Methods and systems are provided for searching time series information in a distributed data processing system. A method of processing a semantic search query comprises receiving a structured search query, processing the structured search query to deconstruct into query elements, identifying a set of connected elements based on the query elements, processing a time series data structure of the identified set of connected elements to determine a command data element, utilizing the command data element to process the time series data structure of the identified set of connected elements, annotating the time series data structure of each of the identified set of connected elements to form a queried data set, and providing the queried data set.

In an approach for a conversational search in a content management system, a processor trains a deep learning model to learn semantic analysis of a plurality of user queries to identify intents and entities in the user queries. A processor analyzes the content management system to extract content keywords to generate a domain ontology. A processor augments the domain ontology based on the identified intents and entities in the user queries by the deep learning model. A processor tags the content keywords with metadata based on the domain ontology. A processor maps the intents and entities extracted from a current user query of a user to the content keywords extracted from the content management system to form a metadata keyword. A processor searches the content management system for a content based on the metadata keyword. A processor returns a search result for the current user query.

One embodiment of the invention provides a method for terminology ranking for use in natural language processing. The method comprises receiving a list of terms extracted from a corpus, where the list comprises a ranking of the terms based on frequencies of the terms across the corpus. The method further comprises accessing a domain ontology associated with the corpus, and re-ranking the list based on the domain ontology. The resulting re-ranked list comprises a different ranking of the terms based on relevance of the terms using knowledge from the domain ontology. The method further comprises generating clusters of terms via a trained model adapted to the corpus, and boosting a rank of at least one term of the re-ranked list based on the clusters to increase a relevance of the at least one term using knowledge from the trained model.

A knowledge base is collaboratively developed by receiving language input from at least one editor, featurizing it into language elements, extracting predicate sets that are missing predicate arguments, querying editors for input regarding the missing arguments, and updating the knowledge base with suitable predicate arguments and other language elements provided by the editors.

A knowledge base is collaboratively developed by receiving language input from at least one editor, featurizing it into language elements, extracting predicate sets that are missing predicate arguments, querying editors for input regarding the missing arguments, and updating the knowledge base with suitable predicate arguments and other language elements provided by the editors.

Techniques facilitating maintenance of tribal knowledge for accelerated compliance control deployment are provided. In one example, a system includes a memory that stores computer executable components and a processor that executes computer executable components stored in the memory, wherein the computer executable components include a knowledge base generation component that generates a knowledge graph corresponding to respective commitments created via tribal exchanges, the knowledge graph comprising a semantic level and an operational level; a semantic graph population component that populates the semantic level of the knowledge graph based on identified parties to the respective commitments; and an operational graph population component that populates the operational level of the knowledge graph based on tracked status changes associated with the respective commitments.

A computer-implemented method according to one embodiment includes converting an input question into a vector form using trained word embeddings; constructing a type similarity matrix using a predetermined ontology; and determining a score for all possible types for the input question, based on the input question in vector form and the type similarity matrix.

The present disclosure is directed to enabling acquisition of information of an argument corresponding to a case. The present disclosure is a language processing apparatus which refers to an argument emergence history database 14 which stores argument emergence patterns associated with cases and arguments of verbs for each meaning of a word or usage of a verb, acquires an argument emergence pattern which matches a verb and a case of the verb included in a request from a user from the argument emergence history database 14, and generates a response to the user using an argument included in the argument emergence pattern acquired from the argument emergence history database 14.

According to one embodiment, a support system includes an editor. The editor displays a first editing region and a second editing region. A plurality of first items is arrangeable in the first editing region. A plurality of second items is arrangeable in the second editing region. A corresponding item is arrangeable in the second editing region. The corresponding item is associated with a first selected item. The first selected item is one of the plurality of first items. A first subordinate item is subordinateable to the selected first item. A second subordinate item is subordinateable to the corresponding item. The second subordinate item is different from the first subordinate item.

According to one embodiment, a support system includes an editor. The editor displays a first editing region and a second editing region. A plurality of first items is arrangeable in the first editing region. A plurality of second items is arrangeable in the second editing region. A corresponding item is arrangeable in the second editing region. The corresponding item is associated with a first selected item. The first selected item is one of the plurality of first items. A first subordinate item is subordinateable to the selected first item. A second subordinate item is subordinateable to the corresponding item. The second subordinate item is different from the first subordinate item.