Patents by Inventor Lidan Wang
Lidan 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: 11966852Abstract: The present disclosure generally provides systems and methods for situation awareness. When executing a set of instructions stored in at least one non-transitory storage medium, at least one processor may be configured to cause the system to perform operations including obtaining, from at least one of one or more sensors, environmental data associated with an environment corresponding to a first time point, generating a first static global representation of an environment corresponding to the first time point based at least in part on the environmental data, generating a first dynamic global representation of the environment corresponding to the first time point based at least in part on the environmental data, and estimating, based on the first static global representation and the first dynamic global representation, a target state of the environment at a target time point using a target estimation model.Type: GrantFiled: December 11, 2019Date of Patent: April 23, 2024Assignee: SHANGHAI UNITED IMAGING INTELLIGENCE CO., LTD.Inventors: Ziyan Wu, Srikrishna Karanam, Lidan Wang
-
Patent number: 11953606Abstract: A preprocessing system includes a first port, where one end of the first port is coupled to a first switch, and the other end of the first port is suspended, where the first switch has a connecting end configured to couple to a first interface and is configured to connect a filter and the first interface, a second port configured to receive a first signal or a second signal, where the filter is configured to filter the first signal to obtain a first positioning signal and a second positioning signal, provide the first positioning signal for the first switch, and provide the second positioning signal for a second interface of a global navigation satellite system (GNSS) chip to adapt to a plurality of antenna configuration types and to achieve universality.Type: GrantFiled: April 21, 2020Date of Patent: April 9, 2024Assignee: HUAWEI TECHNOLOGIES CO., LTD.Inventors: Rui Hu, Meiwen Yang, Jianqiang Wang, Lidan Li
-
Patent number: 11893345Abstract: Systems and methods for natural language processing are described. One or more embodiments of the present disclosure receive a document comprising a plurality of words organized into a plurality of sentences, the words comprising an event trigger word and an argument candidate word, generate word representation vectors for the words, generate a plurality of document structures including a semantic structure for the document based on the word representation vectors, a syntax structure representing dependency relationships between the words, and a discourse structure representing discourse information of the document based on the plurality of sentences, generate a relationship representation vector based on the document structures, and predict a relationship between the event trigger word and the argument candidate word based on the relationship representation vector.Type: GrantFiled: April 6, 2021Date of Patent: February 6, 2024Assignee: ADOBE, INC.Inventors: Amir Pouran Ben Veyseh, Franck Dernoncourt, Quan Tran, Varun Manjunatha, Lidan Wang, Rajiv Jain, Doo Soon Kim, Walter Chang
-
Patent number: 11822887Abstract: Systems and methods for natural language processing are described. One or more embodiments of the disclosure provide an entity matching apparatus trained using machine learning techniques to determine whether a query name corresponds to a candidate name based on a similarity score. In some examples, the query name and the candidate name are encoded using a character encoder to produce a regularized input sequence and a regularized candidate sequence, respectively. The regularized input sequence and the regularized candidate sequence are formed from a regularized character set having fewer characters than a natural language character set.Type: GrantFiled: March 12, 2021Date of Patent: November 21, 2023Assignee: ADOBE, INC.Inventors: Lidan Wang, Franck Dernoncourt
-
Patent number: 11709873Abstract: Techniques and systems are provided for predicting answers in response to one or more input queries. For instance, text from a corpus of text can be processed by a reader to generate one or multiple question and answer spaces. A question and answer space can include answerable questions and the answers associated with the questions (referred to as “question and answer pairs”). A query defining a question can be received (e.g., from a user input device) and processed by a retriever portion of the system. The retriever portion of the system can retrieve an answer to the question from the one or more pre-constructed question and answer spaces, and/or can determine an answer by comparing one or more answers retrieved from the one or more pre-constructed question and answer spaces to an answer generated by a retriever-reader system.Type: GrantFiled: January 13, 2020Date of Patent: July 25, 2023Assignee: Adobe Inc.Inventors: Jinfeng Xiao, Lidan Wang, Franck Dernoncourt, Trung Bui, Tong Sun
-
Patent number: 11620457Abstract: Systems and methods for sentence fusion are described. Embodiments receive coreference information for a first sentence and a second sentence, wherein the coreference information identifies entities associated with both a term of the first sentence and a term of the second sentence, apply an entity constraint to an attention head of a sentence fusion network, wherein the entity constraint limits attention weights of the attention head to terms that correspond to a same entity of the coreference information, and predict a fused sentence using the sentence fusion network based on the entity constraint, wherein the fused sentence combines information from the first sentence and the second sentence.Type: GrantFiled: February 17, 2021Date of Patent: April 4, 2023Assignee: ADOBE INC.Inventors: Logan Lebanoff, Franck Dernoncourt, Doo Soon Kim, Lidan Wang, Walter Chang
-
Patent number: 11556826Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for selecting hyper-parameter sets by utilizing a modified Bayesian optimization approach based on a combination of accuracy and training efficiency metrics of a machine learning model. For example, the disclosed systems can fit accuracy regression and efficiency regression models to observed metrics associated with hyper-parameter sets of a machine learning model. The disclosed systems can also implement a trade-off acquisition function that implements an accuracy-training efficiency balance metric to explore the hyper-parameter feature space and select hyper-parameters for training the machine learning model considering a balance between accuracy and training efficiency.Type: GrantFiled: March 20, 2020Date of Patent: January 17, 2023Assignee: Adobe Inc.Inventors: Trung Bui, Lidan Wang, Franck Dernoncourt
-
Publication number: 20220318505Abstract: Systems and methods for natural language processing are described. One or more embodiments of the present disclosure receive a document comprising a plurality of words organized into a plurality of sentences, the words comprising an event trigger word and an argument candidate word, generate word representation vectors for the words, generate a plurality of document structures including a semantic structure for the document based on the word representation vectors, a syntax structure representing dependency relationships between the words, and a discourse structure representing discourse information of the document based on the plurality of sentences, generate a relationship representation vector based on the document structures, and predict a relationship between the event trigger word and the argument candidate word based on the relationship representation vector.Type: ApplicationFiled: April 6, 2021Publication date: October 6, 2022Inventors: Amir Pouran Ben Veyseh, Franck Dernoncourt, Quan Tran, Varun Manjunatha, Lidan Wang, Rajiv Jain, Doo Soon Kim, Walter Chang
-
Publication number: 20220292263Abstract: Systems and methods for natural language processing are described. One or more embodiments of the disclosure provide an entity matching apparatus trained using machine learning techniques to determine whether a query name corresponds to a candidate name based on a similarity score. In some examples, the query name and the candidate name are encoded using a character encoder to produce a regularized input sequence and a regularized candidate sequence, respectively. The regularized input sequence and the regularized candidate sequence are formed from a regularized character set having fewer characters than a natural language character set.Type: ApplicationFiled: March 12, 2021Publication date: September 15, 2022Inventors: LIDAN WANG, Franck Dernoncourt
-
Publication number: 20220261555Abstract: Systems and methods for sentence fusion are described. Embodiments receive coreference information for a first sentence and a second sentence, wherein the coreference information identifies entities associated with both a term of the first sentence and a term of the second sentence, apply an entity constraint to an attention head of a sentence fusion network, wherein the entity constraint limits attention weights of the attention head to terms that correspond to a same entity of the coreference information, and predict a fused sentence using the sentence fusion network based on the entity constraint, wherein the fused sentence combines information from the first sentence and the second sentence.Type: ApplicationFiled: February 17, 2021Publication date: August 18, 2022Inventors: Logan Lebanoff, Franck Dernoncourt, Doo Soon Kim, Lidan Wang, Walter Chang
-
Publication number: 20220138534Abstract: This disclosure describes methods, non-transitory computer readable storage media, and systems that utilize a plurality of neural networks to determine structural and semantic information via different views of a word sequence and then utilize this information to extract a relationship between word sequence entities. For example, the disclosed systems generate a plurality of sets of encoded word representation vectors utilizing the plurality of neural networks. The disclosed system then extracts the relationship from an overall word representation vector generated based on the sets of encoded word representation vectors. Furthermore, the disclosed system enforces structural and semantic consistency between views via a plurality of constrains involving a control mechanism for the semantic view and a plurality of losses.Type: ApplicationFiled: November 3, 2020Publication date: May 5, 2022Inventors: Amir Pouran Ben Veyseh, Franck Dernoncourt, Quan Tran, Lidan Wang
-
Publication number: 20220050967Abstract: This disclosure describes methods, non-transitory computer readable storage media, and systems that extract a definition for a term from a source document by utilizing a single machine-learning framework to classify a word sequence from the source document as including a term definition and to label words from the word sequence. To illustrate, the disclosed system can receive a source document including a word sequence arranged in one or more sentences. The disclosed systems can utilize a machine-learning model to classify the word sequence as comprising a definition for a term and generate labels for the words from the word sequence corresponding to the term and the definition. Based on classifying the word sequence and the generated labels, the disclosed system can extract the definition for the term from the source document.Type: ApplicationFiled: August 11, 2020Publication date: February 17, 2022Inventors: Amir Pouran Ben Veyseh, Franck Dernoncourt, Quan Tran, Yiming Yang, Lidan Wang, Rajiv Jain, Vlad Morariu, Walter Chang
-
Patent number: 11222167Abstract: The disclosure describes one or more embodiments of a structured text summary system that generates structured text summaries of digital documents based on an interactive graphical user interface. For example, the structured text summary system can collaborate with users to create structured text summaries of a digital document based on automatically generating document tags corresponding to the digital document, determining segments of the digital document that correspond to a selected document tag, and generating structured text summaries for those document segments.Type: GrantFiled: December 19, 2019Date of Patent: January 11, 2022Assignee: ADOBE INC.Inventors: Sebastian Gehrmann, Franck Dernoncourt, Lidan Wang, Carl Dockhorn, Yu Gong
-
Publication number: 20210295191Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for selecting hyper-parameter sets by utilizing a modified Bayesian optimization approach based on a combination of accuracy and training efficiency metrics of a machine learning model. For example, the disclosed systems can fit accuracy regression and efficiency regression models to observed metrics associated with hyper-parameter sets of a machine learning model. The disclosed systems can also implement a trade-off acquisition function that implements an accuracy-training efficiency balance metric to explore the hyper-parameter feature space and select hyper-parameters for training the machine learning model considering a balance between accuracy and training efficiency.Type: ApplicationFiled: March 20, 2020Publication date: September 23, 2021Inventors: Trung Bui, Lidan Wang, Franck Dernoncourt
-
Publication number: 20210279622Abstract: Methods for natural language semantic matching performed by training and using a Markov Network model are provided. The trained Markov Network model can be used to identify answers to questions. Training may be performed using question-answer pairs that include labels indicating a correct or incorrect answer to a question. The trained Markov Network model can be used to identify answers to questions from sources stored on a database. The Markov Network model provides superior performance over other semantic matching models, in particular, where the training data set includes a different information domain type relative to the input question or the output answer of the trained Markov Network model.Type: ApplicationFiled: March 9, 2020Publication date: September 9, 2021Inventors: Trung Huu Bui, Tong Sun, Natwar Modani, Lidan Wang, Franck Dernoncourt
-
Publication number: 20210216577Abstract: Techniques and systems are provided for predicting answers in response to one or more input queries. For instance, text from a corpus of text can be processed by a reader to generate one or multiple question and answer spaces. A question and answer space can include answerable questions and the answers associated with the questions (referred to as “question and answer pairs”). A query defining a question can be received (e.g., from a user input device) and processed by a retriever portion of the system. The retriever portion of the system can retrieve an answer to the question from the one or more pre-constructed question and answer spaces, and/or can determine an answer by comparing one or more answers retrieved from the one or more pre-constructed question and answer spaces to an answer generated by a retriever-reader system.Type: ApplicationFiled: January 13, 2020Publication date: July 15, 2021Applicant: Adobe Inc.Inventors: Jinfeng Xiao, Lidan Wang, Franck Dernoncourt, Trung Bui, Tong Sun
-
Publication number: 20210192126Abstract: The disclosure describes one or more embodiments of a structured text summary system that generates structured text summaries of digital documents based on an interactive graphical user interface. For example, the structured text summary system can collaborate with users to create structured text summaries of a digital document based on automatically generating document tags corresponding to the digital document, determining segments of the digital document that correspond to a selected document tag, and generating structured text summaries for those document segments.Type: ApplicationFiled: December 19, 2019Publication date: June 24, 2021Inventors: Sebastian Gehrmann, Franck Dernoncourt, Lidan Wang, Carl Dockhorn, Yu Gong
-
Publication number: 20210182694Abstract: The present disclosure generally provides systems and methods for situation awareness. When executing a set of instructions stored in at least one non-transitory storage medium, at least one processor may be configured to cause the system to perform operations including obtaining, from at least one of one or more sensors, environmental data associated with an environment corresponding to a first time point, generating a first static global representation of an environment corresponding to the first time point based at least in part on the environmental data, generating a first dynamic global representation of the environment corresponding to the first time point based at least in part on the environmental data, and estimating, based on the first static global representation and the first dynamic global representation, a target state of the environment at a target time point using a target estimation model.Type: ApplicationFiled: December 11, 2019Publication date: June 17, 2021Applicant: SHANGHAI UNITED IMAGING INTELLIGENCE CO., LTD.Inventors: Ziyan WU, Srikrishna KARANAM, Lidan WANG
-
Patent number: 9535995Abstract: Technologies are described herein that pertain to optimizing a ranker component for a risk-oriented objective. Various definitions of risk are described herein, wherein risk is based upon variance in performance scores assigned to the ranker component for respective queries in a data store. Additionally, risk is optionally based upon variance in relative performance of the ranker component versus a baseline ranker component.Type: GrantFiled: December 13, 2011Date of Patent: January 3, 2017Assignee: Microsoft Technology Licensing, LLCInventors: Paul N. Bennett, Kevyn B. Collins-Thompson, Lidan Wang
-
Patent number: D1025276Type: GrantFiled: August 5, 2020Date of Patent: April 30, 2024Assignee: LIAONING QINGYANG EXPLOSIVE MATERIALS CO., LTDInventors: Tao Jiang, Dingming Lin, Jin Zhu, Defei Gao, Guangjun Li, Lidan Jing, Xingzhen Wang, Xiongfei Yang, Ji Fan, Guopeng Ban, Qi Sun