Microsoft Technology Licensing, LLC

Matthew Brigham Hall

Michael C Fanning

Weizhu Chen

Pengcheng He

Evgeny Ivanovich Tvorun

Gary Linscott

Yu Zhao

Yuting Sun

Zheng Chen

Yi-Min Wang

Felix G T I Andrew

Kenneth A Showman

Eslam K Abdelreheem

Jiayuan Huang

Erik Andrew Saltwell

Junyan Chen

Ryan J Salva

Katherine Winant Osborne

Heather T Brown

Georgios Kounenis

Vikas Bahirwani

Jade Huang

Methods, systems, apparatuses, and computer program products are provided for extracting an entity value from a sentence. An embedding set that may include one or more sentence embeddings is generated for at least part of a first sentence that is tagged to associate a first named entity in the sentence with an entity type. A plurality of candidate embeddings is also generated for at least part of a second sentence. The one or more sentence embeddings in the embedding set may be compared with each of the plurality of candidate embeddings, and a match score may be assigned to each comparison to generate a match score set. A particular match score of the match score set may be identified that exceeds a similarity threshold, and an entity value of the entity type may be extracted from the second sentence associated with the identified match score.

Example based entity extraction, slot filling and value recommendation

A system for training and deploying an artificial conversational entity using an artificial intelligence (AI) based communications system is disclosed. The system may comprise a memory storing machine readable instructions. The system may also comprise a processor to execute the machine readable instructions to receive a request via an artificial conversational entity. The processor may also transmit a response to the request based on a dialog tree generated from at least a model-based action generator and a memory-based action generator. The processor may further provide a training option to a user in the event the response is suboptimal. The processor may additionally receive a selection from the user via the training option. The selection may be associated with an optimal response.

Interactive dialog training and communication system using artificial intelligence

A method includes parsing a text source document to construct a document node tree such that the document node tree includes text offsets indicating the location of the text within the text source document corresponding to each node of the document node tree. The method includes constructing, from the document node tree, a Document Object Model (DOM) and a view node tree that represents the DOM. The constructing of the view node tree includes mapping the view node tree to the document node tree. The method includes providing a running representation of the DOM such that DOM elements of the DOM are linked to the text within the text source document corresponding to the DOM elements via the view node tree and the document node tree.

Linking source code to running element

A method includes parsing a text source document to construct a document node tree such that the document node tree includes text offsets indicating the location of the text within the text source document corresponding to each node of the document node tree. The method includes constructing, from the document node tree, a Document Object Model (DOM) and a view node tree that represents the DOM. The constructing of the view node tree includes mapping the view node tree to the document node tree. The method includes providing a running representation of the DOM and one of tracking a modification to the DOM to provide first change information and tracking a modification to the text source document to provide second change information.

Dynamically updating a running page

A screen design user interface that may operate in an interactive mode and a design mode. The user interface includes a screen presentation portion for presenting an application screen under design, and a mode control for selecting between the interactive mode and the design mode. When the user interface is in interactive mode, the user interface actually allows interaction with one or more application element of a screen displayed in the screen presentation portion such that interaction with the corresponding application element causes execution of a corresponding function and thus a corresponding change in state of the screen. When the user interface is in design mode, the user interface supports design of the application screen by recognizing design gestures, but disables the application elements.

Application screen design allowing interaction

It may be advantageous to facilitate communication between two types of source code. For example, a wrapper may be generated to translate between managed source code and native source code. Current techniques may translate a single type of native source code into a managed binary wrapper. However, as provided herein, a managed source code wrapper may be generated based upon a variety of native source code formats. A native binary descriptor describing a set of native code may be received. A provider may be selected based upon the format of the set of native code. The provider may be executed upon the native binary descriptor to produce a common native binary description. A managed source code wrapper may be generated based upon the common native binary description. Because the managed source code wrapper may be in a textual source code format, a developer may easily maintain and/or customize the wrapper.

Source code wrapper generation

Growing community of inventors

Kenmore, WA, United States of America

Matthew Brigham Hall