Abstract: Methods, systems, and computer program products for active learning for natural language question answering are provided herein. A computer-implemented method includes generating a semantic signature of a natural language query; generating a SQL signature for a SQL query corresponding to the natural language query; determining whether a set of mappings includes a semantic signature matching the generated semantic signature, wherein each mapping in the set is between (i) a given semantic signature and (ii) a SQL signature representing a class of SQL queries corresponding to the given semantic signature; and in response to determining that the set of mappings does not include the generated semantic signature, adding a mapping between the generated semantic signature and the generated SQL signature to the set of mappings.

Abstract: A method, apparatus, and non-transitory computer-readable storage medium for presenting information identifying relationships in a database. Entity labels identifying a plurality of different entity types modeled in the database are presented in a user interface. Input identifying one or more selected entity types is received. A plurality of entity instance relationship sets is accessed. Each entity instance relationship set identifies a relationship between entity instances of at least two different entity types. Attribute data of the entity instances identified in only those entity instance relationship sets that identify a relationship between entity instances of the one or more selected entity types are presented, such that attribute data for each unique relationship between entity instances of the one or more selected entity types are presented only once.

Abstract: This application relates to systems and methods for providing search results based on a primary intent. In some examples, a disclosed system includes a memory resource storing instructions; and one or more processors coupled to the memory resource. The one or more processors are configured to execute the instructions to: receive, from a user, a search query including a plurality of words, identify a plurality of intention terms from the words of the search query, compute, for each of the plurality of intention terms, a compatibility score between the intention term and a query context associated with the intention term, determine, from the plurality of intention terms, a primary intention term having a maximum compatibility score among the plurality of intention terms, and generate, based on the primary intention term, a set of intent-based search results in response to the search query, the set of intent-based search results identifying a set of items associated with the primary intention term.

Abstract: Disambiguation of search keywords to expert systems is performed through the application of a semantic ranking function to determine a classification category with confidence for a given query. The semantic ranking function is executed through an application of a semantic distance distribution profile score through analysis of user problem statement (UPS) with nodes in the taxonomy in the same vector space to create a search that combines a user problem statement and a taxonomical node in the search engine index. The distribution profile score calculation is provenance influenced to derive geographic, cultural, and demographic provenance for a user problem statement.

Abstract: The present disclosure describes systems and methods for information retrieval. Embodiments of the disclosure provide a color embedding network trained using machine learning techniques to generate embedded color representations for color terms included in a text search query. For example, techniques described herein are used to represent color text in a same space as color embeddings (e.g., an embedding space created by determining a histogram of LAB based colors in a three-dimensional (3D) space). Further, techniques are described for indexing color palettes for all the searchable images in the search space. Accordingly, color terms in a text query are directly converted into a color palette and an image search system can return one or more search images with corresponding color palettes that are relevant to (e.g., within a threshold distance from) the color palette of the text query.

Abstract: Systems and methods for image searching are described. The systems and methods include receiving a search query comprising user input for a reference image; converting the user input for the reference image to a preference statement using a machine learning model; encoding the preference statement in an embedding space to obtain an encoded preference statement; combining the encoded preference statement with an encoded reference image representing the reference image in the embedding space to obtain a multi-modal search encoding; and performing a search operation using the multi-modal search encoding to retrieve a second image, wherein the second image differs from the reference image based on the user input for the reference image.

Abstract: Examples of the present disclosure describe systems and methods for query execution across multiple graphs. In an example, a graph or isolated collection may be split into multiple subparts, such that each subpart may store information of the isolated collection. Cross-collection reference resources may be used to reference resources that are stored by other isolated collection subparts. A breadth-first search of an isolated collection subpart may be performed in order to identify matches or potential matches in an isolated collection subpart. In an example, a potential match may comprise a cross-collection reference resource, which may reference a resource in another isolated collection subpart. Once query execution has completed in the isolated collection subpart, query execution may be paused and transferred to another isolated collection subpart that comprises a resource referenced by a cross-collection resource reference.

Abstract: First and second big data tables may be aligned into compacted and reordered tables, respectively, such that each row of the compacted table and the corresponding similarly-indexed row of the reordered table have equal keys. Advantageously, the time complexity of alignment scales linearly with the number of rows of the data tables, and the compacted and reordered tables may be subsequently joined by parsing once through the tables. Alignment may be extended to three or more big data tables.

Abstract: Clarification-question selection, including: Receiving a search conversation that includes utterances by a user and by a conversational search system. Retrieving, from a solution documents database, text passages that are relevant to the search conversation. Retrieving, from a clarification questions database, for each of the text passages, candidate clarification questions that are relevant to both the respective text passage and the search conversation.

Abstract: Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing a program and method for mapping webpages to page groups. The program and method provide for receiving plural Uniform Resource Locators (URLs), each URL of the plural URLs corresponding to a respective webpage of a website; generating a distance matrix with pairwise distances between the plural URLs; performing hierarchical clustering based on the distance matrix, to generate a dendrogram in which the plural URLs are arranged in hierarchical clusters; and determining, based on the dendrogram, a predicted page group for each of the plural URLs.

Abstract: In an example, a computer-implemented method for natural language query translation comprises: receiving, by one or more processors, a natural language query; processing, by the one or more processors, the natural language query to identify an intent and a variable of the natural language query; converting, by the one or more processors, the identified variables into low-level variables; combining the identified intent and the low level variables to form a database expression; querying, by the one or more processors, a database storing flight information, using the database expression; and creating, by the one or more processors, at least one graphical representation based on a result of the querying of the database.

Abstract: Various aspects of this disclosure provide digital data processing systems for using encrypted variant data objects to facilitate queries of sensitive data. In one example, a digital data processing system can receive sensitive data about an entity. The digital data processing system can create, in an identity data repository and from the sensitive data, a searchable secure entity data object for the entity. The searchable secure entity data object is usable for servicing a query regarding the entity. For instance, a transformed query parameter can be generated from a query parameter in the query. The query can be serviced by matching the transformed query parameter to tokenized variant data in the searchable secure entity data object and retrieving tokenized sensitive data from the searchable secure entity data object.

Abstract: Embodiments of the present disclosure may provide a dynamic query execution model. This query execution model may provide acceleration by scaling out parallel parts of a query (also referred to as a fragment) to additional computing resources, for example computing resources leased from a pool of computing resources. Execution of the parts of the query may be coordinated by a parent query coordinator, where the query originated, and a fragment query coordinator.

Abstract: Systems of the present disclosure generate database queries for financial information requested in a natural-language form. A natural-language processing (NLP) financial aggregator receives a request for financial information and extracts NLP features of the request, including keywords. The NLP financial aggregator determines a type of the request based on the features and creates a query in a database-query language for the financial information based on the type and on the features. The NLP financial aggregator submits the query to a database where the financial information is stored. The software then receives the financial information from the database and sends the information to the user.

Abstract: Embodiments of the present disclosure provide a method and an apparatus for searching for an image and a related storage medium. The method includes obtaining reference keypoint data of a reference person in a reference image, and searching, based on the reference keypoint data, a set of candidate images for at least one target image containing at least one candidate person that has a pose similar to the reference person.

Abstract: A request may be received to transform records in a data lake that match one or more query criteria. Data lake records that match the criteria may be retrieved. The retrieved records may include two data lake records associated with the same data lake record identifier. A transformed record may be generated based on time stamps associated with the retrieved records.

Abstract: A computer system for performing enhanced rules conflict checking is provided. The computer system includes at least one processor in communication with at least one memory device. The at least one processor is programmed to store a plurality of rules for transmitting to a plurality of destination systems and receive a data message for transmission to the plurality of destination systems. The data message is configured to be routed to each of the plurality of destination systems. The at least one processor is programmed to compare the data message to the plurality of rules to validate the data message and if the data message is validated, instruct the requesting system to transmit the data message to the plurality of destination systems.

Abstract: Provided is a system and method for generating an SQL operation from a natural language input using neural networks which works on data from a database that has not been seen before by the neural networks. In one example, the method may include receiving a natural language input, determining, via a first predictive module, a data structure of a SQL operation based on text included in the natural language input, filling in, via a second predictive module, one or more empty slots of the data structure of the SQL operation with text based on column names of a database and the text included in the natural language input, and storing the filled-in data structure of the SQL operation in a storage.

Abstract: In methods and systems for providing information to a user relating to a point-of-interest (POI), a query is received via a communication network. A processor receives information relating to at least one POI based on the received query. The retrieved information comprises a set of retrieved POI tips relating to the POI. Each of the set of retrieved POI tips is previously extracted from POI free-text reviews and respectively associated in the data storage with one or more semantic categories based on a predefined tip ontology. The processor generates a user interface interactively displaying the retrieved POI tips and the semantic categories associated with each of the POI tips. The displayed POI tips are sorted by their associated displayed semantic categories. The generated user interface is transmitted to a computing device for display.

Abstract: A natural language query to domain-specific language query (NLQ-to-DSLQ) translation system includes a language model and a domain-specific language (DSL) parser that constrains the output of the language model to a DSL, such as structured query language (SQL). At each decoding step, the language model generates a predicted next token for each of a set of potential translations of a NLQ. The DSL parser evaluates each of the potential translations at each decoding step based on a set of stored DSL rules, which define valid terminology, syntax, grammar, and/or other constraints of the DSL. The DSL parser may reject and remove from consideration partial potential translations that are invalid or receive a low parsing score, such that the language model only continues to generate new tokens at the next decoding step for partial potential translations that are determined to be valid and/or sufficiently high scoring.