Abstract: In an embodiment, a method includes receiving, via a processor of a first compute device, a representation of a set of inputs and a set of outputs that were generated by inputting the set of inputs into a machine learning (ML) model by a set of compute devices not including the first compute device to generate the set of outputs. The method further includes receiving, via the processor, a request for a machine learning (ML) explanation associated with the ML model and at least one explicand. The method further includes generating, via the processor and without using the ML model, a representation of the ML explanation based on the at least one explicand, the set of inputs, and the set of outputs.

Abstract: A system for real-time search, including: a set of partitions, each including a set of segments, each segment corresponding to a time slice of messages posted to the messaging platform, and a real-time search engine configured to receive a search term in parallel with other partitions in set the set of partitions, and search at least one of the set of segments in reverse chronological order of the corresponding time slice to identify document identifiers of messages containing the search term; and a search fanout module configured to: receive a search query including the search term; send the search term to each of the set of partitions for parallel searching; and return, in response to the search query, at least one of the identified document identifiers of messages containing the search term.

Abstract: A system for real-time search, including: a set of partitions, each including a set of segments, each segment corresponding to a time slice of messages posted to the messaging platform, and a real-time search engine configured to receive a search term in parallel with other partitions in the set of partitions, and search at least one of the set of segments in reverse chronological order of the corresponding time slice to identify document identifiers of messages containing the search term; and a search fanout module configured to: receive a search query including the search term; send the search term to each of the set of partitions for parallel searching; and return, in response to the search query, at least one of the identified document identifiers of messages containing the search term.

Abstract: A system for real-time search, including: a set of partitions, each including a set of segments, each segment corresponding to a time slice of messages posted to the messaging platform, and a real-time search engine configured to receive a search term in parallel with other partitions in set the set of partitions, and search at least one of the set of segments in reverse chronological order of the corresponding time slice to identify document identifiers of messages containing the search term; and a search fanout module configured to: receive a search query including the search term; send the search term to each of the set of partitions for parallel searching; and return, in response to the search query, at least one of the identified document identifiers of messages containing the search term.

Abstract: A system for real-time search, including: a set of partitions, each including a set of segments, each segment corresponding to a time slice of messages posted to the messaging platform, and a real-time search engine configured to receive a search term in parallel with other partitions in the set of partitions, and search at least one of the set of segments in reverse chronological order of the corresponding time slice to identify document identifiers of messages containing the search term; and a search fanout module configured to: receive a search query including the search term; send the search term to each of the set of partitions for parallel searching; and return, in response to the search query, at least one of the identified document identifiers of messages containing the search term.

Abstract: A method and system for facilitating typeahead. The method can include: identifying a set of topics and/or connected accounts; storing, based on one or more signals associated with a user account, a portion of the topics and/or connected accounts in a cache; and using the cache to provide typeahead suggestions to a client in response to a request associated with the user account.

Abstract: A system, method, and computer-readable medium for identifying relevant content from a messaging platform. The method can include: identifying a context account; identifying a set of initial accounts of the messaging platform; selecting a set of relevant accounts from among the set of initial accounts; selecting a set of messages authored by the set of relevant accounts based at least on a recency of each of the set of messages; and providing the set of messages in response to a request.

Abstract: A system, method, and computer-readable medium for identifying relevant content from a messaging platform. The method can include: identifying a context account; identifying a set of initial accounts of the messaging platform; selecting a set of relevant accounts from among the set of initial accounts; selecting a set of messages authored by the set of relevant accounts based at least on a recency of each of the set of messages; and providing the set of messages in response to a request.

Abstract: A method and system for facilitating typeahead. The method can include: identifying a set of topics and/or connected accounts; storing, based on one or more signals associated with a user account, a portion of the topics and/or connected accounts in a cache; and using the cache to provide typeahead suggestions to a client in response to a request associated with the user account.

Abstract: A system, method, and computer-readable medium for identifying relevant content from a messaging platform. The method can include: identifying a context account; identifying a set of initial accounts of the messaging platform; selecting a set of relevant accounts from among the set of initial accounts; selecting a set of messages authored by the set of relevant accounts based at least on a recency of each of the set of messages; and providing the set of messages in response to a request.

Abstract: A method and system for facilitating typeahead. The method can include: identifying a set of topics and/or connected accounts; storing, based on one or more signals associated with a user account, a portion of the topics and/or connected accounts in a cache; and using the cache to provide typeahead suggestions to a client in response to a request associated with the user account.

Abstract: A system for real-time search, including: a set of partitions, each including a set of segments, each segment corresponding to a time slice of messages posted to the messaging platform, and a real-time search engine configured to receive a search term in parallel with other partitions in the set of partitions, and search at least one of the set of segments in reverse chronological order of the corresponding time slice to identify document identifiers of messages containing the search term; and a search fanout module configured to: receive a search query including the search term; send the search term to each of the set of partitions for parallel searching; and return, in response to the search query, at least one of the identified document identifiers of messages containing the search term.

Abstract: A method for suggesting related queries to a user query using semantic relationships that are present in informational content stored in public domains. Semantic relationships between named entities are discovered and the named entities are extracted. The entities are indexed according to the relationships. When a user query is received that includes one of the entities, query suggestions are returned to the user based on indexed relationships corresponding to the entity named in the user query.

Abstract: Embodiments of the invention disclose an advertisement or segment of a webpage that displays suggested search queries as selectable links. Suggested queries may be based on content associated with the webpage, or the description of the webpage (such as a URL), or default suggestions. In one example, content of a page is crawled for terms that are mapped to suggested queries. Queries may be represented as textual links or multimedia images embedded in pages accessed over a network, and selection of a query may direct or enhance search engine traffic.

Abstract: A method for suggesting related queries to a user query using semantic relationships that are present in informational content stored in public domains. Semantic relationships between named entities are discovered and the named entities are extracted. The entities are indexed according to the relationships. When a user query is received that includes one of the entities, query suggestions are returned to the user based on indexed relationships corresponding to the entity named in the user query.