Contextual speller models on online social networks
ID Hegerty, D Bernhardt, M Holland-Moritz… - US Patent …, 2018 - Google Patents
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 …
grams, determining for each n-gram if a contextual speller model indicates the n-gram is …
Spell correction with hidden markov models on online social networks
H Zhu, D Bernhardt - US Patent 10,049,099, 2018 - Google Patents
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 …
grams, where the n-grams include one or more misspelled n-grams, identifying one or more …
Dynamically generating recommendations based on social graph information
S Narayanan, S Singh, A Li - US Patent 9,223,879, 2015 - Google Patents
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 …
and edges; receiving a request from a first user corresponding to a first user node for a …
Search ranking and recommendations for online social networks based on reconstructed embeddings
B Green - US Patent 10,579,688, 2020 - Google Patents
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 …
or more objects matching the query; generating a reconstructed embedding of the query …
Recommendations from comments on online social networks
J Liu, EJ Virtue, GP Whalin - US Patent 10,452,671, 2019 - Google Patents
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 …
user of an online social network and parsing the text post to identify a query associated with …
Tensor-based deep relevance model for search on online social networks
A Jaech, HM Kamichetty, E Ringger… - US Patent …, 2019 - Google Patents
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 …
user, a search query com prising a number of query terms, generating a query match matrix …
Ontology models for identifying connectivity between entities in a social graph
N Goldman, JC Dingee - US Patent 8,739,016, 2014 - Google Patents
(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 …
PATENT DOCUMENTS people and uses an ontology to build a Social graph. The M …
Deep structured semantic model produced using click-through data
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 …
discriminatively trained based on click-through data, eg, such that a conditional likelihood of …
Pivoting from a graph of semantic similarity of documents to a derivative graph of relationships between entities mentioned in the documents
D Smith, RA Tacchi - US Patent 9,710,544, 2017 - Google Patents
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 …
of relationships between entities mentioned in the documents - Google Patents US9710544B1 …
Generating and using a knowledge-enhanced model
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 …
and knowledge data. In one case, the user-behavioral data identifies queries submitted by …