Abstract: The disclosed embodiments provide a system for performing a natural language search. During operation, the system applies a first machine learning model to a natural language query to predict one or more search intentions associated with the natural language query. Next, the system applies a second machine learning model to the natural language query to produce one or more search parameters associated with a first intention in the search intention(s), wherein the search parameter(s) include a field and a value of the field. The system then performs a first search of a first vertical associated with the first intention using the search parameter(s). Finally, the system generates a ranking containing a first set of search results from the first search of the first vertical and outputs at least a portion of the ranking in a response to the natural language query.

Abstract: Herein are techniques to use an artificial neural network to score the relevance of content items for a target and techniques to rank the content items based on their scores. In embodiments, a computer uses a plurality of expansion techniques to identify expanded targets for a content item. For each of the expanded targets, the computer provides inputs to an artificial neural network to generate a relevance score that indicates a relative suitability of the content item for that target. The computer ranks the expanded targets based on the relevance score generated for each of the expanded targets. Based on the ranking, the computer selects a subset of targets from the available expanded targets as the expanded targets for whom the content item is potentially most relevant. The computer stores an association between the content item and each target in the subset of expanded targets.

Abstract: Embodiments relate to user attitude modeling and behavior prediction for a social media network. One aspect includes collecting data relating to previously demonstrated sentiments, opinions, and actions attributed to network users toward a topic. Another aspect includes creating a model from the data, which includes factorizing the actions for behavior inference, factorizing auxiliary content from the network for opinion and sentiment inferences, and applying sentiment and opinion regularization to constrain user preferences on implicit topics to explicit sentiments and explicit opinions. Another aspect includes applying the model to a new user of the network with respect to the topic, and generating a prediction with respect to the user that includes predicting sentiment and opinion as a function of the auxiliary content and feature coefficients learned during a training process, and predicting a future action of the user as a function of the auxiliary content and latent profiles of the topic.

Abstract: A neural related query generation approach in a search system uses a neural encoder that reads through a source query to build a query intent vector. The approach then processes the query intent vector through a neural decoder to emit a related query. By doing so, the approach gathers information from the entire source query before generating the related query. As a result, the neural encoder-decoder approach captures long-range dependencies in the source query such as, for example, structural ordering of query keywords. The approach can be used to generate related queries for long-tail source queries, including long-tail source queries never before or not recently submitted to the search system.

Abstract: An online system and method includes receiving a search query including at least one search term, the search query being associated with a member of the online system. A data tag is separately applied to each individual search term of the search query. An ambiguity status of the search query is determined based on at least some actions as stored in an electronic data storage, also configured to store content items of the online system, including member profile data. A probability distribution of content item categories is determined based on the data tags and at least some of the actions and, if the search is ambiguous, member profile data. At least one content item associated with a content item category having a highest probability on the probability distribution and a user interface displays the at least one content item.

Abstract: Techniques for providing a personalized neural query auto-completion pipeline are disclosed herein. In some embodiments, a computer system, in response to detecting user-entered text that has been entered by a user in a search field of a search engine, generates auto-completion candidates based on the user-entered text and a corresponding frequency level for each one of the auto-completion candidates, ranks the auto-completion candidates based on profile data of the user using a neural network model, and causes at least a portion of the plurality of auto-completion candidates to be displayed in an auto-complete user interface element of the search field within the user interface of the computing device of the user based on the ranking prior to the user-entered text being submitted by the user as part of a search query.

Abstract: Machine learning techniques are described for generating recommendations using decision trees. A decision tree is generated based on training data that comprises multiple training instances, each of which comprises a feature value for each of multiple features and a label of a target variable. The multiple features correspond to attributes of multiple content delivery campaigns. Later, feature values of a content delivery campaign are received. The decision tree is traversed using the feature values to generate output. Based on the output, one or more recommendations are identified and the one or more recommendations are presented on a computing device.

Abstract: Techniques for extracting features of entities and targets that can be applied in a set of applications, such as entity selection prediction, audience expansion, feed relevance, and job recommendation. In one technique, entity interaction data is stored that indicates, for each of multiple entities, one or more targets that are associated with items with which the entity interacted. Token association data is stored that indicates, for each of multiple tokens, one or more targets that are associated with the token. Then, using one or more machine learning techniques, entity embeddings and target embeddings are generated based on the entity interaction data and the token association data. Later, a request for content is received from a particular entity. Based on at least one entity embedding, a content item for the particular entity is identified. The content item is transferred over a computer network and presented to the particular entity.

Abstract: Techniques for implementing a search query dispatcher using machine learning are disclosed herein. In some embodiments, a method comprises: receiving a search query comprising at least one term entered by a user via a computing device; determining a search intention for the search query based on the term(s) of the search query, the determining comprising determining the search intention to be either a single-target search intention to find a specific single result or multiple-target search intention to find multiple results having at least one common characteristic; selecting a search intention model for the search query from amongst a plurality of distinct search intention models based on the determined search intention, the plurality of distinct search intention models comprising a single-target search model for the single-target search intention and a multiple-target search model for the multiple-target search intention; and generating search results using the selected search intention model.

Abstract: In an example embodiment, traditional offline analysis of search engine quality is modified to provide multiple replays of queries against new versions of search engine algorithms. This helps to evaluate quality of new versions of search engine algorithms while reducing or eliminating parity issues without increasing network bandwidth utilization.

Abstract: Techniques for predicting sequential data using generative adversarial networks are disclosed herein. In some embodiments, a method comprises: receiving a request associated with a user of an online service; in response to the receiving of the request, retrieving a first plurality of sequential data points of the user from a profile of the user stored on a database of the online service, the first plurality of sequential data points comprising at least one attribute for each one of a plurality of sequential career points of the user; generating at least one predicted data point for the user based on the first plurality of sequential data points using a generative model, the generated at least one predicted data point comprising at least one attribute for a predicted career point for the user; and performing a function of the online service using the generated at least one predicted data point.

Abstract: Techniques are provided for generating recommendations to improve the delivery of electronic content items over one or more networks. In one technique, multiple predictive functions are stored, each associated with a different objective and based on multiple features. Multiple feature values of a first content delivery campaign are identified. For each feature value of the multiple feature values, a second feature value that is different than said each feature value is identified and input into each predictive function of the multiple predictive functions to generate multiple outputs, each output corresponding to a different predictive function of the multiple predictive functions. The multiple outputs are combined to generate a predicted performance. Based on the predicted performance associated with each feature value of the multiple feature values, a particular feature is identified and presented on a screen of a computing device.

Abstract: Herein are techniques to use an artificial neural network to score the relevance of content items for a target and techniques to rank the content items based on their scores. In embodiments, a computer uses a plurality of expansion techniques to identify expanded targets for a content item. For each of the expanded targets, the computer provides inputs to an artificial neural network to generate a relevance score that indicates a relative suitability of the content item for that target. The computer ranks the expanded targets based on the relevance score generated for each of the expanded targets. Based on the ranking, the computer selects a subset of targets from the available expanded targets as the expanded targets for whom the content item is potentially most relevant. The computer stores an association between the content item and each target in the subset of expanded targets.

Abstract: A system and method for determining whether a computer system is experiencing a problem are provided. Multiple data sets are identified. Each data set includes multiple values indicating a set of attributes that relate to a computer system and that correspond to a different time period of multiple time periods, such as days or hours. A model is generated based on the multiple data sets. A particular data set is identified that includes a set of values that correspond to the set of attributes and a particular time period that is subsequent to each of the multiple time periods. The model is used to generate a predicted value based on the particular data set. An actual value that corresponds to the particular time period is identified. A difference between the actual value and the predicted value is calculated and indicates a likelihood that the computer system is experiencing a problem.

Abstract: Techniques for simulating performance of a content delivery campaign are provided. In one technique, multiple entities that satisfy one or more criteria associated with a content delivery campaign are identified. For each entity, multiple content item selection events in which that entity participated are identified and data associated with each of the content item selection events are aggregated to generate aggregated data. The aggregated data associated with each entity is combined to generate combined aggregated data. The combined aggregated data is adjusted based on an actual performance value of the content delivery campaign to generate adjusted aggregated data. In response to receiving input, determining, based on the adjusted aggregated data and the input, a simulated performance of the content delivery campaign.

Abstract: Machine learning techniques are described for generating recommendations using decision trees. A decision tree is generated based on training data that comprises multiple training instances, each of which comprises a feature value for each of multiple features and a label of a target variable. The multiple features correspond to attributes of multiple content delivery campaigns. Later, feature values of a content delivery campaign are received. The decision tree is traversed using the feature values to generate output. Based on the output, one or more recommendations are identified and the one or more recommendations are presented on a computing device.

Abstract: A system and method for determining whether a computer system is experiencing a problem are provided. Multiple data sets are identified. Each data set includes multiple values indicating a set of attributes that relate to a computer system and that correspond to a different time period of multiple time periods, such as days or hours. A model is generated based on the multiple data sets. A particular data set is identified that includes a set of values that correspond to the set of attributes and a particular time period that is subsequent to each of the multiple time periods. The model is used to generate a predicted value based on the particular data set. An actual value that corresponds to the particular time period is identified. A difference between the actual value and the predicted value is calculated and indicates a likelihood that the computer system is experiencing a problem.

Abstract: Techniques for assisting a user in determining an interest level between a member of a social network system and an organization. According to various embodiments, applicant data is accessed for applicants having applied to an organization. A set of common applicant characteristics is determined for the set of applicant data. Member data is accessed indicative of a member of an online social media network. An interest score is generated based on a comparison of the member data and the set of applicant data. An identification of the organization is presented based on the interest score.

Abstract: Embodiments relate to user attitude modeling and behavior prediction for a social media network. One aspect includes collecting data relating to previously demonstrated sentiments, opinions, and actions attributed to network users toward a topic. Another aspect includes creating a model from the data, which includes factorizing the actions for behavior inference, factorizing auxiliary content from the network for opinion and sentiment inferences, and applying sentiment and opinion regularization to constrain user preferences on implicit topics to explicit sentiments and explicit opinions. Another aspect includes applying the model to a new user of the network with respect to the topic, and generating a prediction with respect to the user that includes predicting sentiment and opinion as a function of the auxiliary content and feature coefficients learned during a training process, and predicting a future action of the user as a function of the auxiliary content and latent profiles of the topic.