In one embodiment, a method includes receiving a search query including one or more n-
grams, determining for each n-gram if a contextual speller model indicates the n-gram is …

In one embodiment, a method includes receiving a search query including one or more n-
grams, where the n-grams include one or more misspelled n-grams, identifying one or more …

In one embodiment, a method includes maintaining access to information comprising nodes
and edges; receiving a request from a first user corresponding to a first user node for a …

In one embodiment, a method includes receiving a query inputted by a user; identifying one
or more objects matching the query; generating a reconstructed embedding of the query …

In one embodiment, a method includes receiving a text post from a client system of a first
user of an online social network and parsing the text post to identify a query associated with …

In one embodiment, a method includes receiving, from a client system associated with a
user, a search query com prising a number of query terms, generating a query match matrix …

(56) References Cited A system gathers information on important and influential US
PATENT DOCUMENTS people and uses an ontology to build a Social graph. The M …

A deep structured semantic module (DSSM) is described herein which uses a model that is
discriminatively trained based on click-through data, eg, such that a conditional likelihood of …

US9710544B1 - Pivoting from a graph of semantic similarity of documents to a derivative graph
of relationships between entities mentioned in the documents - Google Patents US9710544B1 …

Functionality is described herein for generating a model on the basis of user-behavioral data
and knowledge data. In one case, the user-behavioral data identifies queries submitted by …