Abstract: Methods, computing systems, and technology for generating keywords using machine-learned techniques. The system can receive, from a user device, a first keyword associated with a content item of a first content provider. Additionally, the system can access from a keyword database, a plurality of keywords. Moreover, the system can select, using the machine-learned model, a subset of keywords from the plurality of keywords based on the content item. Furthermore, the system can process, using a machine-learned model, the first keyword and a subset of keywords to calculate a similarity score for each keyword in the subset of keywords and the first keyword. The system can determine a suggested keyword from the subset of keywords based on the similarity score for each keyword in the subset of keywords and the first keyword. Subsequently, the system can cause, on a display of the user device, a presentation of the suggested keyword.

Abstract: Methods, computing systems, and technology for using machine-learned techniques for determining a keyword for a web resource, and automating content presentation for the web resource. The system can receive, from a user device of a first content provider, a request associated with a web resource having a plurality of assets. Additionally, the system can determine, based on the plurality of assets, a first keyword associated with the web resource. Moreover, the system can determine, based on a first keyword cluster associated with the first keyword, the first keyword being associated with a first query cluster having a query performance metric. Furthermore, the system can process, using a machine-learned forecasting model, the first keyword and the first query cluster to generate a keyword performance metric for the first keyword. Subsequently, the system can perform an action based on the keyword performance metric associated with the first keyword.

Abstract: Example aspects of the present disclosure provide an example method. In some implementations, the example method can include receiving request data indicating a request for content. In some implementations, the example method can include determining a request context associated with the request data, wherein the request context is based on account data for a user device associated with the request. In some implementations, the example method can include determining, based on the request and the request context, a data object from a knowledge graph, wherein the data object comprises a subject and one or more attributes for the subject. In some implementations, the example method can include generating, using a machine-learned content generation model, content descriptive of the subject, the content generated based on the request, the request context, and the data object.

Abstract: Systems and methods for generating phonetic spelling variations of a given word based on locale-specific pronunciations. A phoneme-letter density model may be configured to identify a phoneme sequence corresponding to an input word, and to identify all character sequences that may correspond to an input phoneme sequence and their respective probabilities. The phoneme-phoneme error model may be configured to identify locale-specific alternative phoneme sequences that may correspond to a given phoneme sequence, and their respective probabilities. Using these two models, a processing system may be configured to generate, for a given input word, a list of alternative character sequences that may correspond to the input word based on locale-specific pronunciations, and/or a probability distribution representing how likely each alternative character sequence is to correspond to the input word.

Abstract: Example aspects of the present disclosure relate to an example method. The example method includes obtaining, by a computing system comprising one or more processors, a plurality of data bags. In the example method, each respective data bag of the plurality of data bags comprises a respective plurality of instances and is respectively associated with one or more proportion labels. The example method also includes generating, by the computing system, a plurality of training bags from the plurality of data bags according to a plurality of weights. In the example method, the training bags are generated such that a bag-level predicted proportion label error by a machine-learned prediction model over the plurality of training bags correlates to an instance-level predicted proportion label error by the machine-learned prediction model.

Abstract: Systems and methods for generating phonetic spelling variations of a given word based on locale-specific pronunciations. A phoneme-letter density model may be configured to identify a phoneme sequence corresponding to an input word, and to identify all character sequences that may correspond to an input phoneme sequence and their respective probabilities. The phoneme-phoneme error model may be configured to identify locale-specific alternative phoneme sequences that may correspond to a given phoneme sequence, and their respective probabilities. Using these two models, a processing system may be configured to generate, for a given input word, a list of alternative character sequences that may correspond to the input word based on locale-specific pronunciations, and/or a probability distribution representing how likely each alternative character sequence is to correspond to the input word.

Abstract: Systems and methods for generating phonetic spelling variations of a given word based on locale-specific pronunciations. A phoneme-letter density model may be configured to identify a phoneme sequence corresponding to an input word, and to identify all character sequences that may correspond to an input phoneme sequence and their respective probabilities. The phoneme-phoneme error model may be configured to identify locale-specific alternative phoneme sequences that may correspond to a given phoneme sequence, and their respective probabilities. Using these two models, a processing system may be configured to generate, for a given input word, a list of alternative character sequences that may correspond to the input word based on locale-specific pronunciations, and/or a probability distribution representing how likely each alternative character sequence is to correspond to the input word.

Abstract: Enabling advertisers to evaluate performance of an email advertisement campaign is disclosed. An advertisement is circulated via email among the users of an email system and feedback associated with one or more of user actions or automated actions by the email system with respect to the circulated advertisement are detected. The feedback is analyzed to determine the performance of the email advertisement campaign across various user segments. Informative reports regarding the feedback are generated and provided to the advertiser for a charge by the email system provider.

Abstract: Methods and systems for detecting expiration time of an article include receiving the article for a pre-planned event. The article is analyzed to identify one or more attributes. The article is matched to an event identifier using the article attributes. The event identifier is pre-defined and stored in an event database. The event identifier acts as an index to the event database for obtaining event characteristics of the pre-planned event. The article attributes are examined to identify event phase indicators that correlate to a specific event phase of the pre-planned event. The expiration time of the article is computed based on the specific event phase identified for the pre-planned event. The expiration time is used to rank the article and for considering assigning the article to a content pool of articles that is selected for publishing for the specific event phase of the pre-planned event.

Abstract: Briefly, the disclosure describes embodiments of methods or apparatuses for document processing at distributed processing nodes.

Abstract: In one embodiment, a search query may be received. It may be ascertained that the search query pertains to a particular product category. A set of products that pertain to the particular product category may be identified, where the set of products are top selling products in the particular product category. Information pertaining to each product in the set of products may be provided.

Abstract: Methods and systems for detecting expiration time of an article include receiving the article for a pre-planned event. The article is analyzed to identify one or more attributes. The article is matched to an event identifier using the article attributes. The event identifier is pre-defined and stored in an event database. The event identifier acts as an index to the event database for obtaining event characteristics of the pre-planned event. The article attributes are examined to identify event phase indicators that correlate to a specific event phase of the pre-planned event. The expiration time of the article is computed based on the specific event phase identified for the pre-planned event. The expiration time is used to rank the article and for considering assigning the article to a content pool of articles that is selected for publishing for the specific event phase of the pre-planned event.

Abstract: Enabling advertisers to evaluate performance of an email advertisement campaign is disclosed. An advertisement is circulated via email among the users of an email system and feedback associated with one or more of user actions or automated actions by the email system with respect to the circulated advertisement are detected. The feedback is analyzed to determine the performance of the email advertisement campaign across various user segments. Informative reports regarding the feedback are generated and provided to the advertiser for a charge by the email system provider.

Abstract: A system and method for method for performing a web search by a search engine for content including: providing a first search results page to a user in response to a search query; providing an interface for submission of an input action representing a search command, wherein the interface is associated with the search results page; receiving the input action; reformulating the search query to incorporate the search command represented by the input action; and providing a second search results page to the user in response to the reformulated search query.

Abstract: Embodiments of methods, systems and/or apparatuses relating to data processing in distributed computing environments are disclosed. In particular, methods, systems, and/or apparatuses for determining information similarly and/or performing related statistical techniques which may be implemented or operated in a distributed computing environment are disclosed.

Abstract: Briefly, the disclosure describes embodiments of methods or apparatuses for document processing at distributed processing nodes.

Abstract: A system and method for method for performing a web search by a search engine for content including: providing a first search results page to a user in response to a search query; providing an interface for submission of an input action representing a search command, wherein the interface is associated with the search results page; receiving the input action; reformulating the search query to incorporate the search command represented by the input action; and providing a second search results page to the user in response to the reformulated search query.

Abstract: Embodiments are directed towards an automated machine learning framework to extract keywords within a message that are relevant to an attachment to the message. The machine learning model finds a set of relevant sentences within the message determined to be relevant to the one or more attachments based on identification of one or more sentence level features within a given sentence. The sentence level features include, for example, anchor features, noisy sentence features, short message features, threading features, anaphora detections, and lexicon features. From the set of relevant sentences, useful keywords may be extracted using a sequence of heuristics to convert the sentence set into the set of useful keywords. The set of useful keywords may then be associated to at least one attachment such that the keywords may subsequently be used to perform various indexing, searching, sorting, and to provide further context to the attachment.

Abstract: Embodiments of methods, systems and/or apparatuses relating to data processing in distributed computing environments are disclosed. In particular, methods, systems, and/or apparatuses for determining information similarly and/or performing related statistical techniques which may be implemented or operated in a distributed computing environment are disclosed.

Abstract: A method and apparatus for creating templates for electronic documents is provided. One or more attributes are extracted, using a seed template, from a first document, such as a web page. A second document that contains a particular attribute, extracted from the first document, is identified. The second document may be in a different cluster than the first document. The second document is annotated, using an extracted attribute, to create an annotated document. The second document is annotated without human intervention. A new template for the annotated document is generated. The new template facilitates extraction of information from the annotated document. The new template may be used to extract additional attributes from all documents in the cluster of documents of which the second document is a member. The process may continue over numerous iterations to generate a large number of templates in an automated fashion.