Abstract: An offline adaptation method of customizing and incorporating external knowledge domain specific knowledge sources into an existing knowledge base (KB) of a cognitive conversation system, includes obtaining an instance-concept frequency from the existing KB. All the contexts of a domain ontology in which an instance-concept is used are computed. All instance-concepts from the existing KB to an external domain-specific knowledge source are mapped. The existing KB is configured to search for semantically related terms in response to a natural language query received from a conversation system.

Abstract: A system, method, and computer readable medium perform a method of query relaxation. A query output from a conversational system is received. At least one search term in the query is identified. Instance data is output to the conversational system in response to determining that the instance data in a data store matches the at least one search term in the query. The computer device outputs the received query to an external domain-specific knowledge source in response to determining that the at least one search term does not the match instance data in the data store. The computer device receives the relaxed data matches from the external domain-specific knowledge source being semantically-related to at least one search term in the query based on a plurality of criteria associated with the query. The computing device generates a response to the query based on contextual information and structural information.

Abstract: A system, method, and computer readable medium perform a method of query relaxation. A query output from a conversational system is received. At least one search term in the query is identified. Instance data is output to the conversational system in response to determining that the instance data in a data store matches the at least one search term in the query. The computer device outputs the received query to an external domain-specific knowledge source in response to determining that the at least one search term does not the match instance data in the data store. The computer device receives the relaxed data matches from the external domain-specific knowledge source being semantically-related to at least one search term in the query based on a plurality of criteria associated with the query. The computing device generates a response to the query based on contextual information and structural information.

Abstract: A method and structure for analyzing a database having non-text data in data fields and text in text fields. The invention first selects a subset of the database based upon criteria. The subset includes data field(s) and associated text field(s). The invention searches for data matching the criteria within structured data fields of the database. If the invention searches multiple databases, the invention creates shared dimensions for databases that do not share common attributes. The invention automatically selects a relatively short text phrase from the text fields that helps to explain the underlying meaning (i.e. unique text content) of a data subset selected using the non-text data fields.

Abstract: A system and method for processing a document to generate a set of related documents. A system is provided that includes a textual analytics system that analyzes unstructured data contained in a source document and extracts a set of structured information about the source document; and a compare system that identifies a set of related documents by comparing the set of structured information with metadata indexed from a set of publications.

Abstract: A system and method for enhancing patent documents. A system is disclosed that includes: an extraction system for extracting non-patent references from a patent document; a system for cross-referencing an extracted non-patent reference with a metadata database to identify metadata information associated with the extracted non-patent reference; and a system for annotating the patent document with the metadata information.

Abstract: A method and system for interesting relationships in text documents includes generating a dictionary of keywords in the text documents, forming categories of the text documents using the dictionary and an automated algorithm, counting occurrences of the structured variables, categories and structured variable/category combinations in the text documents, and calculating probabilities of occurrences of the structured variable/category combinations.

Abstract: According to a preferred embodiment of the present invention, a bridging system (100) and method provides a way of linking two independent data systems by receiving a dataset from a source data system. The bridging system (100) translates the dataset from a source schema to a target schema according to a set of mapping rules, and queues the translated data in persistent storage, and then sends the translated dataset to a destination data system. The system (100) includes an XML bridge (114), multiple application specific gateways (116,118), and a web admin interface (210), all in communication via a wide area network.

Abstract: A data warehouse is created using an input file that can contain sub-documents of different formats. A root document model including path names to all nodes among the sub-documents is generated, and a table is generated with columns being derived from the path names of the root model. The sub-documents are shredded to populate the table. Then, the dimensions of the data warehouse are defined by selecting respective columns. A routine such as a DDL may then be generated to populate the data warehouse with data.

Abstract: A user initially analyzes a statistically significant sample of documents randomly drawn from a data warehouse to create a cached feature space and text classifier, which can then be used to establish a classification dimension in the data warehouse for in depth and detailed text analysis of the entire data set.