Microsoft Technology Licensing, LLC

100.co, LLC

Sansa Al Inc.

Idibon, Inc.

100.co Technologies, Inc.

Tyler J Schnoebelen

Robert J Munro

Brendan D Callahan

Jason Brenier

Paul A Tepper

Schuyler D Erle

Jessica D Long

Edgar Nunez

Erez Kikin-Gil

Christine Anderson

Gary C King

Sara Liu Yang

Thomas Jan Stovicek

Sandra Hirsh

Wendy Chan

Nancy Jane Bell

Eliot Carleton Gillum

Krishna C Vitaldevara

Christopher Walker

Tripti Saxena

Rebecca Ping Zhu

Sarah K Luger

Andrew Gilchrist-Scott

Veena Basavaraj

Haley Most

Jackie Sandoval

Ross Mechanic

Sanchan Sahai Saxena

Omar H Shahine

Stefan Krawczyk

James B Robinson

Michelle Casbon

Ujjwal Sarin

Aneesh Nair

Martha G Hinrichs

Systems and methods are presented for the automatic placement of rules applied to topics in a logical hierarchy when conducting natural language processing. In some embodiments, a method includes: accessing, at a child node in a logical hierarchy, at least one rule associated with the child node; identifying a percolation criterion associated with a parent node to the child node, said percolation criterion indicating that the at least one rule associated with the child node is to be associated also with the parent node; associating the at least one rule with the parent node such that the at least one rule defines a second factor for determining whether the document is to also be classified into the parent node; accessing the document for natural language processing; and determining whether the document is to be classified into the parent node or the child node based on the at least one rule.

Methods and systems for modeling complex taxonomies with natural language understanding

Methods and systems are disclosed for creating and linking a series of interfaces configured to display information and receive confirmation of classifications made by a natural language modeling engine to improve organization of a collection of documents into an hierarchical structure. In some embodiments, the interfaces may display to an annotator a plurality of labels of potential classifications for a document as identified by a natural language modeling engine, collect annotated responses from the annotator, aggregate the annotated responses across other annotators, analyze the accuracy of the natural language modeling engine based on the aggregated annotated responses, and predict accuracies of the natural language modeling engine's classifications of the documents.

Graphical systems and methods for human-in-the-loop machine intelligence

Methods, apparatuses and computer readable medium are presented for generating a natural language model. A method for generating a natural language model comprises: selecting from a pool of documents, a first set of documents to be annotated; receiving annotations of the first set of documents elicited by first human readable prompts; training a natural language model using the annotated first set of documents; determining documents in the pool having uncertain natural language processing results according to the trained natural language model and/or the received annotations; selecting from the pool of documents, a second set of documents to be annotated comprising documents having uncertain natural language processing results; receiving annotations of the second set of documents elicited by second human readable prompts; and retraining a natural language model using the annotated second set of documents.

Optimization techniques for artificial intelligence

Providing a user interface (UI) on a web page. A toolbar section is defined on the web page. The web page includes a content section being different and separate from the toolbar section, and the content section displays additional content of the web page. One or more groups are specified to include one or more action controls associated therewith. Each of the specified groups has a group identifier associated therewith. The one or more action controls are displayed according to the specified groups in the toolbar section of the web page. Each of the one or more displayed action controls includes properties associated therewith, and the included properties define at least one of the following: a name of the action control, a link of the action control, the group identifier of the action control, and a classification identifier of the action control.

Extensible and application-adaptable toolbar for web services

Methods are presented for generating a natural language model. The method may comprise: ingesting training data representative of documents to be analyzed by the natural language model, generating a hierarchical data structure comprising at least two topical nodes within which the training data is to be subdivided into by the natural language model, selecting a plurality of documents among the training data to be annotated, generating an annotation prompt for each document configured to elicit an annotation about said document indicating which node among the at least two topical nodes said document is to be classified into, receiving the annotation based on the annotation prompt; and generating the natural language model using an adaptive machine learning process configured to determine patterns among the annotations for how the documents in the training data are to be subdivided according to the at least two topical nodes of the hierarchical data structure.

Methods for generating natural language processing systems

Email tags are described. In embodiments, email messages are received for distribution to client devices that correspond to respective recipients of the email messages. Email routing decisions are applied to route an email message to an email folder for a recipient of the email message, where the email folder may include an email inbox, a junk folder, or a user-created folder. The email message is then tagged with an email tag to generate a tagged email message. The email tag includes a routing description that indicates why the email message was routed to the particular email folder.

Email tags

Focusing electronic mail messages in a list of messages. Category information is received for classifying particular e-mail messages or senders of the messages in the list of e-mail messages according to a category. The method also includes setting a status data associated with each of the particular messages. The status data indicates the category classified by the user. A first instruction is received from the user for focusing the particular messages according to the category. The particular messages having the status data therewith in the list are focused collectively without altering a preexisting order of the messages in the list.

Inbox with focused messages according to categories

Growing community of inventors

San Francisco, CA, United States of America

Tyler J Schnoebelen