Patents by Inventor Hoifung Poon
Hoifung Poon 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: 20240013055Abstract: This document relates to training of machine learning models. One example method involves providing a machine learning model having one or more mapping layers. The one or more mapping layers can include at least a first mapping layer configured to map components of pretraining examples into first representations in a space. The example method also includes performing a pretraining stage on the one or more mapping layers using the pretraining examples. The pretraining stage can include adding noise to the first representations of the components of the pretraining examples to obtain noise-adjusted first representations. The pretraining stage can also include performing a self-supervised learning process to pretrain the one or more mapping layers using at least the first representations of the training data items and the noise-adjusted first representations of the training data items.Type: ApplicationFiled: September 26, 2023Publication date: January 11, 2024Applicant: Microsoft Technology Licensing, LLCInventors: Xiaodong Liu, Hao Cheng, Yu Wang, Jianfeng Gao, Weizhu Chen, Pengcheng He, Hoifung Poon
-
Publication number: 20240013074Abstract: The present disclosure relates to devices and methods for determining new virtual evidence to use with a deep probabilistic logic module. The devices and methods may receive output from a deep probabilistic logic module in response to running an initial set of virtual evidence through the deep probabilistic logic module. The devices and methods may use the output to automatically propose at least one factor as new virtual evidence for use with the deep probabilistic logic module. The devices and methods may add the new virtual evidence to the deep probabilistic logic module.Type: ApplicationFiled: August 1, 2023Publication date: January 11, 2024Inventors: Hoifung POON, Hunter LANG
-
Patent number: 11803758Abstract: This document relates to training of machine learning models. One example method involves providing a machine learning model having one or more mapping layers. The one or more mapping layers can include at least a first mapping layer configured to map components of pretraining examples into first representations in a space. The example method also includes performing a pretraining stage on the one or more mapping layers using the pretraining examples. The pretraining stage can include adding noise to the first representations of the components of the pretraining examples to obtain noise-adjusted first representations. The pretraining stage can also include performing a self-supervised learning process to pretrain the one or more mapping layers using at least the first representations of the training data items and the noise-adjusted first representations of the training data items.Type: GrantFiled: May 22, 2020Date of Patent: October 31, 2023Assignee: Microsoft Technology Licensing, LLCInventors: Xiaodong Liu, Hao Cheng, Yu Wang, Jianfeng Gao, Weizhu Chen, Pengcheng He, Hoifung Poon
-
Patent number: 11755939Abstract: The present disclosure relates to devices and methods for determining new virtual evidence to use with a deep probabilistic logic module. The devices and methods may receive output from a deep probabilistic logic module in response to running an initial set of virtual evidence through the deep probabilistic logic module. The devices and methods may use the output to automatically propose at least one factor as new virtual evidence for use with the deep probabilistic logic module. The devices and methods may add the new virtual evidence to the deep probabilistic logic module.Type: GrantFiled: June 24, 2020Date of Patent: September 12, 2023Assignee: MICROSOFT TECHNOLOGY LICENSING, LLCInventors: Hoifung Poon, Hunter Lang
-
Patent number: 11720610Abstract: Systems, methods, and computer-readable media for providing entity relation extraction across sentences in a document using distant supervision are disclosed. A computing device can receive an input, such as a document comprising a plurality of sentences. The computing device can identify syntactic and/or semantic links between words in a sentence and/or between words in different sentences, and extract relationships between entities throughout the document. A knowledge base (e.g., a table, chart, database etc.) of entity relations based on the extracted relationships can be populated. An output of the populated knowledge base can be used by a classifier to identify additional relationships between entities in various documents. Machine learning can be applied to train the classifier to predict relations between entities. The classifier can be trained using known entity relations, syntactic links and/or semantic links.Type: GrantFiled: December 2, 2021Date of Patent: August 8, 2023Assignee: Microsoft Technology Licensing, LLCInventors: Christopher Brian Quirk, Hoifung Poon
-
Publication number: 20230102428Abstract: A computer implemented method comprising: receiving a report on a condition of a human or animal subject, composed by a user based on a scan of the subject; inputting the current report and the scan into a trained machine learning model; and based on the report and the scan, the machine learning model generating one or more suggestions for updating the text of the report. The method further comprises causing a user interface to display to the user one or more suggestions for updating the text of the report, with each respective suggestion visually linked in the user interface to a corresponding subregion within at least one image of the scan based upon which the respective suggestion was generated.Type: ApplicationFiled: September 24, 2021Publication date: March 30, 2023Inventors: Ozan OKTAY, Javier Alvarez VALLE, Melanie BERNHARDT, Daniel COELHO DE CASTRO, Shruthi BANNUR, Anton SCHWAIGHOFER, Aditya NORI, Hoifung POON
-
Publication number: 20230019081Abstract: Systems and methods are provided for generating and training a relation extraction model configured to extract document-level relations. Systems obtain a knowledge database that comprises a plurality of entity tuples and a plurality of relation types, use the knowledge database to generate annotated relation instances based on relation instances that are identified in a set of unlabeled text, generate a training dataset comprising the annotated relation instances and the set of unlabeled text, and generate the machine learning model via modular self-supervision. Systems and methods are also provided for using a relation extraction model to extract document-level relations in specific use scenarios, such as for extracting drug response relations from full-text medical research articles.Type: ApplicationFiled: July 16, 2021Publication date: January 19, 2023Inventors: Sheng ZHANG, Cliff Richard WONG, Naoto USUYAMA, Sarthak JAIN, Tristan Josef NAUMANN, Hoifung POON
-
Publication number: 20220092093Abstract: Systems, methods, and computer-readable media for providing entity relation extraction across sentences in a document using distant supervision. In some examples, a computing device can receive an input, such as a document comprising a plurality of sentences. The computing device can identify syntactic and/or semantic links between words in a sentence and/or between words in different sentences, and extract relationships between entities throughout the document. Techniques and technologies described herein populate a knowledge base (e.g., a table, chart, database etc.) of entity relations based on the extracted relationships. An output of the populated knowledge base can be used by a classifier to identify additional relationships between entities in various documents. Example techniques described herein can apply machine learning to train the classifier to predict relations between entities. The classifier can be trained using known entity relations, syntactic links and/or semantic links.Type: ApplicationFiled: December 2, 2021Publication date: March 24, 2022Applicant: Microsoft Technology Licensing, LLCInventors: Christopher Brian Quirk, Hoifung Poon
-
Patent number: 11250331Abstract: A technique is described herein for processing documents in a time-efficient and accurate manner. In a training phase, the technique generates a set of initial training examples by associating entity mentions in a text corpus with corresponding entity identifiers. Each entity identifier uniquely identifies an entity in a particular ontology. The technique then removes noisy training examples from the set of initial training examples, to provide a set of filtered training examples. The technique then applies a machine-learning process to generate a linking component based, in part, on the set of filtered training examples. In an application phase, the technique uses the linking component to link input entity mentions with corresponding entity identifiers. Various application systems can leverage the capabilities of the linking component, including a search system, a document-creation system, etc.Type: GrantFiled: October 31, 2017Date of Patent: February 15, 2022Assignee: Microsoft Technology Licensing, LLCInventors: Christopher Brian Quirk, Hoifung Poon, Wen-tau Yih, Hai Wang
-
Publication number: 20210406741Abstract: The present disclosure relates to devices and methods for determining new virtual evidence to use with a deep probabilistic logic module. The devices and methods may receive output from a deep probabilistic logic module in response to running an initial set of virtual evidence through the deep probabilistic logic module. The devices and methods may use the output to automatically propose at least one factor as new virtual evidence for use with the deep probabilistic logic module. The devices and methods may add the new virtual evidence to the deep probabilistic logic module.Type: ApplicationFiled: June 24, 2020Publication date: December 30, 2021Inventors: Hoifung POON, Hunter LANG
-
Patent number: 11210324Abstract: Systems, methods, and computer-readable media provide entity relation extraction across sentences in a document using distant supervision. A computing device can receive an input, such as a document comprising a plurality of sentences. The computing device can identify syntactic and/or semantic links between words in a sentence and/or between words in different sentences, and extract relationships between entities throughout the document. A knowledge base (e.g., a table, chart, database etc.) of entity relations based on the extracted relationships can be populated. An output of the populated knowledge base can be used by a classifier to identify additional relationships between entities in various documents. Machine learning can be applied to train the classifier to predict relations between entities. The classifier can be trained using known entity relations, syntactic links and/or semantic links.Type: GrantFiled: June 3, 2016Date of Patent: December 28, 2021Assignee: Microsoft Technology Licensing, LLCInventors: Christopher Brian Quirk, Hoifung Poon
-
Publication number: 20210326751Abstract: This document relates to training of machine learning models. One example method involves providing a machine learning model having one or more mapping layers. The one or more mapping layers can include at least a first mapping layer configured to map components of pretraining examples into first representations in a space. The example method also includes performing a pretraining stage on the one or more mapping layers using the pretraining examples. The pretraining stage can include adding noise to the first representations of the components of the pretraining examples to obtain noise-adjusted first representations. The pretraining stage can also include performing a self-supervised learning process to pretrain the one or more mapping layers using at least the first representations of the training data items and the noise-adjusted first representations of the training data items.Type: ApplicationFiled: May 22, 2020Publication date: October 21, 2021Applicant: Microsoft Technology Licensing, LLCInventors: Xiaodong Liu, Hao Cheng, Yu Wang, Jianfeng Gao, Weizhu Chen, Pengcheng He, Hoifung Poon
-
Patent number: 10943068Abstract: A computing system is provided. The computing system includes a processor configured to execute one or more programs and associated memory. The processor is configured to execute neural network system that includes a first neural network and a second neural network. The processor is configured to receive input text, and for each of a plurality of text spans within the input text: identify a vector of semantic entities and a vector of entity mentions; define an n-ary relation between entity mentions including subrelations; and determine mention-level representation vectors in the text spans that satisfy the n-ary relation or subrelations. The processor is configured to: aggregate the mention-level representation vectors over all of the text spans to produce entity-level representation vectors; input to the second neural network the entity-level representation vectors; and output a prediction of a presence of the n-ary relation for the semantic entities in the input text.Type: GrantFiled: March 29, 2019Date of Patent: March 9, 2021Assignee: Microsoft Technology Licensing, LLCInventors: Hoifung Poon, Cliff Wong, Robin Jia
-
Publication number: 20200311198Abstract: A computing system is provided. The computing system includes a processor configured to execute one or more programs and associated memory. The processor is configured to execute neural network system that includes a first neural network and a second neural network. The processor is configured to receive input text, and for each of a plurality of text spans within the input text: identify a vector of semantic entities and a vector of entity mentions; define an n-ary relation between entity mentions including subrelations; and determine mention-level representation vectors in the text spans that satisfy the n-ary relation or subrelations. The processor is configured to: aggregate the mention-level representation vectors over all of the text spans to produce entity-level representation vectors; input to the second neural network the entity-level representation vectors; and output a prediction of a presence of the n-ary relation for the semantic entities in the input text.Type: ApplicationFiled: March 29, 2019Publication date: October 1, 2020Applicant: Microsoft Technology Licensing, LLCInventors: Hoifung POON, Cliff WONG, Robin JIA
-
Publication number: 20190130282Abstract: A technique is described herein for processing documents in a time-efficient and accurate manner. In a training phase, the technique generates a set of initial training examples by associating entity mentions in a text corpus with corresponding entity identifiers. Each entity identifier uniquely identifies an entity in a particular ontology. The technique then removes noisy training examples from the set of initial training examples, to provide a set of filtered training examples. The technique then applies a machine-learning process to generate a linking component based, in part, on the set of filtered training examples. In an application phase, the technique uses the linking component to link input entity mentions with corresponding entity identifiers. Various application systems can leverage the capabilities of the linking component, including a search system, a document-creation system, etc.Type: ApplicationFiled: October 31, 2017Publication date: May 2, 2019Inventors: Christopher Brian QUIRK, Hoifung POON, Wen-tau YIH, Hai WANG
-
Patent number: 10255269Abstract: Long short term memory units that accept a non-predefined number of inputs are used to provide natural language relation extraction over a user-specified range on content. Content written for human consumption is parsed with distant supervision in segments (e.g., sentences, paragraphs, chapters) to determine relationships between various words within and between those segments.Type: GrantFiled: December 30, 2016Date of Patent: April 9, 2019Assignee: MICROSOFT TECHNOLOGY LICENSING, LLCInventors: Christopher Brian Quirk, Kristina Nikolova Toutanova, Wen-tau Yih, Hoifung Poon, Nanyun Peng
-
Patent number: 10133728Abstract: The system that performs semantic parsing may automatically extract complex information from databases. Complex information may comprise nested event structures. In one example process, a processor may receive unannotated text and may access a natural-language database that includes nested events. The processor, in performing semantic parsing, may automatically generate syntactic trees that include annotations that represent the semantic information. In particular, the natural-language sentences and the database include nested event structures.Type: GrantFiled: March 20, 2015Date of Patent: November 20, 2018Assignee: Microsoft Technology Licensing, LLCInventors: Hoifung Poon, Kristina Toutanova, Ankur P. Parikh
-
Publication number: 20180189269Abstract: Long short term memory units that accept a non-predefined number of inputs are used to provide natural language relation extraction over a user-specified range on content. Content written for human consumption is parsed with distant supervision in segments (e.g., sentences, paragraphs, chapters) to determine relationships between various words within and between those segments.Type: ApplicationFiled: December 30, 2016Publication date: July 5, 2018Applicant: Microsoft Technology Licensing, LLCInventors: Christopher Brian Quirk, Kristina Nikolova Toutanova, Wen-tau Yih, Hoifung Poon, Nanyun Peng
-
Publication number: 20170351749Abstract: Systems, methods, and computer-readable media for providing entity relation extraction across sentences in a document using distant supervision. In some examples, a computing device can receive an input, such as a document comprising a plurality of sentences. The computing device can identify syntactic and/or semantic links between words in a sentence and/or between words in different sentences, and extract relationships between entities throughout the document. Techniques and technologies described herein populate a knowledge base (e.g., a table, chart, database etc.) of entity relations based on the extracted relationships. An output of the populated knowledge base can be used by a classifier to identify additional relationships between entities in various documents. Example techniques described herein can apply machine learning to train the classifier to predict relations between entities. The classifier can be trained using known entity relations, syntactic links and/or semantic links.Type: ApplicationFiled: June 3, 2016Publication date: December 7, 2017Inventors: Christopher Brian Quirk, Hoifung Poon
-
Publication number: 20170193157Abstract: Drug combinations offer promising treatment for some conditions such as cancer. However, the large number of available drug combinations makes it impractical to try all possible combinations. Machine-learning techniques described in this disclosure train a classification algorithm. Once trained, the classification algorithm uses genomic data from a specific patient to perform in silico tests of drugs and drug combinations against the genomic data to determine which therapies are likely to be effective for treating a condition of the specific patient.Type: ApplicationFiled: December 30, 2015Publication date: July 6, 2017Inventors: Christopher B. Quirk, Wen-tau Yih, Hoifung Poon, Kristina Toutanova, Stephen William Mayhew, Sheng Wang