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 mechanism is provided in a data processing system for tailoring question answering system output based on user expertise. The mechanism receives an input question from a questioning user and determines a set of features associated with text of the input question. The mechanism determines an expertise level of the questioning user based on the set of features associated with the text of the input question using a trained expertise model. The mechanism generates one or more candidate answers for the input question and tailors output of the one or more candidate answers based on the expertise level of the questioning user.

Abstract: A mechanism is provided in a data processing system for tailoring question answering system output based on user expertise. The mechanism receives an input question from a questioning user and determines a set of features associated with text of the input question. The mechanism determines an expertise level of the questioning user based on the set of features associated with the text of the input question using a trained expertise model. The mechanism generates one or more candidate answers for the input question and tailors output of the one or more candidate answers based on the expertise level of the questioning user.

Abstract: An active learning framework is operative to identify informative questions that should be added to existing question-answer (Q&A) pairs that comprise a training dataset for a learning model. In this approach, the question-answer pairs (to be labeled as “true” or “false”) are automatically selected from a larger pool of unlabeled data. A spatial-directed clustering algorithm partitions the relevant question-answer space of unlabeled data. A margin-induced loss function is then used to rank a question. For each question selected, a label is then obtained, preferably by assigning a prediction for each associated question-answer pair using a current model that has been trained on labeled question-answer pairs. After the questions are labeled, an additional re-sampling is performed to assure high quality of the training data. Preferably, and with respect to a particular question, this additional re-sampling is based on a distance measure between correct and incorrect answers.

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 mechanism is provided in a data processing system for tailoring question answering system output based on user expertise. The mechanism receives an input question from a questioning user and determines a set of features associated with text of the input question. The mechanism determines an expertise level of the questioning user based on the set of features associated with the text of the input question using a trained expertise model. The mechanism generates one or more candidate answers for the input question and tailors output of the one or more candidate answers based on the expertise level of the questioning 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: An active learning framework is operative to identify informative questions that should be added to existing question-answer (Q&A) pairs that comprise a training dataset for a learning model. In this approach, the question—answer pairs (to be labeled as “true” or “false”) are automatically selected from a larger pool of unlabeled data. A spatial-directed clustering algorithm partitions the relevant question-answer space of unlabeled data. A margin-induced loss function is then used to rank a question. For each question selected, a label is then obtained, preferably by assigning a prediction for each associated question-answer pair using a current model that has been trained on labeled question-answer pairs. After the questions are labeled, an additional re-sampling is performed to assure high quality of the training data. Preferably, and with respect to a particular question, this additional re-sampling is based on a distance measure between correct and incorrect answers.

Abstract: A mechanism is provided in a data processing system for categorizing a user providing a text input. The mechanism receives an input text written by a user and determines a set of features associated with the input text. The mechanism processes the input text and the set of features by a detection model. The detection model comprises a plurality of detectors corresponding to a plurality of categories. Each of the plurality of detectors determines whether the user fits a respective category based on the input text and the set of features. The mechanism categorizes the user into one or more of the plurality of categories based on a result of processing the input text and the set of features by the detection model.

Abstract: A mechanism is provided in a data processing system for tailoring question answering system output based on user expertise. The mechanism receives an input question from a questioning user and determines a set of features associated with text of the input question. The mechanism determines an expertise level of the questioning user based on the set of features associated with the text of the input question using a trained expertise model. The mechanism generates one or more candidate answers for the input question and tailors output of the one or more candidate answers based on the expertise level of the questioning user.

Abstract: A method, computer system and/or computer program product pre-highlight text that is located in a search. A text highlight and a triple statement semantic annotation based on the text highlight of a first document are received. The triple statement semantic annotation comprises a subject, a relationship and an object. A natural language processing (NLP) pattern based on the triple statement semantic annotation is generated. The NLP pattern is representative of a linguistic pattern between the text highlight and the triple statement semantic annotation. A multi-dimensional linguistic profile is generated based on the text highlight, the triple statement semantic annotation and the NLP pattern, wherein the multi-dimensional linguistic profile defines entities, relationships and attributes associated with document text. Text in a second document is compared with the multi-dimensional linguistic profile, and text in the second document is highlighted based on the comparison.

Abstract: A method, computer system and/or computer program product pre-highlight text that is located in a search. A text highlight and a triple statement semantic annotation based on the text highlight of a first document are received. The triple statement semantic annotation comprises a subject, a relationship and an object. A natural language processing (NLP) pattern based on the triple statement semantic annotation is generated. The NLP pattern is representative of a linguistic pattern between the text highlight and the triple statement semantic annotation. A multi-dimensional linguistic profile is generated based on the text highlight, the triple statement semantic annotation and the NLP pattern, wherein the multi-dimensional linguistic profile defines entities, relationships and attributes associated with document text. Text in a second document is compared with the multi-dimensional linguistic profile, and text in the second document is highlighted based on the comparison.