Facebook, Inc.

Meta Platforms, Inc.

Meta Platforms Technologies, LLC

Wenhai Yang

Benoit F Dumoulin

Honglei Liu

Fuchun Peng

Rajen Subba

Anuj Kumar

Kun Han

Vivek Natarajan

David Scott Reiss

Kshitiz Malik

Nanshu Wang

Prince Gill

Brian Nelson

Ying Zhang

Emmanouil Koukoumidis

Antoine Roland Raux

Shawn C P Mei

Savas Parastatidis

Cheng Zhang

Vivek Narayanan

Stefan Nelson-Lindall

Laurent Nicolas Landowski

Michael Robert Hanson

Ou Jin

Pararth Paresh Shah

Julia Anne Framel

Aram Grigoryan

Irina-Elena Veliche

Fei Sha

Davide Testuggine

Brett Charles Groel

Wenxuan Li

In one embodiment, a method includes, by one or more computing systems, receiving, by an assistant xbot associated with the one or more computing systems, a user request for a content digest, retrieving one or more content objects corresponding to the user request, generating one or more slides for the one or more retrieved content objects, respectively, and providing, by the assistant xbot, instructions for presenting the content digest responsive to the request from the first user, wherein the content digest comprises the one or more slides, and wherein one or more of the slides of the content digest are removed from the content digest after a predetermined time period.

Ephemeral content digests for assistant systems

In one embodiment, a method includes training a target machine-learning model iteratively by accessing training data of content objects, training an intermediate machine-learning model that outputs contextual evaluation measurements based on the training data, generating state-indications associated with the training data, wherein the state-indications comprise user-intents, system actions, and user actions, training the target machine-learning model based on the contextual evaluation measurements, the state-indications, and an action set comprising possible system actions, extracting rules based on the target machine-learning model by a sequential pattern-mining model, generating synthetic training data based on the rules, updating the training data by adding the synthetic training data to the training data, determining if a completion condition is reached for the training, and if the completion condition is reached returning the target machine-learning model, else repeating the iterative training of the target machine-learning model.

Interpretability of deep reinforcement learning models in assistant systems

In one embodiment, a method includes receiving an indication of a trigger action by a first user at a client system, wherein the trigger action is associated with a priming content object, identifying related content objects associated with the priming content object, selecting recommended content objects based on the priming content object, the related content objects, and profile information of the first user, wherein each of the selected recommended content objects comprises entity information of entities associated with the priming content object, and presenting content suggestions at the client system, wherein each content suggestion comprises one of the selected recommended content objects.

Engaging users by personalized composing-content recommendation

Exemplary embodiments relate to methods, mediums, and systems for moving language models from a server to the client device. Such embodiments may be deployed in an environment where the server is not able to provide modeling services to the clients, such as an end-to-end encrypted (E2EE) environment. Several different techniques are described to address issues of size and complexity reduction, model architecture optimization, model training, battery power reduction, and latency reduction.

Methods, mediums, and systems for providing a model for an end-user device

Methods, mediums, and systems for training a model

Methods, mediums, and systems for representing a model in a memory of device

In one embodiment, a method includes accessing an input vector representing an input post, wherein: the vector space comprises clusters each associated with a topic; each cluster was determined based on a clustering of training-page vectors corresponding to training pages that each comprise training posts, each training post submitted by a user to a training page and comprises content selected by the user; and each training-page vector was generated by an ANN that was trained, based on the training posts of training pages associated with the ANN, to receive a post and then output a probability that the received post is related to the training posts of the training pages; determining that the input vector is located within a particular cluster in the vector space; and determining a topic of the input post based on the topic associated with the particular cluster that the input vector is located within.

Post topic classification

In one embodiment, a method includes receiving an indication of a trigger action by a first user, wherein the trigger action is associated with a priming content object, identifying one or more related content objects associated with the priming content object, generating a first feature vector representing the priming content object, the one or more related content objects, and profile information of the first user, accessing a plurality of second feature vectors representing a plurality of recommended content objects, respectively, selecting one or more of the recommended content objects based on comparisons between the first feature vector and the respective second feature vectors representing the recommended content objects, and sending, to a client system in response to the trigger action, instructions for presenting one or more content suggestions to the first user, wherein each content suggestion comprises one of the selected recommended content objects.

In one embodiment, a method includes, by one or more computing systems, receiving, from a client system associated with a user, a request from the user for a content digest from an online social network, retrieving one or more content objects associated with the online social network that are accessible by the user, selecting one or more of the retrieved content objects to incorporate into the content digest based on their identified categories, generating one or more slides for the one or more selected content objects, respectively, wherein each slide comprises a summary and representative image of the respective selected content object, sending, to the client system of the user, instructions for presenting the content digest responsive to the request from the user, wherein the content digest comprises the one or more slides.

In one embodiment, a method includes receiving a user request for a summarization of a particular type of content objects from a client system associated with a first user, determining one or more modalities associated with the user request, selecting a plurality of content objects of the particular type based on a user profile of the first user, wherein the user profile comprises one or more confidence scores associated with one or more subjects associated with the first user, respectively, and wherein the plurality of content objects are selected based on the one or more confidence scores, generating a summary of each content object based on the user profile and the determined modalities, and sending, to the client system in response to the user request, instructions for presenting the summaries of the plurality of content objects, wherein the summaries are presented via one or more of the determined modalities.

Generating personalized content summaries for users

A virtual assistant receives a message including message content from a client device. The virtual assistant determines an intent to organize an event and initial parameters for the event based on the message content. The virtual assistant retrieves a set of messages related to the received message from a data store and refines the initial parameters based on the related messages. A set of potential recommendations is generated based on the refined event parameters and the virtual assistant selects one or more of the potential recommendations to surface to users. The selected recommendations are sent to the client device for presentation to the user.

Determining and servicing user intent with a virtual assistant

A user interacts with a virtual digital assistant with the intent that it provides assistance with a task. The user sends messages to the virtual digital assistant that include content obtained via user input at a client device. An intent determination model is applied to the content to identify the user's intent. The virtual digital assistant identifies agents that are capable of servicing the intent are identified and retrieves contextual data relating to the message from a data store. An intent arbitration model is used to select one of the agents which is activated to provide assistance with the task. The contextual information may include global metrics of agent performance and/or information regarding the user's preferences.

Intent arbitration for a virtual assistant

Exemplary embodiments relate to methods, mediums, and systems for managing a conversation. In an embodiment, a computer-implemented input interface is provided to receive an input comprising information in natural language. A dialog manager is configured to determine an intent of the input, determine information to fulfill the intent, and identify one or both of information available to the dialog manager or information that is unavailable to the dialog manager. A conversational understanding document documents the intent and the identified information. An output interface forwards the conversational understanding document towards a task completion handler separate and distinct from the dialog manager. Other embodiments are described and claimed.

Conversational understanding

A system for answering user questions can provide answers from a knowledge base that stores question/answer pairs. These pairs can be associated with characteristics of the asking user so that, when subsequent users ask similar questions, answers can be selected that have been identified as most relevant to that type of user. The question/answer pairs in the knowledge base can be identified from social media posts where the original post contains a question and one or more comments on the post provide an answer. Posts can be identified as containing a question using a question classification model. A post comment can be identified as an answer based on: whether the question poster responded positively to the comment, whether the comment has similar keywords to the question, whether the comment has the characteristics of an answer, and how often a similar answer has been provided for similar questions.

Growing community of inventors

Mountain View, CA, United States of America

Wenhai Yang