage medium are provided. The method includes: acquiring a query input by a user, and acquiring a reference text content selected by the user from search results corresponding to the query; generating a term vector of the query according to a term relative to the query in the reference text content; determining the concern of the user from a plurality of reference concerns according to similarities between the term vector of the query and term vectors of the plurality of reference concerns; and recommending the text content matched with the concern to the user.Type: GrantFiled: January 2, 2018Date of Patent: June 2, 2020Assignee: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.Inventors: Chengxiang Liu, Xinyan Xiao
-
Publication number: 20190012377Abstract: The present disclosure provides a method and a device for generating a text tag. The method includes: performing keyword extraction using strategies corresponding to respective tag types on a target text, to obtain one or more candidate tags of the respective tag types for the target text, wherein the tag type includes at least one of an entity word, a segment text and a topic; performing reduplication removing between different tag types on the one or more candidate tags of the respective tag types to obtain one or more validated candidate tags; and determining one or more target tags of the target text based on the one or more validated candidate tags.Type: ApplicationFiled: June 26, 2018Publication date: January 10, 2019Inventors: Jiachen LIU, Bolei HE, Xinyan XIAO, Yajuan LYU, Xiaoxu FEI
-
Publication number: 20180373787Abstract: A method for recommending a text content based on a concern, a computer device, and a non-transitory computer readable storage medium are provided. The method includes: acquiring a query input by a user, and acquiring a reference text content selected by the user from search results corresponding to the query; generating a term vector of the query according to a term relative to the query in the reference text content; determining the concern of the user from a plurality of reference concerns according to similarities between the term vector of the query and term vectors of the plurality of reference concerns; and recommending the text content matched with the concern to the user.Type: ApplicationFiled: January 2, 2018Publication date: December 27, 2018Inventors: Chengxiang LIU, Xinyan XIAO
-
Publication number: 20180341700Abstract: The present disclosure discloses an artificial intelligence based method and apparatus for determining regional information. A specific embodiment of the method comprises: acquiring to-be-determined information, and extracting a keyword set of the to-be-determined information; inputting the keyword set of the to-be-determined information into a pre-trained topic classification model for classifying, to obtain a topic class of the to-be-determined information, wherein the topic classification model is used for representing a corresponding relation between the keyword set of the information and the topic class of the information; selecting, from a pre-stored place name set, a place name corresponding to the topic class of the to-be-determined information as a target place name set; matching, in the to-be-determined information, the target place name set; and determining, based on a matching result, whether the to-be-determined information belongs to the regional information.Type: ApplicationFiled: March 30, 2018Publication date: November 29, 2018Inventors: Liangyu CHEN, Xinyan XIAO, Yajuan LV