Google Inc.

Yahoo! Inc.

Oath Inc.

Verizon Patent and Licensing Inc.

Excalibur Ip, LLC

Yahoo Assets LLC

Verizon Media Inc.

Idan Szpektor

Dan S Pelleg

Yoelle Smadja Maarek

Oleg Rokhlenko

Yossi Matias

Vladimir Vuskovic

David Carmel

David Kogan

Richard D Borovoy

Michael Fink

Asaf Revach

Eran Ofek

Deborah Cohen

Shimon Or Salant

Andrew Callahan

Andrew Richardson

Jeffrey Bonforte

Ido Guy

Gideon Dror

Alexander Nus

Shirin Oskooi

Jonathan Berant

Yuval David Pinter

Somesh Jain

Archit Shrivastava

Andrei Z Broder

Edo Liberty

Vishwanath Tumkur Ramarao

Mark Risher

Yehuda Arie Koren

Avihai Mejer

Yoelle Maarek Smadja

Adi Omari

Generating expanded responses that guide continuance of a human-to computer dialog that is facilitated by a client device and that is between at least one user and an automated assistant. The expanded responses are generated by the automated assistant in response to user interface input provided by the user via the client device, and are caused to be rendered to the user via the client device, as a response, by the automated assistant, to the user interface input of the user. An expanded response is generated based on at least one entity of interest determined based on the user interface input, and is generated to incorporate content related to one or more additional entities that are related to the entity of interest, but that are not explicitly referenced by the user interface input.

Generating a composite response to natural language input using a trained generative model and based on responsive content from disparate content agents

Disclosed are systems and methods for improving interactions with and between computers in content searching, generating, hosting and/or providing systems supported by or configured with personal computing devices, servers and/or platforms. The systems interact to identify and retrieve data within or across platforms, which can be used to improve the quality of data used in processing interactions between or among processors in such systems. The disclosure provides a novel, computerized framework for automatically identifying and recommending socially-engaging photos to their creators for sharing. Execution of the disclosed systems and methods turns a tedious manual chore into an automated, software-driven process. The disclosed systems and methods utilizes a novel, computerized learn-to-rank (LTR) algorithm for identifying the most engaging, socially driven photos by: (a) grouping near-duplicate photos; (b) selecting a representative photo for sharing per group; and (c) ranking of the groups by their likelihood to contain a 'shareable' photo.

Computerized system and method for automatically determining and providing digital content within an electronic communication system

Selectively generating expanded responses that guide continuance of a human-to-computer dialog

Methods and devices for assessing the quality of user-generated content are described. In one embodiment, a method is disclosed for measuring the quality of a user-generated answer to a question by combining various factors, including question-answer surface word vector similarity, question-answer explicit semantic analysis vector similarity, answer-answer explicit sematic analysis vector similarity, query performance predictor, sentiment analysis, textual analysis of the answer, and reputation of the answerer. The method uses a learning procedure to determine the best algorithm for measuring the overall quality of the answer based on these factors.

Quality-based scoring and inhibiting of user-generated content

Disclosed are systems and methods for improving interactions with and between computers in content searching, generating, hosting and/or providing systems supported by or configured with personal computing devices, servers and/or platforms. The systems interact to identify and retrieve data within or across platforms, which can be used to improve the quality of data used in processing interactions between or among processors in such systems. A novel, computerized framework for automatically identifying and recommending socially-engaging photos to their creators for sharing is provided. Execution of the disclosed framework turns a tedious manual chore into an automated, software-driven process. The disclosed framework utilizes a novel, computerized learn-to-rank (LTR) algorithm for identifying the most engaging, socially driven photos by: (a) grouping near-duplicate photos; (b) selecting a representative photo for sharing per group; and (c) ranking of the groups by their likelihood to contain a 'shareable' photo.

Briefly, example methods, apparatuses, and/or articles of manufacture are disclosed that may be implemented, in whole or in part, using one or more computing devices to facilitate and/or support one or more operations and/or techniques for in part, to facilitate and/or support one or more operations and/or techniques for ranking answers for on-line community questions.

Ranking answers for on-line community questions

Disclosed herein is a mechanism, which may be in a community-driven system, to assist a user, or member of the community, to articulate a request, such as a question, that is likely to receive a response, e.g., an answer to a question posed, from the user community. A machine learning approach may be used to generate a model, which model may be trained using previously-posted requests, e.g., questions, and response, e.g., answers. The generated model may be used to make a prediction, e.g., to predict a potential number of answers for a given question, which prediction may also have an accompanying confidence score. A prediction generated by the model may be presented to the user as the user is providing the input, e.g., typing a question. Such prediction may be generated for a partial question, e.g., as the question is being typed, as well as a completed question.

System and method of predicting community member responsiveness

Briefly, embodiments disclosed herein may relate to formulating synthetic questions, such as in response to a search query, for example. Candidate synthetic questions may be presented to a user who may initiate a search at least in part by selecting one or more candidate synthetic questions, for example, in an embodiment.

Synthetic question formulation

A content item presented to a user may involve two or more topics, such as news articles mentioning athletes or actors. Users may enjoy expressing opinions about a comparison of the topics, such as personal preferences or an evaluation of talent. Presented herein are techniques for automatically generating, for the content item, a poll among the topics of the content item. The respective comparisons of a comparison set are evaluated for the topics of the content item, and a comparison relevance score is computed identifying the relevance of the comparison of the topics. The comparison having the highest relevance for the topics is selected, and a comparison question is formulated and presented to the user with the content item. Results may be tabulated and presented for the topics of the content item. These techniques facilitate user expression about the content item without depending upon user-authored polls for each content item.

Automatically generated comparison polls

A system and method for learning a new user's interests in the absence of historical data includes: generating a user interface on which a user interacts in a session; formulating questions such that a user response to the questions indicates a preference; presenting the questions to the user on the user interface; receiving responses from the user, the responses indicating user preferences; and populating a new user profile with the user preferences. The steps of presenting, receiving, and populating are repeated until the session terminates.

Deriving a user profile from questions

Embodiments are directed towards identifying auto-folder tags for messages by using a combinational optimization approach of bi-clustering folder names and features of messages based on relationship strengths. The combinational optimization approach of bi-clustering, generally, groups a plurality of folder names and a plurality of features into one or more metafolders to optimize a cost. The cost is based on an aggregate of cut relationship strengths, where a cut results when a relationship folder name and feature are grouped in separate metafolders. Furthermore, the plurality of folder names and the plurality of features are obtained by monitoring actions of a plurality of users, where the folder names are user generated folder names and features are from a plurality of messages. The metafolders may be used to tag new user messages with an auto-folder tag.

Mining global email folders for identifying auto-folder tags

Growing community of inventors

Kfar Saba, Israel

Idan Szpektor