Patents by Inventor Dingcheng Li
Dingcheng Li 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: 11080615Abstract: Aspects of the present invention disclose a method for analyzing data from a plurality of data sources. The method includes extracting features of data received from a first source and from a second source by analyzing the data received from the first source of data and from the second source. The method includes processors determining a topic modeling framework, wherein the topic modeling framework detects a semantic structure of the features of the data received from the first data source and the second source. The method includes processors applying the topic modeling framework to the data received from the first source of data the second source of data. The method includes generating a final entity output, wherein the final entity output includes a cluster of entity mentions that the applied topic modeling framework extracts from the first source of data and the second source of data are combined.Type: GrantFiled: June 15, 2017Date of Patent: August 3, 2021Assignee: International Business Machines CorporationInventors: Yu Gu, Dingcheng Li, Kai Liu, Su Liu
-
Publication number: 20200380385Abstract: Leveraging domain knowledge is an effective strategy for enhancing the quality of inferred low-dimensional representations of documents by topic models. Presented herein are embodiments of a Bayesian nonparametric model that employ knowledge graph (KG) embedding in the context of topic modeling for extracting more coherent topics; embodiments of the model may be referred to as topic modeling with knowledge graph embedding (TMKGE). TMKGE embodiments are hierarchical Dirichlet process (HDP)-based models that flexibly borrow information from a KG to improve the interpretability of topics. Also, embodiments of a new, efficient online variational inference method based on a stick-breaking construction of HDP were developed for TMKGE models, making TMKGE suitable for large document corpora and KGs. Experiments on datasets illustrate the superior performance of TMKGE in terms of topic coherence and document classification accuracy, compared to state-of-the-art topic modeling methods.Type: ApplicationFiled: May 30, 2019Publication date: December 3, 2020Applicant: Baidu USA LLCInventors: Dingcheng LI, Jingyuan ZHANG, Ping LI, Siamak ZAMANI DADANEH
-
Publication number: 20200372428Abstract: A method, computer program product, and a system where a processor(s) determines generates a cognitive user profile representing patterns of usage of each of a plurality of users of the transportation resource sharing system, a cognitive resource profile for each resource of the plurality of resources, a cognitive route profile for each route traversed by at least one resource of the plurality of resources, and a cognitive station profile for each station of the plurality of stations. The processor(s) assigns one or more specific resources of the plurality of resources to one or more specific users of the plurality of users and the one or more specific resources of the plurality of resources to one or more specific stations of the plurality of stations.Type: ApplicationFiled: May 21, 2019Publication date: November 26, 2020Inventors: Su Liu, Yu Gu, Dingcheng Li, Kai Liu
-
Publication number: 20200356851Abstract: Described herein are embodiments for a deep level-wise extreme multi-label learning and classification (XMLC) framework to facilitate the semantic indexing of literatures. In one or more embodiments, the Deep Level-wise XMLC framework comprises two sequential modules, a deep level-wise multi-label learning module and a hierarchical pointer generation module. In one or more embodiments, the first module decomposes terms of domain ontology into multiple levels and builds a special convolutional neural network for each level with category-dependent dynamic max-pooling and macro F-measure based weights tuning. In one or more embodiments, the second module merges the level-wise outputs into a final summarized semantic indexing. The effectiveness of Deep Level-wise XMLC framework embodiments is demonstrated by comparing it with several state-of-the-art methods of automatic labeling on various datasets.Type: ApplicationFiled: May 10, 2019Publication date: November 12, 2020Applicant: Baidu USA LLCInventors: Dingcheng LI, Jingyuan ZHANG, Ping LI
-
Patent number: 10821608Abstract: Embodiments generally relate to robots and enabling robots to locate objects in a physical environment. In some embodiments, a method includes charging a radio-frequency identification (RFID) tag with an RFID reader, where the RFID tag is coupled to an object, and where the RFID reader is coupled to a robot arm. The method further includes receiving a plurality of responses from the RFID tag, where each response includes a power value to which the RFID tag was charged and a time value for charging the RFID tag to the power value. The method further includes moving the RFID reader to a plurality of RFID reader positions using the robot arm, where each RFID reader position is associated with one of the responses of the plurality of responses. The method further includes determining a plurality of distances from the RFID reader to the RFID tag based on power values and the time values of the respective responses at the respective RFID reader positions.Type: GrantFiled: October 23, 2017Date of Patent: November 3, 2020Assignee: International Business Machines CorporationInventors: Yu Gu, Dingcheng Li, Kai Liu, Su Liu
-
Publication number: 20200293902Abstract: Described herein are embodiments for systems and methods for mutual machine learning with global topic discovery and local word embedding. Both topic modeling and word embedding map documents onto a low-dimensional space, with the former clustering words into a global topic space and the latter mapping word into a local continuous embedding space. Embodiments of Topic Modeling and Sparse Autoencoder (TMSA) framework unify these two complementary patterns by constructing a mutual learning mechanism between word co-occurrence based topic modeling and autoencoder. In embodiments, word topics generated with topic modeling are passed into auto-encoder to impose topic sparsity for the autoencoder to learn topic-relevant word representations. In return, word embedding learned by autoencoder is sent back to topic modeling to improve the quality of topic generations. Performance evaluation on various datasets demonstrates the effectiveness of the disclosed TMSA framework in discovering topics and embedding words.Type: ApplicationFiled: March 15, 2019Publication date: September 17, 2020Applicant: Baidu USA LLCInventors: Dingcheng LI, Jingyuan ZHANG, Ping LI
-
Publication number: 20200242444Abstract: Described herein are embodiments for question answering over knowledge graph using a Knowledge Embedding based Question Answering (KEQA) framework. Instead of inferring an input questions' head entity and predicate directly, KEQA embodiments target jointly recovering the question's head entity, predicate, and tail entity representations in the KG embedding spaces. In embodiments, a joint distance metric incorporating various loss terms is used to measure distances of a predicated fact to all candidate facts. In embodiments, the fact with the minimum distance is returned as the answer. Embodiments of a joint training strategy are also disclosed for better performance. Performance evaluation on various datasets demonstrates the effectiveness of the disclosed systems and methods using the KEQA framework.Type: ApplicationFiled: January 30, 2019Publication date: July 30, 2020Applicant: Baidu USA LLCInventors: Jingyuan ZHANG, Dingcheng LI, Ping LI, Xiao HUANG
-
Publication number: 20200184339Abstract: Described herein are embodiments of a unified neural network framework to integrate Topic modeling, Word embedding and Entity Embedding (TWEE) for representation learning of inputs. In one or more embodiments, a novel topic sparse autoencoder is introduced to incorporate discriminative topics into the representation learning of the input. Topic distributions of inputs are generated from a global viewpoint and are utilized to enable autoencoder to learn topical representations. A sparsity constraint may be added to ensure that the most discriminative representations are related to topics. In addition, both words and entity related information may be embedded into the network to help learn a more comprehensive input representation. Extensive empirical experiments show that embodiments of the TWEE framework outperform the state-of-the-art methods on different datasets.Type: ApplicationFiled: November 21, 2019Publication date: June 11, 2020Applicant: Baidu USA LLCInventors: Dingcheng LI, Jingyuan ZHANG, Ping LI
-
Publication number: 20190377807Abstract: Embodiments generally relate transforming data for a target schema. In some embodiments, a method includes receiving input data, where the input data includes a plurality of segments, and where the segments include a plurality of source fields containing target data. The method further includes characterizing the input data based at least in part on a plurality of predetermined metrics, where the predetermined metrics determine a structure of the input data. The method further includes mapping the target data in the source fields of the segments to a plurality of target fields of a target schema based at least in part on the characterizing. The method further includes populating the target fields of the target schema with the target data from the source fields based at least in part on the mapping.Type: ApplicationFiled: June 11, 2018Publication date: December 12, 2019Inventors: Daniel DEAN, Checed A. RODGERS, Dingcheng LI, Pei Ni LIU, Xiao Xi LIU, Hui LEI, Yu GU, Jing Min XU, Yaoping RUAN
-
Publication number: 20190118382Abstract: Embodiments generally relate to robots and enabling robots to locate objects in a physical environment. In some embodiments, a method includes charging a radio-frequency identification (RFID) tag with an RFID reader, where the RFID tag is coupled to an object, and where the RFID reader is coupled to a robot arm. The method further includes receiving a plurality of responses from the RFID tag, where each response includes a power value to which the RFID tag was charged and a time value for charging the RFID tag to the power value. The method further includes moving the RFID reader to a plurality of RFID reader positions using the robot arm, where each RFID reader position is associated with one of the responses of the plurality of responses. The method further includes determining a plurality of distances from the RFID reader to the RFID tag based on power values and the time values of the respective responses at the respective RFID reader positions.Type: ApplicationFiled: October 23, 2017Publication date: April 25, 2019Inventors: Yu GU, Dingcheng LI, Kai LIU, Su LIU
-
Patent number: 10198431Abstract: For generating a word space, manual thresholding of word scores is used. Rather than requiring the user to select the threshold arbitrarily or review each word, the user is iteratively requested to indicate the relevance of a given word. Words with greater or lesser scores are labeled in the same way depending upon the response. For determining the relationship between named entities, Latent Dirichlet Allocation (LDA) is performed on text associated with the name entities rather than on an entire document. LDA for relationship mining may include context information and/or supervised learning.Type: GrantFiled: August 22, 2011Date of Patent: February 5, 2019Assignee: SIEMENS CORPORATIONInventors: Swapna Somasundaran, Dingcheng Li, Amit Chakraborty
-
Publication number: 20180365592Abstract: Aspects of the present invention disclose a method for analyzing data from a plurality of data sources. The method includes extracting features of data received from a first source and from a second source by analyzing the data received from the first source of data and from the second source. The method includes processors determining a topic modeling framework, wherein the topic modeling framework detects a semantic structure of the features of the data received from the first data source and the second source. The method includes processors applying the topic modeling framework to the data received from the first source of data the second source of data. The method includes generating a final entity output, wherein the final entity output includes a cluster of entity mentions that the applied topic modeling framework extracts from the first source of data and the second source of data are combined.Type: ApplicationFiled: December 28, 2017Publication date: December 20, 2018Inventors: Yu Gu, Dingcheng Li, Kai Liu, Su Liu
-
Publication number: 20180365588Abstract: Aspects of the present invention disclose a method for analyzing data from a plurality of data sources. The method includes extracting features of data received from a first source and from a second source by analyzing the data received from the first source of data and from the second source. The method includes processors determining a topic modeling framework, wherein the topic modeling framework detects a semantic structure of the features of the data received from the first data source and the second source. The method includes processors applying the topic modeling framework to the data received from the first source of data the second source of data. The method includes generating a final entity output, wherein the final entity output includes a cluster of entity mentions that the applied topic modeling framework extracts from the first source of data and the second source of data are combined.Type: ApplicationFiled: June 15, 2017Publication date: December 20, 2018Inventors: Yu Gu, Dingcheng Li, Kai Liu, Su Liu
-
Publication number: 20180330231Abstract: Disclosed aspects relate to entity model establishment using an infinite mixture topic modeling (IMTM) technique. A set of event data which corresponds to a set of events may be detected. Using the IMTM technique, the set of event data which corresponds to the set of events may be analyzed. Based on analyzing the set of event data using the IMTM technique, a set of entity models for the set of events may be determined. Based on the set of entity models for the set of events, a subset of the set of entity models for the set of events may be established.Type: ApplicationFiled: May 10, 2017Publication date: November 15, 2018Inventors: Yu Gu, Dingcheng Li, Kai Liu, Su Liu
-
Publication number: 20120078918Abstract: For generating a word space, manual thresholding of word scores is used. Rather than requiring the user to select the threshold arbitrarily or review each word, the user is iteratively requested to indicate the relevance of a given word. Words with greater or lesser scores are labeled in the same way depending upon the response. For determining the relationship between named entities, Latent Dirichlet Allocation (LDA) is performed on text associated with the name entities rather than on an entire document. LDA for relationship mining may include context information and/or supervised learning.Type: ApplicationFiled: August 22, 2011Publication date: March 29, 2012Applicant: Siemens CorporationInventors: Swapna Somasundaran, Dingcheng Li, Amit Chakraborty