Abstract: Aspects of the present disclosure, in certain embodiments, are directed toward providing a visual representation of question quality in a question answering system. More particularly, aspects are directed toward receiving, by a question answering system, an input question having a set of query attributes. The set of query attributes may be user-influenced characteristics of the input question. Aspects of the present disclosure are also directed toward evaluating, by comparing the set of query attributes to a set of assessment criteria, the quality of the input question. Aspects of the present disclosure are also directed toward assigning, in response to evaluating the quality of the input question, a set of quality values to the set of query attributes. Using the assigned set of quality values and the set of query attributes, an icon that indicates a visual representation of the quality of the input question may be generated.

Abstract: According to an embodiment of the present invention, an artifact is received, and unstructured content of the artifact is parsed and analyzed to identify data for one or more of missing structured content of the artifact and inaccurate structured content of the artifact. The identified data is then added to the artifact. Embodiments of the present invention can be used, for example, to provide data for missing and inaccurate structured content in artifacts of Application Lifecycle Management (ALM) frameworks, and improve accuracy of structured information that used to run queries and create reports.

Abstract: According to an embodiment of the present invention, an artifact is received, and unstructured content of the artifact is parsed and analyzed to identify data for one or more of missing structured content of the artifact and inaccurate structured content of the artifact. The identified data is then added to the artifact. Embodiments of the present invention can be used, for example, to provide data for missing and inaccurate structured content in artifacts of Application Lifecycle Management (ALM) frameworks, and improve accuracy of structured information that used to run queries and create reports.

Abstract: Software that answers questions asked of question answering systems, by performing the following steps: (i) identifying a hierarchy of question and answer pairs, where a first answer paired to a first question in the hierarchy of question and answer pairs includes at least a second answer paired to a second question in the hierarchy of question and answer pairs; (ii) receiving, by a question answering system, an input question from a first user; (iii) identifying first user contextual information pertaining to the first user; and (iv) answering the input question, by the question answering system, based, at least in part, on the hierarchy of question and answer pairs and the first user contextual information.

Abstract: A mechanism is provided in a data processing system for automatically generating question and answer pairs for training a question answering system for a given domain. The mechanism receives user input of question text for a question to be submitted to a question answering system in a user interface. The mechanism determines a question strength score for the question text. The question strength score represents a likelihood the question text will result in a correct answer with high confidence. The mechanism presents a graphical representation of the question strength score in the user interface.

Abstract: Collaborative annotation of a document. A GUI is generated by a host computer that displays a document to annotate. The GUI is transmitted by the host computer to a plurality of client computers. Real time communication modes are established by the host computer between the client computers, each including communication channels between all the client computers. The host computer receives annotations entered into the GUIs at the client computers, each annotation identifying a span of words in the document to annotate and including an associated annotation type. The host computer updates the GUI to include for display the received annotations and inter-rater agreement statistics indicating the level of agreement between annotations received from each client computer and annotations received from the other client computers. The updated GUI is then transmitted by the host computer to the plurality of client computers.

Abstract: Mechanisms are provided, in a Question and Answer (QA) system, for identifying a related previously processed question. A first question is processed by the QA system to generate an answer to the first question and a supporting evidence passage that supports the answer to the first question being a correct answer to the first question. The QA system performs a lookup operation in a question repository based on an identifier of the supporting evidence passage to identify an entry corresponding to a previously processed question, different than the first question, that previously had an answer generated based on the supporting evidence passage. The QA system returns the previously processed question and the answer to the first question to a submitter of the first question.

Abstract: Mechanisms are provided for managing a corpus of content. A question is processed by a Question Answering (QA) system to generate an answer to the question and a supporting evidence passage. A corpus value metric is calculated for the supporting evidence passage based on a determined number of times the supporting evidence passage is used to generate a high ranking answer to questions submitted to the QA system. A first corpus management operation is performed on the supporting evidence passage in response to determining that the corpus value metric meets or exceeds a first threshold, the first corpus management operation increasing a relative importance of the supporting evidence passage within the corpus. A second corpus management operation on the supporting evidence passage is performed in response to determining that the corpus value metric meets or falls below a second threshold, the second corpus management operation decreasing the passage's relative importance.

Abstract: Mechanisms are provided for managing a corpus of content. A question is processed by a Question Answering (QA) system to generate an answer to the question and a supporting evidence passage. A corpus value metric is calculated for the supporting evidence passage based on a determined number of times the supporting evidence passage is used to generate a high ranking answer to questions submitted to the QA system. A first corpus management operation is performed on the supporting evidence passage in response to determining that the corpus value metric meets or exceeds a first threshold, the first corpus management operation increasing a relative importance of the supporting evidence passage within the corpus. A second corpus management operation on the supporting evidence passage is performed in response to determining that the corpus value metric meets or falls below a second threshold, the second corpus management operation decreasing the passage's relative importance.

Abstract: An approach is provided for monitoring the health of a Question/Answer (QA) Computing System. In the approach, performed by an information handling system, a number of static questions are periodically submitted to the QA system, wherein each of the static questions corresponds to a previously established verified answer. Responses are received from the QA system, with the responses including answers corresponding to the submitted static questions. Monitoring the performance of the QA system based on the received responses. When the monitoring detects a problem with the QA system, a user is notified of the detected problem.

Abstract: Mechanisms are provided for modifying an operation of a question answering (QA) system. An input question is received and processed to generate at least one query to be applied to a corpus of information. The at least one query is applied to the corpus of information to generate candidate answers to the input question from which a final answer is selected for output. A training engine modifies, using a machine learning technique that compares the final answer to a known correct answer for the input question, at least one of logic or configuration parameters of the QA system for at least one of the processing of the input question to generate the at least one query, applying of the at least one query to the corpus of information to generate the candidate answers, or the selecting of the final answer from the candidate answers.

Abstract: A mechanism is provided in a data processing system for automatically generating question and answer pairs for training a question answering system for a given domain. The mechanism receives user input of question text for a question to be submitted to a question answering system in a user interface. The mechanism determines a question strength score for the question text. The question strength score represents a likelihood the question text will result in a correct answer with high confidence. The mechanism presents a graphical representation of the question strength score in the user interface.

Abstract: Mechanisms are provided for answering questions about at least one previous execution of a question answering (QA) system on a previous input question. An input question is received that is directed to a previous execution of a QA system with regard to a previous input question. The input question is processed to generate at least one query for application to a corpus of information, which comprises information about the QA system and the previous execution of the QA system on the previous input question. The at least one query is applied to the corpus of information to generate candidate answers to the input question which are ranked according to confidence measure values associated with the candidate answers. A final answer for the input question is output based on the ranking of the candidate answers.

Abstract: An approach is provided for monitoring the health of a Question/Answer (QA) Computing System. In the approach, performed by an information handling system, a number of static questions are periodically submitted to the QA system, wherein each of the static questions corresponds to a previously established verified answer. Responses are received from the QA system, with the responses including answers corresponding to the submitted static questions. Monitoring the performance of the QA system based on the received responses. When the monitoring detects a problem with the QA system, a user is notified of the detected problem.

Abstract: Mechanisms are provided for answering questions about at least one previous execution of a question answering (QA) system on a previous input question. An input question is received that is directed to a previous execution of a QA system with regard to a previous input question. The input question is processed to generate at least one query for application to a corpus of information, which comprises information about the QA system and the previous execution of the QA system on the previous input question. The at least one query is applied to the corpus of information to generate candidate answers to the input question which are ranked according to confidence measure values associated with the candidate answers. A final answer for the input question is output based on the ranking of the candidate answers.

Abstract: Mechanisms are provided for modifying an operation of a question answering (QA) system. An input question is received and processed to generate at least one query to be applied to a corpus of information. The at least one query is applied to the corpus of information to generate candidate answers to the input question from which a final answer is selected for output. A training engine modifies, using a machine learning technique that compares the final answer to a known correct answer for the input question, at least one of logic or configuration parameters of the QA system for at least one of the processing of the input question to generate the at least one query, applying of the at least one query to the corpus of information to generate the candidate answers, or the selecting of the final answer from the candidate answers.

Abstract: An approach is provided to automatically classify and handle data. The approach is implemented by an information handling system. In the approach, data is received, from a sender, at a content management system. When the data is received, the system automatically utilizes an artificial intelligence (AI) engine (e.g., IBM Watson, etc.) to perform an unstructured information analysis using a pre-existing knowledge base. The result of using the AI engine is an identification of a confidentiality level of the data. The approach further performs an action based on the identified confidentiality level of the data.

Abstract: A system and method for transforming a thread of email messages into a real-time e-meeting. Collaborative processing between asynchronous and synchronous components are controlled through a UI which controls the selection of threaded messages and initiates an e-meeting including all the recipients of the thread, each participant may privately view the full content of the message by selecting the message, and the moderator has the option to terminate the real-time meeting. Any participant who accepts the invitation can see a synchronized inbox that is limited to the selected thread. A final summary of the decisions is then sent as a final message in the thread, thereby being captured in everyone's inbox.

Abstract: The present invention discloses a software solution for localization/globalization of software applications. Localization refers to a language specific version of globalized software. The invention can generate externalized language specific files that are decoupled from source code, while alleviating many mistakes and problems inherent in legacy localization methodologies. That is, the invention provides an end-to-end framework that automatically replaces source code strings with placeholders, which are linked to national language (NL) specific strings of a target language. During build time, an executable can be generated that is customized for the target language. The original source code remains unchanged, which makes the globalization process described transparent to software developers. Further, the placeholders are automatically generated for each build, which resolves many problems with manually specifying keys that replace text, such as orphaned keys, duplicate keys, and the like.

Abstract: A system and method for transforming a thread of email messages into a real-time e-meeting. Collaborative processing between asynchronous and synchronous components are controlled through a UI which controls the selection of threaded messages and initiates an e-meeting including all the recipients of the thread, each participant may privately view the full content of the message by selecting the message, and the moderator has the option to terminate the real-time meeting. Any participant who accepts the invitation can see a synchronized inbox that is limited to the selected thread. A final summary of the decisions is then sent as a final message in the thread, thereby being captured in everyone's inbox.