Abstract: Described herein are systems and methods for generating an embedding—a learned representation—for an image. The embedding for the image is derived to capture visual aspects, as well as textual aspects, of the image. An encoder-decoder is trained to generate the visual representation of the image. An optical character recognition (OCR) algorithm is used to identify text/words in the image. From these words, an embedding is derived by performing an average pooling operation on pre-trained embeddings that map to the identified words. Finally, the embedding representing the visual aspects of the image is combined with the embedding representing the textual aspects of the image to generate a final embedding for the image.

Abstract: Disclosed are systems, methods, and non-transitory computer-readable media for expanding search queries. A search system executes a search query based on a search term and the geographic indicator. In response to determining that a number of the search results is less than a threshold number, the search system determines, based on historical search logs from other users in the first geographic region, a likelihood value indicating a likelihood that the other users in the first geographic region expanded the geographic region of their search queries. The search system compares the likelihood value to a threshold likelihood value, and determines, based on the comparison, that the likelihood value meets or exceeds the threshold likelihood value. The search system then executes an expanded search based on the search term and an expanded geographic indicator that encompasses the first geographic region.

Abstract: In an example, features in a boosting decision tree model are initialized to zero, the boosting decision tree model located in a GLMM and connected to a deep neural network collaborative filtering model via a prediction layer. While the features in the boosting decision tree model remain zero, the deep neural network collaborative filtering model is trained. One or more trees in the boosting decision tree model are boosted using logits produced by the training of the deep neural network collaborative filtering model as a margin. The prediction layer is trained using features from the deep neural network collaborative filtering model and features from the boosting decision tree model. It is then determined whether a set of convergence criteria is met. If not, then the deep neural network collaborative filtering model is retrained using the features and the process is repeated until the set of convergence criteria is met.

Abstract: The disclosed embodiments illustrate methods and systems for searching for a first user. The one or more inputs pertaining to one or more first attributes of the first user are received. Further, the one or more first attributes of the first user are ranked based on at least a presence of the one or more first attributes among one or more second attributes pertaining to one or more second users. Thereafter, one or more search strings comprising at least one attribute selected from the ranked one or more first attributes are generated, wherein the one or more search strings are utilizable to search for the first user. Finally, a list of third users is obtained from one or more search engines in response to the one or more search strings.

Abstract: A method, non-transitory computer readable medium, and apparatus for recommending a topic-cohesive and interactive implicit community are disclosed. For example, the method receives a request for customer care, selects an implicit community identified from a plurality of individual users of a social media website based upon a relevance score related to a topic of the request for customer care and recommends the implicit community in response to the request for customer care.

Abstract: Disclosed are systems, methods, and non-transitory computer-readable media for expanding search queries. A search system executes a search query based on a search term and the geographic indicator. In response to determining that a number of the search results is less than a threshold number, the search system determines, based on historical search logs from other users in the first geographic region, a likelihood value indicating a likelihood that the other users in the first geographic region expanded the geographic region of their search queries. The search system compares the likelihood value to a threshold likelihood value, and determines, based on the comparison, that the likelihood value meets or exceeds the threshold likelihood value. The search system then executes an expanded search based on the search term and an expanded geographic indicator that encompasses the first geographic region.

Abstract: In an example embodiment, a machine learning algorithm is used to train a deep semantic similarity neural network to output a semantic similarity score between a candidate job search query and a candidate job search result. This semantic similarity score can then be used in a ranking phase to rank job search results in response to a first job search query.

Abstract: Disclosed are systems, methods, and non-transitory computer-readable media for expanding search queries. A search system executes a search query based on a search term and the geographic indicator. In response to determining that a number of the search results is less than a threshold number, the search system determines, based on historical search logs from other users in the first geographic region, a likelihood value indicating a likelihood that the other users in the first geographic region expanded the geographic region of their search queries. The search system compares the likelihood value to a threshold likelihood value, and determines, based on the comparison, that the likelihood value meets or exceeds the threshold likelihood value. The search system then executes an expanded search based on the search term and an expanded geographic indicator that encompasses the first geographic region.

Abstract: Disclosed are systems, methods, and non-transitory computer-readable media for expanding search queries. A search system determines a set of candidate alternate search terms based on historical search logs that include records of previously submitted search terms, corresponding search results that were presented to users, and corresponding search results that were selected by the users. The set of candidate alternate search terms is selected from titles of the corresponding search results that were selected by the users. The search system ranks the set of candidate alternate search terms based on determined probabilities that each of the alternate candidate search terms will be selected if presented to a user, and selects a first candidate alternate search term from the set of candidate alternate search terms based on the ranking. The search system generates an expanded search term based on the first candidate alternate search term.

Abstract: In an example embodiment, a machine learning algorithm is used to train a query-based deep semantic similarity neural network to output a query context vector in a vector space that includes both query context vectors and document context vectors. Both the query context vectors and document context vectors are clustered using a clustering algorithm. When an input search query is obtained, the input search query is also passed into the query-based deep semantic similarity neural network and its output document context vector assigned to a first cluster based on the clustering algorithm. Documents within the first cluster are then retrieved in response to the input search query.

Abstract: A method and a system are provided for correlation detection in multiple spatio-temporal datasets for event sensing in a geographical area. The method includes extracting datasets, comprising information about one or more events, from one or more data sources. The method further includes identifying a primary data source and secondary data sources from the one or more data sources. The method further includes extracting primary features from the datasets associated with the primary data source and secondary features from the datasets associated with the secondary data sources. The primary features are categorized into one or more categories. The method further includes training classifiers based on the primary features and/or the one or more categories. The method further includes detecting a correlation among the information associated with the one or more events based on a category transfer distribution from the primary data source to the secondary data sources.

Abstract: Method and system to generate multiple entity aware typeahead suggestions is provided. The system is configured to use multiple Finite State Transducers (FSTs) to examine an input string submitted by a user via a search box, and to generate one or more typeahead suggestions based on the results of the examination. Different FSTs are constructed with respect to strings identified as associated with different entity types. At least one of the typeahead suggestions includes a portion associated with one entity type and a portion associated with a different entity type.

Abstract: A method for assigning a topic to a collection of microblog posts may include, by an acquisition module, receiving from at least one messaging service server, a plurality of posts, wherein each of the plurality of posts comprise post content; by a generation module, analyzing the posts and extract, from at least one of the posts, a link with an address to an external document; and, by the acquisition module, accessing the external document that is associated with the address and fetch external content associated with the document. The method may also include by the generation module: analyzing the post content to identify at least one label for each post, for each post that includes a link, analyzing the external content to identify a topic, and using a topic modeling technique to generate a trained topic model comprising a plurality of topics and a plurality of associated words.

Abstract: The disclosed embodiments illustrate methods and systems for processing social media data for content recommendation to a user. The method includes extracting a set of entity data from the social media data of the user. The method further includes extracting semantic data of each entity data in the extracted set of entity data from one or more knowledge databases over a communication network. The method further includes generating a user-interest vector of the user. The user-interest vector of the user is generated based on at least a mapping of the extracted semantic data of each entity data with one or more leaf nodes in an interest taxonomy. The generated user-interest vector is further utilized for recommending targeted content to the user.

Abstract: In some embodiments, the disclosed subject matter involves techniques for generating personalized query suggestions for a user in a specific subject or application domain that are ranked using confidence levels and contextual scoring. Partial query strings may be parsed for literal matching and be processed for spell checks, acronym expansion, and other expansion and rewriting of the partial query to a known possible query suggestion. Possible query suggestions are weighted using global feature metrics and personalized metrics. Various weighting, confidence levels and merging based on scoring may be used to rank the suggestions. A machine learning model may be used to assist in assigning scores based on metrics on interaction in the search domain. Other embodiments are described and claimed.

Abstract: In some embodiments, the disclosed subject matter involves techniques for generating type-ahead query suggestions for a user in a specific subject or application domain that are ranked using confidence levels and contextual scoring. Partial query strings may be parsed for literal matching and be processed for spell checks, acronym expansion, and other expansion and rewriting of the partial query to a known possible query suggestion. Possible query suggestions are weighted using global feature metrics. Various weighting, confidence levels and merging based on scoring may be used to rank the suggestions. A machine learning model may be used to assist in assigning scores based on metrics on interaction in the search domain. Other embodiments are described and claimed.

Abstract: Disclosed are systems, methods, and non-transitory computer-readable media for expanding search queries. A search system executes a search query based on a search term and the geographic indicator. In response to determining that a number of the search results is less than a threshold number, the search system determines, based on historical search logs from other users in the first geographic region, a likelihood value indicating a likelihood that the other users in the first geographic region expanded the geographic region of their search queries. The search system compares the likelihood value to a threshold likelihood value, and determines, based on the comparison, that the likelihood value meets or exceeds the threshold likelihood value. The search system then executes an expanded search based on the search term and an expanded geographic indicator that encompasses the first geographic region.

Abstract: Disclosed are systems, methods, and non-transitory computer-readable media for expanding search queries. A search system identifies, based on search parameters received from a client device, a target company identified in the search parameters. The search parameters include a search term comprising at least two keywords, a first one of the at least two keyword identifying the target company, and the second one of the at least two keywords identifying an employment position. The search system identifies a second company based on a set of peer scores indicating a probability of employees transitioning between companies. The peer scores are calculated based on historical movement data indicating employee transitions between companies. The search system generates an expanded search term comprising a new keyword identifying the second company and the second keyword identifying the employment position.

Abstract: Disclosed are systems, methods, and non-transitory computer-readable media for expanding search queries. A search system determines a set of candidate alternate search terms based on historical search logs that include records of previously submitted search terms, corresponding search results that were presented to users, and corresponding search results that were selected by the users. The set of candidate alternate search terms is selected from titles of the corresponding search results that were selected by the users. The search system ranks the set of candidate alternate search terms based on determined probabilities that each of the alternate candidate search terms will be selected if presented to a user, and selects a first candidate alternate search term from the set of candidate alternate search terms based on the ranking. The search system generates an expanded search term based on the first candidate alternate search term.

Abstract: In an example, features in a boosting decision tree model are initialized to zero, the boosting decision tree model located in a GLMM and connected to a deep neural network collaborative filtering model via a prediction layer. While the features in the boosting decision tree model remain zero, the deep neural network collaborative filtering model is trained. One or more trees in the boosting decision tree model are boosted using logits produced by the training of the deep neural network collaborative filtering model as a margin. The prediction layer is trained using features from the deep neural network collaborative filtering model and features from the boosting decision tree model. It is then determined whether a set of convergence criteria is met. If not, then the deep neural network collaborative filtering model is retrained using the features and the process is repeated until the set of convergence criteria is met.