Abstract: A question answering system that determines whether a question is off-topic by performing the following steps: (i) receiving, by a question answering system, a set of documents; (ii) identifying topical subset(s) for each document of the set of documents using named entity recognition, where each topical subset relates to a corresponding topic; (iii) assigning a set of topic score(s) for each topical subset using natural language processing, where each topic score relates to a corresponding probability associated with the respective topical subset under a probabilistic language model; and (iv) determining, based, at least in part, on the topic score(s) corresponding to the topical subset(s), whether a question input into the question answering system is off-topic.

Abstract: A question answering system that determines whether a question is off-topic by performing the following steps: (i) receiving, by a question answering system, a set of documents; (ii) identifying topical subset(s) for each document of the set of documents using named entity recognition, where each topical subset relates to a corresponding topic; (iii) assigning a set of topic score(s) for each topical subset using natural language processing, where each topic score relates to a corresponding probability associated with the respective topical subset under a probabilistic language model; and (iv) determining, based, at least in part, on the topic score(s) corresponding to the topical subset(s), whether a question input into the question answering system is off-topic.

Abstract: An approach is provided for automatically generating user-specific interaction modes for processing question and answers at the information handling system by receiving a question from a user, extracting user context parameters identifying a usage scenario for the user, identifying first input and output presentation modes for the user based on the extracted user context parameters, monitoring user interaction with the system in relation to the question, and adjusting the first input and output presentation modes based on the extracted user context parameters and detected user interaction with the system.

Abstract: An approach is provided for automatically generating user-specific interaction modes for processing question and answers at the information handling system by receiving a question from a user, extracting user context parameters identifying a usage scenario for the user, identifying first input and output presentation modes for the user based on the extracted user context parameters, monitoring user interaction with the system in relation to the question, and adjusting the first input and output presentation modes based on the extracted user context parameters and detected user interaction with the system.

Abstract: An approach is provided to receive audible speech and convert the received speech to text while the audible speech is being delivered to a user. An annotation candidate is identified in the text and an annotation reference relating to the identified annotation candidate is retrieved and presented to the user.

Abstract: A question answering system that determines whether a question is off-topic by performing the following steps: (i) receiving, by a question answering system, a set of documents; (ii) identifying topical subset(s) for each document of the set of documents using named entity recognition, where each topical subset relates to a corresponding topic; (iii) assigning a set of topic score(s) for each topical subset using natural language processing, where each topic score relates to a corresponding probability associated with the respective topical subset under a probabilistic language model; and (iv) determining, based, at least in part, on the topic score(s) corresponding to the topical subset(s), whether a question input into the question answering system is off-topic.

Abstract: A question answering system that determines whether a question is off-topic by performing the following steps: (i) receiving, by a question answering system, a set of documents; (ii) identifying topical subset(s) for each document of the set of documents using named entity recognition, where each topical subset relates to a corresponding topic; (iii) assigning a set of topic score(s) for each topical subset using natural language processing, where each topic score relates to a corresponding probability associated with the respective topical subset under a probabilistic language model; and (iv) determining, based, at least in part, on the topic score(s) corresponding to the topical subset(s), whether a question input into the question answering system is off-topic.

Abstract: A method, computer program product, and computer system for identifying data associated with an event. A recommendation is provided to at least the event based upon, at least in part, at least one of a character of the event determined based upon, at least in part, the data associated with the event, and a personality of a real-time crowd at the event determined based upon, at least in part, the data associated with the event.

Abstract: A method, computer program product, and computer system for identifying data associated with an event. A recommendation is provided to at least the event based upon, at least in part, at least one of a character of the event determined based upon, at least in part, the data associated with the event, and a personality of a real-time crowd at the event determined based upon, at least in part, the data associated with the event.

Abstract: A method, system and computer-usable medium are disclosed for preserving conceptual distance within unstructured documents by characterizing conceptual relationships. Natural language processing is applied to content in a plurality of documents to identify topics and subjects. Analytic analysis is then applied to the identified topics and subjects to identify concepts. The content in each of the plurality of documents is partitioned into a first structured hierarchy, preserving at least one structure in each document inherent in the each document. Access is then provided to the content through a first index based upon utilizing the first structured hierarchy and through a second index utilizing a second structured hierarchy. The conceptual relationship criteria are based upon a directed graph with weights based upon a similarity and a distance based upon concepts.

Abstract: A method, system and computer-usable medium are disclosed for preserving conceptual distance within unstructured documents by characterizing conceptual relationships. Natural language processing is applied to content in a plurality of documents to identify topics and subjects. Analytic analysis is then applied to the identified topics and subjects to identify concepts. The content in each of the plurality of documents is partitioned into a first structured hierarchy, preserving at least one structure in each document inherent in the each document. Access is then provided to the content through a first index based upon utilizing the first structured hierarchy and through a second index utilizing a second structured hierarchy. The conceptual relationship criteria are based upon a directed graph with weights based upon a similarity and a distance based upon concepts.

Abstract: An approach is provided for automatically generating user-specific interaction modes for processing question and answers at the information handling system by receiving a question from a user, extracting user context parameters identifying a usage scenario for the user, identifying first input and output presentation modes for the user based on the extracted user context parameters, monitoring user interaction with the system in relation to the question, and adjusting the first input and output presentation modes based on the extracted user context parameters and detected user interaction with the system.

Abstract: An approach is provided to receive audible speech and convert the received speech to text while the audible speech is being delivered to a user. An annotation candidate is identified in the text and an annotation reference relating to the identified annotation candidate is retrieved and presented to the user.

Abstract: An approach is provided for automatically generating user-specific interaction modes for processing question and answers at the information handling system by receiving a question from a user, extracting user context parameters identifying a usage scenario for the user, identifying first input and output presentation modes for the user based on the extracted user context parameters, monitoring user interaction with the system in relation to the question, and adjusting the first input and output presentation modes based on the extracted user context parameters and detected user interaction with the system.

Abstract: A method, system and computer-usable medium are disclosed for preserving conceptual distance within unstructured documents by characterizing conceptual relationships. Natural language processing is applied to content in a plurality of documents to identify topics and subjects. Analytic analysis is then applied to the identified topics and subjects to identify concepts. The content in each of the plurality of documents is partitioned into a first structured hierarchy, preserving at least one structure in each document inherent in the each document. Access is then provided to the content through a first index based upon utilizing the first structured hierarchy and through a second index utilizing a second structured hierarchy. The conceptual relationship criteria are based upon a directed graph with weights based upon a similarity and a distance based upon concepts.

Abstract: A method, system and computer-usable medium are disclosed for preserving conceptual distance within unstructured documents by characterizing conceptual relationships. Natural language processing is applied to content in a plurality of documents to identify topics and subjects. Analytic analysis is then applied to the identified topics and subjects to identify concepts. The content in each of the plurality of documents is partitioned into a first structured hierarchy, preserving at least one structure in each document inherent in the each document. Access is then provided to the content through a first index based upon utilizing the first structured hierarchy and through a second index utilizing a second structured hierarchy. The conceptual relationship criteria are based upon a directed graph with weights based upon a similarity and a distance based upon concepts.

Abstract: A system, and computer program product for disambiguation of dependent referring expression in natural language processing are provided in the illustrative embodiments. A portion of a document in a set of document is selected, the portion including a set of dependent referring expression instances. The portion is filtered to identify an instance from a set of dependent referring expression instances by using a linguistic characteristic of the instance, the instance of dependent referring expression referring to a full expression occurring in the set of documents. The full expression is located in one member document in the set of documents by locating where the dependent referring expression is defined to be a stand-in for the full expression. The instance is resolved using the full expression such that information about the full expression is available at a location of the instance.

Abstract: A system, and computer program product for disambiguation of dependent referring expression in natural language processing are provided in the illustrative embodiments. A portion of a document in a set of document is selected, the portion including a set of dependent referring expression instances. The portion is filtered to identify an instance from a set of dependent referring expression instances by using a linguistic characteristic of the instance, the instance of dependent referring expression referring to a full expression occurring in the set of documents. The full expression is located in one member document in the set of documents by locating where the dependent referring expression is defined to be a stand-in for the full expression. The instance is resolved using the full expression such that information about the full expression is available at a location of the instance.

Abstract: A method for disambiguation of dependent referring expression in natural language processing is provided in the illustrative embodiments. A portion of a document in a set of document is selected, the portion including a set of dependent referring expression instances. The portion is filtered to identify an instance from a set of dependent referring expression instances by using a linguistic characteristic of the instance, the instance of dependent referring expression referring to a full expression occurring in the set of documents. The full expression is located in one member document in the set of documents by locating where the dependent referring expression is defined to be a stand-in for the full expression. The instance is resolved using the full expression such that information about the full expression is available at a location of the instance.

Abstract: Provided are techniques for creating a hierarchy of results. An unstructured result set is received. Each result in the unstructured result set is hashed into a preliminary result set. For each hashed result, one or more related concepts are obtained using one or more taxonomies; one or more matches between the one or more related concepts and other hashed results in the preliminary result set are found; a candidate group for the hashed result is formed, wherein the candidate group includes the hashed result and one or more other hashed results based on the one or more matches; in response to determining that a frequency associated with the hashed result exceeds a threshold, the candidate group associated with that hashed result is compared with pre-existing groups that are in use; and, based on the comparing, one or more suggestions regarding the candidate group are provided.