Abstract: Embodiments relate to an intelligent computer platform to decipher and translate an analogical phrase. A phrase is translated, yielding a second language phrase. An idiom database is searched for one or more matching idiom phrases. The idiom phrases are ranked according to similarity to the second language phrase and idiom phrase with a highest similarity ranking is outputted as the final output.

Abstract: An approach is provided in which a question answer system monitors a voice conversation between a first entity and a second entity. During the conversation, the question answer system parses the conversation into information phrases, and constructs the information phrases into a current conversation pattern. The question answer system identifies deceptive conversation properties of the current conversation by analyzing the current conversation pattern against domain-based conversation patterns. The question answer system, in turn, sends an alert message to the first entity to notify the first entity of the identified deceptive conversation properties.

Abstract: Mechanisms are provided for evaluating test cases for testing a software product based on a requirements change. The mechanisms analyze a test case corpus to identify a plurality of first relationships between elements of test cases in the test case corpus and generate a test case relationship model based on the identified plurality of first relationships. The mechanisms receive a proposed requirements change to change one or more requirements of the software product and then perform a search of the test case relationship model to identify test case relationships corresponding to the proposed requirements change. The mechanisms identify a subset of test cases affected by the proposed requirements change and generate an output specifying the identified subset of test cases.

Abstract: An approach is provided to ingest software source code files into a question/answering (QA) system. During ingestion, source code blocks are classified to identify one or more constructs in the blocks as being domain-specific. Relationships between the blocks are then mapped. Software compliance regulations are ingested into the QA system. Using the QA system, a source code file is analyzed for compliance to the software compliance regulations. The analysis identifies code sections within the source code file as being domain-specific and subject to the ingested set of software compliance regulations.

Abstract: An approach is provided in which a QA system ingests traditional sources, which includes traditional terms, into a domain dictionary. Next, the QA system ingests crowd-based sources that include crowd-based terms and corresponding crowd-based metadata. In turn, the QA system calculates weightings pertaining to the traditional terms based upon the crowd-based metadata. When the QA system receives a question from a requestor that includes question terms, the QA system identifies an answer to the question based on the calculated weightings pertaining to the traditional terms that are relevant to the question terms.

Abstract: An approach is provided in which a QA system ingests traditional sources, which includes traditional terms, into a domain dictionary. Next, the QA system ingests crowd-based sources that include crowd-based terms and corresponding crowd-based metadata. In turn, the QA system calculates weightings pertaining to the traditional terms based upon the crowd-based metadata. When the QA system receives a question from a requestor that includes question terms, the QA system identifies an answer to the question based on the calculated weightings pertaining to the traditional terms that are relevant to the question terms.

Abstract: An approach is provided to ingest software source code files into a question/answering (QA) system. During ingestion, source code blocks are classified to identify one or more constructs in the blocks as being domain-specific. Relationships between the blocks are then mapped. Software compliance regulations are ingested into the QA system. Using the QA system, a source code file is analyzed for compliance to the software compliance regulations. The analysis identifies code sections within the source code file as being domain-specific and subject to the ingested set of software compliance regulations.

Abstract: Embodiments relate to a system, program product, and method for use with an intelligent computer platform to decipher analogical phrases. A phrase is parsed into a set of terms to reveal an analogical pattern. The set of terms are categorized according to syntactic placement and each term is placed into two or more categories according to word type patterns in the phrase to produce metadata. The metadata is matched to outcome metadata generated from a set of outcomes produced from data storage and a set of grammatical data is generated for each potential outcome. A statistical model is trained, whereby the training includes weighing and ranking each potential outcome according to degree of congruence with the syntactic placement and word type patterns of the phrase. A highest outcome is selected, the highest outcome being the potential outcome with the highest rank and a confidence level data metric is then applied.

Abstract: Embodiments relate to a system, program product, and method for use with an intelligent computer platform to decipher analogical phrases. An analogy list is obtained, each analogy within the analogy list having a known meaning, and receiving an analogy phrase. A verb is identified within the phrase and a verb definition list is generated. A subject is identified within the phrase and a subject definition list is generated. An adjective is identified within the phrase and an adjective definition list is generated, including filtering adjectives to accept adjective definitions associated with the identified subject. A set of outcomes is identified, incorporating the verb definition, subject definition, and adjective definition, and a corpus is searched for evidentiary use. The outcomes are ranked in accordance to evidentiary use found in the corpus the highest ranked outcome is outputted.

Abstract: Embodiments relate to a system, program product, and method for use with an intelligent computer platform to decipher analogical phrases. A phrase is compared to an analogy classifier database in order to identify a match between the analogical pattern and an analogy entry. If a match is identified, generating an idiomatic structure from the analogical pattern. An analysis is then applied whereby the analysis includes building a set of outcomes of the generated idiomatic structure based on semantic analysis into corresponding metadata for the idiomatic structure. An ontological database is searched for evidence of a pattern associated with the set of outcomes and each entry in the outcome set is scored according to a weighted calculation from the ontological database based on congruence with the pattern. An entry from the outcome set is selected based on the scoring and is represented as a meaning of the analogical pattern.

Abstract: A technique for pre-filling a computing device form with information associated with an action command found in a message includes receiving a message. Content of the message is analyzed utilizing natural language processing (NLP) to locate an action command within the message. NLP is applied to text in the message that is associated with the action command to determine a context of the action command. A similarity algorithm is applied to the text and one or more input fields of the form to identify one or more matching elements between the text and the input fields of the form. Finally, the input fields of the form are automatically pre-filled with information associated with the matching elements in the message whose similarity exceeds a predetermined threshold.

Abstract: An approach is provided to correct documents ingested by a question answering (QA) system. A document previously ingested by the QA system is selected. A correction to the selected document is identified from one or more correction sources and the correction is applied to the selected document within the QA system. In one embodiment, the correction source is a non-ingested document, such as a published document or an issued correction. In another embodiment, the correction source is a post in a forum. In this embodiment, a statement in the ingested document is compared with a contradictory statement found in an ingested post of a threaded discussion. The statement and the contradictory statement are evaluated by the QA system. The statement in the ingested document is replaced with the contradictory statement in response to the evaluation revealing that the contradictory statement is correct and that the statement is incorrect.

Abstract: A technique for pre-filling a computing device form with information associated with an action command found in a message includes receiving a message. Content of the message is analyzed utilizing natural language processing (NLP) to locate an action command within the message. NLP is applied to text in the message that is associated with the action command to determine a context of the action command. A similarity algorithm is applied to the text and one or more input fields of the form to identify one or more matching elements between the text and the input fields of the form. Finally, the input fields of the form are automatically pre-filled with information associated with the matching elements in the message whose similarity exceeds a predetermined threshold.

Abstract: An approach is provided to determine answer stability in a question answering (QA) system. In the approach, a question submitted to a question answering (QA) system is selected and data pertaining to a candidate answers generated by the QA system are analyzed. The analysis of the data results in a stability characteristic that pertains to the candidate answers. A confidence value associated with the candidate answers is adjusted based on the respective answer's stability characteristic. One or more of the candidate answers are provided to a requestor based on the adjusted confidence values.

Abstract: A data processing system determines whether a natural language query or a result has a temporal characteristic. In response, at least one of user profile information or user activity history information for a user is analyzed to identify user characteristics indicative of a timeframe for scheduling a reminder notification of the result. A timeframe for scheduling the reminder notification is calculated based on results of analyzing the user profile information or user activity history information. A reminder notification is scheduled to be output at a scheduled reminder notification time based on the calculated timeframe. At a later time, in response to the later time being equal to or later than the scheduled reminder notification time, the reminder notification is output to a client device associated with the user, wherein the reminder notification specifies the result generated for the natural language query.

Abstract: A technique for dynamically generating game activities for a game (e.g., a role-playing game) includes loading game information about the game into a data processing system (e.g., a question answering system). Context data (e.g., a question) is received from a client (e.g., a player of the game, a user of the game, another system, or a game engine). In response to receiving the context data, a game activity is dynamically generated based on the context data and the game information. The game activity is then initiated in the game and presented to the client.

Abstract: A technique for dynamically generating game activities for a game (e.g., a role-playing game) includes loading game information about the game into a data processing system (e.g., a question answering system). Context data (e.g., a question) is received from a client (e.g., a player of the game, a user of the game, another system, or a game engine). In response to receiving the context data, a game activity is dynamically generated based on the context data and the game information. The game activity is then initiated in the game and presented to the client.

Abstract: A method is provided for analyzing log message content. The computer-implemented method may include detecting, by at least one processor, log messages in an application code, identifying a log level assigned to each of the log messages, and performing natural language processing (NLP) analysis on each of the log messages by using at least keyword and synonym matching percentage analysis criteria. The computer-implemented method may further include determining, in response to the NLP analysis, a severity score of each of the log messages, and reclassifying, based on the severity score, the assigned log level of one or more of the log messages to a different log level.

Abstract: In an approach to content selection, one or more computer processors receive a first query from a user. The one or more computer processors retrieve a first response for the first query. The one or more computer processors determine whether the first response exceeds a threshold for a policy for content usage associated with the first response, wherein the policy for content usage specifies one or more restrictions for usage of a content asset. In response to determining the first response exceeds the threshold for the policy for content usage, the one or more computer processors select a first subset of the first response to meet the threshold for the policy for content usage. The one or more computer processors send the first subset of the first response to the user.

Abstract: A method for training a question answering system includes providing training questions to a question answering system executing on a computer and to a plurality of subject matter experts. The question answering system generates first answers to each training question. Second answers to the training questions are received from the subject matter experts. Feature scores for each of the first answers and the second answers are generated and compared across the second answers and the first answers. Each of the feature scores is representative of a quality of an answer that is indicative of relevance to a corresponding training question. Based on the comparing, a measure of consistency of the feature scores of the second answers is determined, and a measure of consistency of the feature scores of the second answers to the first answers is determined. The measures of consistency are transmitted to the subject matter experts.