A solution is proposed for ranking documents belonging to two different domains. A corresponding method comprises generating a descriptor for each of the documents; the descriptor comprises corresponding values and confidence indexes of multiple properties (of the corresponding document); the documents of a domain are ranked with respect to a document of another domain according to a comparison of their descriptors. A computer program product for performing the method are also proposed. Moreover, a computing system for implementing the method is proposed.

The invention includes systems and methods to provide a research reporting narrative, in particular, for research metrics. Specifically, the invention includes content performance metrics and contributing factors to performance, The invention collects, analyzes, and places into a narrative format, data from research that is not easily digestible. The invention provides a quick and efficient report for absorption by users,

Using databases and tables of records on a mobile device can enhanced utilization of text messages. Fields of a records in a table in a database on a mobile device can be used to store both incoming (received) and outgoing (sent) text messages and emails. If the records in said table have blank fields that are both editable and searchable then it is possible to store annotation and create relational records in said table in a database. This is achieved by adding fields for user entered descriptive notes to Text Messages store on a mobile device in a field labelled as annotation and adding distinct alphanumeric character strings to field labelled as Searchkey. Enabling the user of the mobile device to enhance the value of content of messages stored on the mobile device by adding clarifying notes that will help show significant of message at a later time. The ability to annotate messages when they are first encountered will enable the user to increase the relevant of a message when it is viewed at a later date. By being able to add information to the text message that may have been conveyed to the user by methods other than the Email or Text messages that is being notated.

Embodiments provide a computer implemented method of evaluating one or more IR systems, the method including: providing, by a processor, a pre-indexed knowledge-based document to a pre-trained sentence identification model; identifying, by the sentence identification model, a predetermined number of query-worthy sentences from the pre-indexed knowledge-based document, wherein the query-worthy sentences are ranked based on a prediction probability value of each query-worthy sentence; providing, by the sentence identification model, the query-worthy sentences to a pre-trained query generation model; generating, by the query generation model, a query for each query-worthy sentence; and evaluating, by the processor, the one or more IR systems using the generated queries, wherein one or more searches are performed via the one or more IR systems, and the one or more searches are performed in a set of knowledge-based documents including the pre-indexed knowledge-based document.

Aspects of the present disclosure describe techniques for generating a machine learning model for extracting information from textual content. The method generally includes receiving a training data set including a plurality of documents having related textual strings. A relevancy model is generated from the training data set. The relevancy model is generally configured to generate relevance scores for a plurality of words extracted from the plurality of documents. A knowledge graph model illustrating relationships between the plurality of words extracted from the plurality of documents is generated from the training data set. The relevancy model and the knowledge graph model are aggregated into a complimentary model including a plurality of nodes from the knowledge graph model and weights associated with edges between connected nodes, wherein the weights comprise relevance scores generated from the relevancy model, and the complimentary model is deployed for use in analyzing documents.

Direct storage loading may be used to add data to a database. New data may be added to a database, using nodes different than a database engine to access a database. The addition of the new data may be assigned to different nodes. The nodes may obtain the data and store the data to storage locations according allocated space in the database by the database engine. The new data can then be made available for access at the database engine.

Systems, methods and computer program products for using searchable aggregate indices associated with non-aggregated value storage. In one method, a search system stores metadata values for each of a plurality of objects in a storage unit. The metadata values are stored in corresponding value storage locations that are associated with an identifiable metadata fields. An aggregate index is provided which includes a dictionary of terms that are contained in metadata values associated with a designated set of the metadata fields. The aggregate index is searched for one or more specific search terms, and one or more of the metadata values are retrieved from the value storage locations in response to the search, where the individual metadata fields associated with the retrieved metadata values are identified.

The technology described herein provides for a match fix-up stage that removes matching documents identified for a search query that don't actually contain terms from the search query. A representation of each document (e.g., a forward index storing a list of terms for each document) is used to identify valid matching documents (i.e., documents containing terms from the search query) and invalid matching documents (i.e., documents that don't contain terms from the search query). Any invalid matching documents are removed from further processing and ranking for the search query.

Systems, methods, and computer-readable media for providing entity relation extraction across sentences in a document using distant supervision. In some examples, a computing device can receive an input, such as a document comprising a plurality of sentences. The computing device can identify syntactic and/or semantic links between words in a sentence and/or between words in different sentences, and extract relationships between entities throughout the document. Techniques and technologies described herein populate a knowledge base (e.g., a table, chart, database etc.) of entity relations based on the extracted relationships. An output of the populated knowledge base can be used by a classifier to identify additional relationships between entities in various documents. Example techniques described herein can apply machine learning to train the classifier to predict relations between entities. The classifier can be trained using known entity relations, syntactic links and/or semantic links.

Embodiments as disclosed herein provide a search system with an pre-indexing filter that provides both a sophisticated and contextually tailored approach to filtering documents and a corrector that is adapted to alter a document that has been designated to be filtered out from the indexing process and determine if the altered document should be indexed. The alteration of the document may be tied to the attributes, rules or thresholds used to initially filter the document from the indexing process. The filtering criteria can thus be tailored to a specific context such that both the initial filtering and the alteration process may be better suited for application in that context.