Facebook, Inc.

Meta Platforms, Inc.

Bo Zeng

Fuchun Peng

Benoit F Dumoulin

Haixun Wang

Kun Han

A computing device receives a message including a request for a recommendation. A representation of a hypothetical ideal recommendation to provide in response to the message is determined based on the message content. Data regarding entities that are potential recommendations are retrieved from a data store, the data regarding each entity including a representation of the entity (e.g., a vector) derived from factual information about the entity and opinions of other users of the entity. Ranking scores are determined for at least a subset of the entities based on the difference between the entity representations and the representation of the hypothetical ideal recommendation. An entity to recommend is selected based on the ranking scores and a reply to the message is sent that identifies the selected entity.

Combining machine-learning and social data to generate personalized recommendations

An online system receives a request to generate presentation content for presentation to a user. The online system receives a set of content items and identifies a surface for presenting the presentation information to the user. For example, the surface may be a voice only surface, a voice and graphical display, a graphical display only. Based on the identified surface, the online system ranks the set of content items. The online system then determines presentation information for a subset of the content items and transmits instructions to present the presentation information at the surface.

Applying templates to customize presentation of content based on surface type

In one embodiment, a method includes receiving a search query comprising one or more n-grams from a client system associated with a user of an online social network, generating one or more term embeddings representing the one or more n-grams of the search query, respectively, encoding the one or more term embeddings to generate a query embedding representing the search query, decoding the query embedding to generate one or more output term embeddings representing one or more query tokens, constructing a query command from the one or more output term embeddings, executing the query command to retrieve one or more search results, and sending, to the client system in response to the search query, instructions for generating a search-results interface for presentation to the user, the search-results interface comprising one or more of the retrieved search results.

Translating search queries on online social networks

In one embodiment, a method includes receiving a query including multiple n-grams; parsing the query to identify a subset of n-grams; generating, for each identified n-gram, an embedding of the n-gram; determining, for each identified n-gram, one or more word senses; calculating, for each word sense for each identified n-gram, a relatedness-score for the word sense based similarity metrics of the embedding of the word sense and the embeddings of each of the other word senses corresponding to the other identified n-grams; selecting, for each identified n-gram, one of the word senses determined for the identified n-gram having a highest relatedness-score; identifying objects matching at least a portion of the query; ranking each identified object based on a quality of matching of the object to selected word senses; and sending search results corresponding to one or more of the identified objects and having a rank greater than a threshold rank.

Growing community of inventors

Fremont, CA, United States of America

Bo Zeng