Microsoft Technology Licensing, LLC

Matteo Venanzi

John Guiver

Dmitriy Meyerzon

John Michael Winn

Alexander Armin Spengler

Ivan Korostelev

Vladimir V Gvozdev

Nikita Voronkov

Pavel Myshkov

Yordan Kirilov Zaykov

Elena Pochernina

Pushmeet Kohli

Omar Zia Khan

Milad Shokouhi

Hui Li

Samuel Alexander Webster

Jeffrey L Wight

Gabriella Kazai

Martin Kukla

Jan-Ove Almli Karlberg

Åge Andre Kvalnes

Helge Grenager Solheim

Tariq Sharif

Lynn Ayres

Mark Rolland Knight

Yamin Wang

Shobana Balakrishnan

Filip Andrzej Radlinski

Rachel Sirkin

Thomas Minka

Andrei-Alin Corodescu

Amy Huyen Phuoc Nguyen

Junyi Chai

Anthony Arnold Wieser

Robin Thomas

Katja Hofmann

Simon Thoresen Hult

Marius Bunescu

Thuy Thanh Duong

Chia-Jiun Tan

Christophe Jacky Henri Van Gysel

Andrei Razvan Popov

Noura Farra

Bhaskar Mitra

Omar Faruk

Sravya Narala

Grzegorz Stanislaw Kukla

Nicola Cancedda

Roy Rosemarin

Sri Ramya Mallipudi

Brian Brost

Sanil Rajput

In various examples there is a computer-implemented method of database construction. The method comprises storing a knowledge graph comprising nodes connected by edges, each node representing a topic. Accessing a topic type hierarchy comprising a plurality of types of topics, the topic type hierarchy having been computed from a corpus of text documents. One or more text documents are accessed and the method involves labelling a plurality of the nodes with one or more labels, each label denoting a topic type from the topic type hierarchy, by, using a deep language model; or for an individual one of the nodes representing a given topic, searching the accessed text documents for matches to at least one template, the template being a sequence of words and containing the given topic and a placeholder for a topic type; and storing the knowledge graph comprising the plurality of labelled nodes.

Knowledge base with type discovery

Examples of the present disclosure describe systems and methods for cross-provider topic conflation. In aspects, a request relating to one or more topics may be received by a content surfacing platform. One or more data sources of multiple content providers may be searched for documents relating to the topic(s). Document content (e.g., document metadata and sentences, phrases, and other word content within the document) relating to the topic(s) may be extracted from the documents of the various content providers. The document content may be classified and/or separated into subparts. The subparts may be clustered and/or conflated by topic, thereby removing duplicated data while preserving the unique information in each subpart. The conflated topics may be stored in a single knowledge base, such as an enterprise knowledge graph, and/or presented in response to the request.

Cross-provider topic conflation

In various examples there is an information retrieval system which has a memory storing an index of items, each item having one or more features of a plurality of features. The index includes, for each item, an indication of the features of that item; and is configured at least according to the features. The memory stores a plurality of questions about the features of the items. The information retrieval system has a question selector that selects at least one of the questions on the basis of at least an expected information gain of the question with respect to the items. A search component searches the index using answers to the selected questions received from a user.

Information retrieval system

Examples described herein generally relate to a computer system for generating a knowledge graph storing a plurality of entities and to displaying a topic page for an entity in the knowledge graph. The computer system performs a mining of source documents within an enterprise intranet to determine a plurality of entity names. The computer system generates an entity record within the knowledge graph for a mined entity name based on an entity schema and the source documents. The entity record includes attributes aggregated from the source documents. The computer system receives a curation action on the entity record from a first user. The computer system updates the entity record based on the curation action. The computer system displays an entity page including at least a portion of the attributes to a second user based on permissions of the second user to view the source documents.

Enterprise knowledge graph

Examples described herein generally relate to a computer system including a knowledge graph storing a plurality of entities. A mining of a set of enterprise source documents within an enterprise intranet is performed, by a plurality of knowledge mining toolkits, to determine a plurality of entity names. The plurality of entity names are linked based on entity metadata by traversing various relationships between people, files, sites, groups, associated with entities. An entity record is generated within a knowledge graph for a mined entity name from the linked entity names based on an entity schema and ones of the set of enterprise source documents associated with the mined entity name. The entity record includes attributes aggregated from the ones of the set of enterprise source documents associated with the mined entity name.

Enterprise knowledge graphs using multiple toolkits

Systems and methods are provided that automatically process a message input, construct an intelligent query based on the processing of the message input, and provide at least one attachable entity according to the processing results and the intelligent query. In some example aspects, a message is received. A natural language processor to determine if the message is requesting content may then process the message. If the message is determined to be requesting content, then candidate sub-queries may be generated to serve as a training set for a query that will be sent to an external search engine to retrieve the attachable entity. The sub-queries may be ranked in order of relevance and performance score. The highest ranked sub-queries may then be used in the actual query that is fired against the external search engine. The external search engine may search local and remote repositories for the top K most relevant attachable entities and present them to a user for attachment in a reply message.

Intelligent query system for attachments

Mining of a set of enterprise source documents within an enterprise intranet is performed, by a plurality of knowledge mining toolkits, to determine a plurality of entity names. A plurality of entity records are generated within a knowledge graph for mined entity names from the entity names based on an entity schema and ones of the set of enterprise source documents associated with the mined entity names. Pattern recognition is applied to an active document using an enterprise named entity recognition (ENER) system to identify potential entity names within the document that match a respective one of a plurality of entity records in the knowledge graph. One or more matching entity names are annotated within the document with information from the knowledge graph for the respective ones of the plurality of entity records. The annotated information is displayed with the active document.

Annotations for enterprise knowledge graphs using multiple toolkits

Examples described herein generally relate to a computer system including a knowledge graph storing a plurality of entities. The computer system compares source documents within an enterprise intranet to a plurality of templates defining potential entity attributes to identify extracts matching at least one of the plurality of templates. The computer system parses the extracts according to respective templates of the plurality of templates that match the extracts to determine instances. The computer system performs incremental clustering on a number of the instances to determine potential entity names. The computer system queries the knowledge graph with the potential entity names to obtain a set of candidate entity records. The computer system links the potential entity names with at least partial matching ones of the set of candidate entity records to define updated matching candidate entity records. The computer system updates the knowledge graph with the updated matching candidate entity records.

Incremental clustering for enterprise knowledge graph

Crowdsourcing using active learning is described, for example, to select pairs of tasks and groups of workers so that information gained about answers to the tasks in the pool is optimized. In various examples a machine learning system learns variables describing characteristics of communities of workers, characteristics of workers, task variables and uncertainty of these variables. In various examples, the machine learning system predicts task variables and uncertainty of the predicted task variables for possible combinations of communities of workers and tasks. In examples the predicted variables and uncertainty are used to calculate expected information gain of the possible combinations and to rank the possible combinations. In examples, the crowdsourcing system uses the expected information gain to allocate tasks to worker communities and observe the results; the results may then be used to update the machine learning system.

Adaptive task assignment

Crowdsourcing systems with machine learning are described. Specifically, item-label inference methods and systems are presented, for example, to provide aggregated answers to a crowdsourced task in a manner achieving good accuracy even where observed data about past behavior of crowd members is sparse. In various examples, an item-label inference system infers variables describing characteristics of both individual crowd workers and communities of the workers. In various examples, an item-label inference system provides aggregated labels while considering the inferred worker characteristics and the inferred characteristics of the worker communities. In examples the item-label inference system provides uncertainty information associated with the inference results for selecting workers and generating future tasks.

Crowdsourcing system with community learning

Crowdsourcing systems with machine learning are described, for example, to aggregate answers to a crowdsourced task in a manner achieving good accuracy even where observed data about past behavior of crowd members is sparse. In various examples a machine learning system jointly learns variables describing characteristics of both individual crowd workers and communities of the workers. In various examples, the machine learning system learns aggregated labels. In examples learnt variables describing characteristics of an individual crowd worker are related, by addition of noise, to learnt variables describing characteristics of a community of which the individual is a member. In examples the crowdsourcing system uses the learnt variables describing characteristics of individual workers and of communities of workers for any one or more of: active learning, targeted training of workers, targeted issuance of tasks, calculating and issuing rewards.

Growing community of inventors

Southampton, United Kingdom

Matteo Venanzi