Microsoft Technology Licensing, LLC

Other

Hisami Suzuki

William B Dolan

Simon H Corston-Oliver

Jianfeng Gao

Omar Zia Khan

Kristina Nikolova Toutanova

Joshua T Goodman

Ruhi Sarikaya

Lisa Joy Stifelman

Christopher Brian Quirk

Alice Jane Bernheim Brush

Christopher John Brockett

Imed Zitouni

Lucretia Henrica Vanderwende

Young-Bum Kim

Patrick H Halstead, Jr

Gary Kacmarcik

Paul Anthony Crook

Wen-tau Yih

Vipul Agarwal

Vikram Reddy Dendi

Oliver Scholz

Pallavi Choudhury

Ravi Kumar Bikkula

Asli Celikyilmaz

Achraf Chalabi

James Francis Gilsinan, Iv

Zhaleh Feizollahi

Robert Juan Miller

Satoshi Sekine

Karl Rolando Henderson, Jr

Nikhil Rajkumar Jain

Hanjiang Zhou

Danko Panic

Nikhil Ramesh

Alexandre Rochette

Paul Crook

A primary virtual assistant and local virtual assistant herein can provide secondary information, including, without limitation, user-specific information, without having direct access to such information. For example, a user may invoke a secondary virtual assistant, through the local virtual assistant connected to a primary virtual assistant system. This invocation may be sent through the primary virtual assistant to the third party provider, i.e., the secondary virtual assistant. The secondary virtual assistant has access to the secondary information, for example, email, calendars, other types of information specifically associated with the user or learned from past user actions while this information is not directly available to the primary virtual assistant. This secondary information is then provided to the local virtual assistant in response to the invocation to be provided to the user.

Personalized updates upon invocation of a service

Systems and methods are disclosed for personalized communications using semantic memory. In one implementation, a first communication is received from a user and processed to identify a first content element within the communication. The first content element is associated with a second content element within a content repository. A second communication that includes the first content element is received from the user. Based on an association between the first content element and the second content element within the content repository, a third communication that includes the second content element is generated and provided to the user in response to the second communication.

Personalized communications using semantic memory

Methods and systems are provided for collaborative completion of tasks using task frames. Upon receiving a request to perform a task, a system utilizes task frames in completing the requested task. A task frame is a data structure that contains the parameters and status signals that represent a particular task and captures the combined system's understanding of a current state of the task. Input is received at a client device and sent to a server, where the input is processed. Based on the processed input, a task frame is retrieved and filled. The filled task frame is sent to the client device, where the client device performs actions based on the task frame and updates the task frame parameters and the state of the task. The updated task frame is returned to the server. The shared task frame provides improvements to the overall task completion process.

Building multimodal collaborative dialogs with task frames

The universal text input technique described herein addresses the difficulties of typing text in various languages and scripts, and offers a unified solution, which combines character conversion, next word prediction, spelling correction and automatic script switching to make it extremely simple to type any language from any device. The technique provides a rich and seamless input experience in any language through a universal IME (input method editor). It allows a user to type in any script for any language using a regular qwerty keyboard via phonetic input and at the same time allows for auto-completion and spelling correction of words and phrases while typing. The technique also provides a modeless input that automatically turns on and off an input mode that changes between different types of script.

Universal text input

Grammatical element prediction is used in the context of machine translation. Features from both the source language and the target language sentences (or other text fragments) are used in predicting the grammatical elements.

Grammatical element generation in machine translation

Methods are disclosed for acquiring ontological knowledge using query logs. In one embodiment, query logs are first utilized as a basis for identifying important contexts associated with terms belonging to a semantic category. Then, those contexts are as a basis for identifying new terms belonging to the same category or, in another embodiment, as a basis for removing extraneous or obsolete terms identified as being in the same category.

Acquiring ontological knowledge from query logs

Grammatical element prediction is used to predict grammatical elements in text fragments (such as phrases or sentences). In one embodiment, a statistical model, using syntax features, is used to predict grammatical elements.

Generating grammatical elements in natural language sentences

Document summarization is performed by scoring individual words in sentences in a document or document cluster. Sentences from the document or document cluster are selected to form a summary based on the scores of the words contained in those sentences.

Document summarization by maximizing informative content words

A method of training language model parameters trains discriminative model parameters in the language model based on a performance measure having discrete values.

Discriminative training for language modeling

A system is utilized for determining a relationship between first and second textual inputs. The system identifies constituents in the first textual input, having predetermined characteristics indicative of usefulness in determining the relationship. The relationship is then determined based on the constituents identified. The constituents can be eliminated from the first textual input, weighted in the first textual input, or simply annotated in one of a variety of ways.

System for improving the performance of information retrieval-type tasks by identifying the relations of constituents

Growing community of inventors

Redmond, WA, United States of America

Hisami Suzuki