International Business Machines Corporation

Other

Jennifer Lynn La Rocca

Mario J Lorenzo

Kristin E McNeil

Rebecca Lynn Dahlman

Scott Robert Carrier

Mark Gregory Megerian

Richard D Dettinger

Debra L Angst

Joshua M Lee

Richard Joseph Stevens

Jeffrey K Huebert

Robert Christian Sizemore

David Blake Werts

Sterling Richardson Smith

Robert E Goff

Rick Joseph Stevens

A mechanism is provided in a data processing system to implement an annotator for annotating content using context-based surface forms. The mechanism receives a dictionary data structure of surface forms comprising a plurality of regular expressions and input content. The mechanism compares a given span of text in the input content to each regular expression in the dictionary data structure. Responsive to the given span of text matching a given regular expression, an annotator annotates the span of text with a content indicator corresponding to a content category associated with the dictionary data structure. The mechanism performs a natural language processing operation on the input content based on results of the annotation.

Context based surface form generation for cognitive system dictionaries

Aspects of the present disclosure include determining, by a processor, an ontology, the ontology comprising a plurality of ontological relationships, receiving, by the processor, a plurality of passages, determining, by the processor, a target set of co-occurring entities comprising a first entity and a second entity, determining a first passage in the plurality of passages that includes the first entity and the second entity, determining, from the ontology, a first ontological relationship between the first entity and the second entity, analyzing the first passage to determine a congruency score for the first ontological relationship, and generating a relationship annotation between the first entity and the second entity in the first passages based on the congruency score being within a threshold.

Semantic linkage qualification of ontologically related entities

Techniques for natural language processing based on user context include identifying a context of a user and responsive to receiving a request from the user intended for processing by a natural language processing (NLP) model, accounting for the context of the user in relation to the request. A result from the NLP model having accounted for the context of the user is provided.

Natural language processing based on user context

Embodiments include methods, system and computer program products for extracting attributes from embedded table structures in a document. Aspects include identifying a table in the document and identifying one or more headers of the table by locating co-occurring attributes in the table. Aspects also include identifying a plurality of values in the table and creating an annotation for each of the plurality of values value in the table, wherein each annotation includes text extracted from the one or more headers that correspond to the location of the value in the table.

Extracting attributes from embedded table structures

According to a computer-implemented method, an output is received resulting from natural language processing of unstructured text. In the output different phrases of the unstructured text are categorized into classes. A different visual distinction is generated for at least one class. A generated visual distinction is applied to phrases in the unstructured text based on their respective class. The unstructured text is displayed such that phrases in the unstructured text that correspond to the at least one class appear with the corresponding visual distinction indicative of that class.

Text display with visual distinctions per class

According to a computer-implemented method, a cognitive model container is created. The container includes a set of artifacts. Each artifact includes 1) content used by a cognitive service to convert unstructured text into structured text and 2) metadata. During deployment of a container, for each artifact a set of deployment descriptors are automatically identified. The deployment descriptors identify how the artifact is to be executed in the cognitive service. Also, during deployment of the container, content of an artifact is pushed to a number of cognitive services based on the deployment descriptors. The container is instantiated along with the set of artifacts to the cognitive service. During runtime execution of the container, content of each artifact in a container is obtained and unstructured text is converted into structured text based on the content of the artifacts.

Cognitive service updates via container instantiation

An artifact identification engine identifies artifacts from structured and unstructured data in one or more documents based on pre-defined artifacts, by using cognitive annotations. The identified artifacts are analyzed based at least on received inputs. A cartridge that includes artifacts that are relevant to the structured and unstructured data is generated, based on the analyzing.

Data driven approach for automatically generating a natural language processing cartridge

According to an embodiment of the present invention, a system filters a collection of application programming interfaces based on input data representing information of a document to be processed, and generates a pipeline of filtered application programming interfaces. Each filtered application programming interface is sequentially executed within the pipeline. The document may be processed through the pipeline and visualizations based on the processing of the document may be generated, allowing the pipeline to be refined to produce desired output data selected within the visualizations. Embodiments of the present invention further include a method and computer program product for generating a pipeline of filtered application programming interfaces in substantially the same manner described above.

Dynamically generating a service pipeline comprising filtered application programming interfaces

An embodiment of the present executes a sequence of a plurality of application programming interfaces. Request objects are generated for the application programming interfaces of the sequence. Each request object is generated in accordance with a common object model. Execution of each application programming interface is enabled in an order of the sequence to process a corresponding request object and generate a corresponding response object containing results. Each response object is generated in accordance with the common object model and includes information from the corresponding request object aggregated with the results. Further, each request object for a succeeding application programming interface in the sequence includes the aggregated information from a response object of a prior executed application programming interface in the sequence.

Dynamically forming and executing application programming interface pipelines

A global key control mechanism provides a single point of overall control for key generation, but portions of the key generation and/or allocation tasks may be delegated to client computer systems, thereby reducing network traffic. The global key control mechanism may download a client key generation mechanism on one or more client computer systems, and may allocate a block of keys to the client key generation mechanism. Requests for keys may then be routed to the client key generation mechanism, which can generate and/or allocate keys within the block of keys that the global key control mechanism allocated to it. When the block of keys is used up, the client key generation mechanism may request another block from the global key control mechanism. The preferred embodiments also include the capability of downloading a client key generation mechanism with an associated block of keys once the requests from one or more client applications exceed a predetermined threshold. In addition, the preferred embodiments include a hierarchy of key control mechanisms, with a single global key control mechanism that maintains control over one or more client key control mechanisms that may, in turn, control other client key control mechanism(s) or which may generate and/or allocate keys directly to requesting applications.

Apparatus and method for generating keys in a network computing environment

A database operation mechanism includes the capability of specifying a predefined database operation as a source of data for a different database operation. When the different database operation needs to be performed, the database operation mechanism determines whether the different database operation can use a predefined database operation as a data source. If so, the predefined database operation is specified as the source of data for the different database operation. If the different database operation cannot use a predefined database operation as a data source, the database operation mechanism determines whether the different database operation can use a modified form of a predefined database operation as a data source. If so, the different database operation may use the modified predefined database operation as a source of data. If the different database operation cannot use a predefined database operation or a modified form of a predefined database operation as a data source, a different database operation is generated and executed.

Growing community of inventors

Cary, NC, United States of America

Jennifer Lynn La Rocca