Abstract: In one embodiment, a method includes receiving, at a client system, an audio input, where the audio input comprises a coreference to a target object, accessing visual data from one or more camera associated with the client system, where the visual data comprises images portraying one or more objects, resolving the coreference to the target object from among the one or more objects, resoling the target object to a specific entity, and providing, at the client system, a response to the audio input, where the response comprises information about the specific entity.

Abstract: In one embodiment, a method includes receiving, by a first client system, from one or more remote servers, a current version of a neural network model including multiple model parameters, training the neural network model on multiple examples retrieved from a local data store to generate multiple updated model parameters, wherein each of the examples includes one or more features and one or more labels, calculating a user valuation associated with the first client system, wherein the user valuation represents a measure of utility of training the neural network model on the multiple examples, and sending, to one or more of the remote servers, the trained neural network model and the user valuation, wherein the user valuation is associated with a likelihood of the first client system being selected for a subsequent training of the neural network model.

Abstract: In one embodiment, a method includes receiving a user request from a client system associated with a user, determining that the user request corresponds to a first suspended task, retrieving a first dialog state of the first suspended task from a dialog history associated with the user, generating a summary of the first suspended task based on the first dialog state using a natural-language generating (NLG) module, and sending instructions to the client system for providing the summary of the first suspended task to the user.

Abstract: A caption of a multimodal message (e.g., social media post) can be identified as a named entity using an entity recognition system. The entity recognition system can use an attention-based mechanism that emphasis or de-emphasizes each data type (e.g., image, word, character) in the multimodal message based on each datatypes relevance. The output of the attention mechanism can be used to update a recurrent network to identify one or more words in the caption as being a named entity.

Abstract: In one embodiment, a method includes receiving a first user input from a user from a client system associated with the user, accessing a memory-data store comprising digital memories, wherein each digital memory comprises media content items, temporal information associated with the media content items, and relational information pointing to second digital memories, selecting priming digital memories from the digital memories based on the first user input, proactively selecting related digital memories based on the relational information associated with the priming digital memories, generating a priming response based on the priming digital memories and a proactive suggestion based on the related digital memories, and sending instructions for presenting the priming response and the proactive suggestion to the client system responsive the first user input.

Abstract: A system for user behavior prediction generates a first series of behavior event elements describing a first set of behaviors of one or more users, upon processing user interactions with an online system. In a first flow, the system generates a first series of time-distributed embeddings of the behavior event elements, and in a second flow parallel with the first flow, the system generates a proposed future embedding of a proposed future behavior of a user at a future time point subsequent to the first set of time points. Using a predictive model (e.g., a recursive neural network), the system transforms components of the first and second flows into an output describing plausibility of occurrence of the proposed future behavior of the user.

Abstract: A caption of a multimodal message (e.g., social media post) can be identified as a named entity using an entity recognition system. The entity recognition system can use an attention-based mechanism that emphasis or de-emphasizes each data type (e.g., image, word, character) in the multimodal message based on each datatypes relevance. The output of the attention mechanism can be used to update a recurrent network to identify one or more words in the caption as being a named entity.

Abstract: In one embodiment, a method includes receiving, from a client system associated with a user, a user request comprising a reference to a target object, accessing visual data from the client system, wherein the visual data comprises images portraying the target object and one or more additional objects, and wherein attribute information of the target object is recorded in a multimodal dialog state, resolving the reference to the target object based on the attribute information recorded in the multimodal dialog state, determining relational information between the target object and one or more of the additional objects portrayed in the visual data, and sending, to the client system, instructions for presenting a response to the user request, wherein the response comprises the attribute information and the determined relational information.

Abstract: In one embodiment, a method includes receiving a user request from a client system associated with a user, generating a response to the user request which references one or more entities, generating a personalized recommendation based on the user request and the response, wherein the personalized recommendation references one or more of the entities of the response, and sending instructions for presenting the response and the personalized recommendation to the client system.

Abstract: In one embodiment, a method includes receiving, from a client system associated with a user, a user request comprising a reference to a target object, accessing visual data from the client system, wherein the visual data comprises images portraying the target object and one or more additional objects, and wherein attribute information of the target object is recorded in a multimodal dialog state, resolving the reference to the target object based on the attribute information recorded in the multimodal dialog state, determining relational information between the target object and one or more of the additional objects portrayed in the visual data, and sending, to the client system, instructions for presenting a response to the user request, wherein the response comprises the attribute information and the determined relational information.

Abstract: In one embodiment, a method includes receiving a query from a user from a client system associated with the user, determining one or more initial memory slots based on the query, accessing a memory graph associated with the user which comprises a plurality of nodes and a plurality of edges connecting the nodes, and wherein one or more of the nodes correspond to one or more episodic memories of the user, respectively, and wherein each edge corresponds to a relationship between the connected nodes, selecting one or more candidate nodes from the memory graph by one or more machine-learning models based on the initial memory slots, generating a response based on the initial memory slots and episodic memories corresponding to the selected candidate nodes, and sending instructions for presenting the response to the client system in response to the query.

Abstract: In one embodiment, a method includes receiving a user request from a client system associated with a user, generating a response to the user request which references one or more entities, generating a personalized recommendation based on the user request and the response, wherein the personalized recommendation references one or more of the entities of the response, and sending instructions for presenting the response and the personalized recommendation to the client system.

Abstract: In one embodiment, a method includes receiving a user request from a client system associated with a user, generating a response to the user request which references one or more entities, generating a personalized recommendation based on the user request and the response, wherein the personalized recommendation references one or more of the entities of the response, and sending instructions for presenting the response and the personalized recommendation to the client system.

Abstract: In one embodiment, a method includes receiving a user request from a client system associated with a user, generating a response to the user request which references one or more entities, generating a personalized recommendation based on the user request and the response, wherein the personalized recommendation references one or more of the entities of the response, and sending instructions for presenting the response and the personalized recommendation to the client system.

Abstract: A machine learning based system can identify an entity as the likely subject of a multimodal message (e.g., a social media post having a short text phrase overlaid on an image) by creating embeddings for an image of the multimodal message and one or more string embeddings from text of the multimodal message. The embeddings can be weighted to maximize information gain, then recombined and compared against a result embedding database to identify an entity as the subject of the multimodal message.

Abstract: In one embodiment, a method includes receiving, at a client system, an audio input, where the audio input comprises a coreference to a target object, accessing visual data from one or more camera associated with the client system, where the visual data comprises images portraying one or more objects, resolving the coreference to the target object from among the one or more objects, resoling the target object to a specific entity, and providing, at the client system, a response to the audio input, where the response comprises information about the specific entity.

Abstract: In one embodiment, a system includes an automatic speech recognition (ASR) module, a natural-language understanding (NLU) module, a dialog manager, one or more agents, an arbitrator, a delivery system, one or more processors, and a non-transitory memory coupled to the processors comprising instructions executable by the processors, the processors operable when executing the instructions to receive a user input, process the user input using the ASR module, the NLU module, the dialog manager, one or more of the agents, the arbitrator, and the delivery system, and provide a response to the user input.

Abstract: A machine learning based system can identify an entity as the likely subject of a multimodal message (e.g., a social media post having a short text phrase overlaid on an image) by creating embeddings for an image of the multimodal message and one or more string embeddings from text of the multimodal message. The embeddings can be weighted to maximize information gain, then recombined and compared against a result embedding database to identify an entity as the subject of the multimodal message.

Abstract: In one embodiment, a method includes accessing visual data from a client system associated with a user, wherein the visual data comprises images portraying one or more objects, receiving, from the client system, a user request, wherein the user request comprises a coreference to a target object, resolving the coreference to the target object from among the one or more objects, resolving the target object to a specific entity, and sending, to the client system, instructions for providing a response to the user request, wherein the response comprises attribute information about the specific entity.

Abstract: In one embodiment, a method includes receiving a query from a user from a client system associated with the user, accessing a knowledge graph comprising a plurality of nodes and edges connecting the nodes, wherein each node corresponds to an entity and each edge corresponds to a relationship between the entities corresponding to the connected nodes, determining one or more initial entities associated with the query based on the query, selecting one or more candidate nodes by a conversational reasoning model from the knowledge graph corresponding to one or more candidate entities, respectively, wherein each candidate node is selected based on the nodes corresponding to the initial entities, dialog states associated with the query, and a context associated with the query, generating a response based on the initial entities and the candidate entities, and sending instructions for presenting the response to the client system in response to the query.