Abstract: A computer-implemented method of managing perspective data associated with a common feature in items is disclosed. The method can include identifying a common feature in a first item and a second item, the first item having a set of perspective data and establishing a subset of perspective data associated with the common feature. The method can include associating the subset of perspective with the second item. The method can include determining a set of relevancy scores for the subset of perspective data associated with the common feature and establishing a set of relevant perspective data from the subset of perspective data. The set of relevant perspective data can have relevancy scores outside of a relevancy threshold. The method can include associating the set of relevant perspective data with the second item.

Abstract: First, a computer may receive an input query of a first medium type. The input query may then be analyzed. Based on the analysis, the input query may be categorized as being associated with at least a second medium type. A first-medium-type search of a set of corpora may then be performed. Based on the results of the first-medium-type search, a candidate answer of the first medium type may be generated. In response to the categorizing, a second-medium-type search of the set of corpora may also be performed.

Abstract: A system and computer-implemented method for managing perspective data is disclosed. The method may include identifying a variant feature of an item having a first set of perspective data. The method may include grouping, based on the variant feature, the first set of perspective data into a first group and a second group. The method may include determining a first set of relevancy scores for the first group and a second set of relevancy scores for the second group. The method may also include establishing, using at least one of the first and second relevancy scores, a second set of perspective data configured to include a subset of the first set of perspective data.

Abstract: A system and computer implemented method for managing perspective data is disclosed. The method may include collecting a first lot of perspective data for an item. The method may include introducing a variant feature to the item to constitute a modified item. The method may include collecting a second lot of perspective data for the modified item. The method may also include evaluating the first and second lots of perspective data to ascertain a sentiment fluctuation based on information relevant to the variant feature.

Abstract: A system and computer-implemented method for managing perspective data is disclosed. The method may include identifying a variant feature of an item having a first set of perspective data. The method may include grouping, based on the variant feature, the first set of perspective data into a first group and a second group. The method may include determining a first set of relevancy scores for the first group and a second set of relevancy scores for the second group. The method may also include establishing, using at least one of the first and second relevancy scores, a second set of perspective data configured to include a subset of the first set of perspective data.

Abstract: A system and computer implemented method for managing perspective data is disclosed. The method may include collecting a first lot of perspective data for an item. The method may include introducing a variant feature to the item to constitute a modified item. The method may include collecting a second lot of perspective data for the modified item. The method may also include evaluating the first and second lots of perspective data to ascertain a sentiment fluctuation based on information relevant to the variant feature.

Abstract: A cohort analysis mechanism analyzes cohorts with similar attributes to extrapolate additional knowledge and answer a question in a question answering system. The cohort analysis mechanism identifies cohorts for an entity of the question and extracts relevant data concerning the cohorts. The cohort analysis mechanism aggregates the relevant information for evidence scoring and answer scoring to answer a question posed to the question answering system. The aggregating of the data includes combining and ranking answers from the cohorts, gathering evidence and then answering the question with the gathered evidence.

Abstract: A cohort analysis mechanism analyzes cohorts with similar attributes to extrapolate additional knowledge and answer a question in a question answering system. The cohort analysis mechanism identifies cohorts for an entity of the question and extracts relevant data concerning the cohorts. The cohort analysis mechanism aggregates the relevant information for evidence scoring and answer scoring to answer a question posed to the question answering system. The aggregating of the data includes combining and ranking answers from the cohorts, gathering evidence and then answering the question with the gathered evidence.

Abstract: In some NLP systems, queries are compared to different data sources stored in a corpus to provide an answer to the query. However, the best data sources for answering the query may not currently be contained within the corpus or the data sources in the corpus may contain stale data that provides an inaccurate answer. When receiving a query, the NLP system may evaluate the query to identify a data source that is likely to contain an answer to the query. If the data source is not currently contained within the corpus, the NLP system may ingest the data source. If the data source is already within the corpus, however, the NLP may determine a time-sensitivity value associated with at least some portion of the query. This value may then be used to determine whether the data source should be re-ingested—e.g., the information contained in the corpus is stale.

Abstract: In some NLP systems, queries are compared to different data sources stored in a corpus to provide an answer to the query. However, the best data sources for answering the query may not currently be contained within the corpus or the data sources in the corpus may contain stale data that provides an inaccurate answer. When receiving a query, the NLP system may evaluate the query to identify a data source that is likely to contain an answer to the query. If the data source is not currently contained within the corpus, the NLP system may ingest the data source. If the data source is already within the corpus, however, the NLP may determine a time-sensitivity value associated with at least some portion of the query. This value may then be used to determine whether the data source should be re-ingested—e.g., the information contained in the corpus is stale.

Abstract: System, computer-implemented method, and computer program product to receive a case by a deep question answering system, identify a policy relevant in generating a response to the case, the policy containing a set of criteria used in generating the response to the case, produce, by a first annotator, of a set of annotators, one or more relevant passages of the case, compute a criteria score for a first criterion, of the set of criteria, based on the one or more relevant passages of the case, an determine that the first criterion is met by the case when the criteria score for the first criterion exceeds a predefined threshold.

Abstract: System, computer-implemented method, and computer program product to receive a case by a deep question answering system, identify a policy relevant in generating a response to the case, the policy containing a set of criteria used in generating the response to the case, produce, by a first annotator, of a set of annotators, one or more relevant passages of the case, compute a criteria score for a first criterion, of the set of criteria, based on the one or more relevant passages of the case, an determine that the first criterion is met by the case when the criteria score for the first criterion exceeds a predefined threshold.

Abstract: System, method, and computer program product for performing an operation, the operation comprising receiving, by a deep question answering system, a question not specifying an element of input data, identifying a set of possible values for the element of input data, generating, by the deep question answering system, a respective set of candidate answers for the question: (i) without the element of input data, and (ii) with each possible value in the set of possible values for the element of input data, and returning at least one candidate answer from at least one set of candidate answers as responsive to the question.

Abstract: System, method, and computer program product for performing an operation, the operation comprising receiving, by a deep question answering system, a question not specifying an element of input data, identifying a set of possible values for the element of input data, generating, by the deep question answering system, a respective set of candidate answers for the question: (i) without the element of input data, and (ii) with each possible value in the set of possible values for the element of input data, and returning at least one candidate answer from at least one set of candidate answers as responsive to the question.

Abstract: System, method, and computer program product for performing an operation, the operation comprising analyzing a question submitted to a deep question answering system to determine a level of sophistication of the question, and modifying one or more subsequent communications issued by the deep question answering system based on the determined level of sophistication, wherein the modifying attempts to more closely match the determined level of sophistication of the question with a level of sophistication of the one or more subsequent communications.

Abstract: System, method, and computer program product for performing an operation, the operation comprising analyzing a question submitted to a deep question answering system to determine a level of sophistication of the question, and modifying one or more subsequent communications issued by the deep question answering system based on the determined level of sophistication, wherein the modifying attempts to more closely match the determined level of sophistication of the question with a level of sophistication of the one or more subsequent communications.

Abstract: System, method, and computer program product to determine that a question received by a deep question answering system is speculative, generate, by one or more predictive algorithms, a set of candidate answers, compute a score for each candidate answer in the set of candidate answers, and return a first candidate answer, of the set of candidate answers, as responsive to the speculative question received by the deep question answering system.

Abstract: System, method, and computer program product to determine that a question received by a deep question answering system is speculative, generate, by one or more predictive algorithms, a set of candidate answers, compute a score for each candidate answer in the set of candidate answers, and return a first candidate answer, of the set of candidate answers, as responsive to the speculative question received by the deep question answering system.

Abstract: In some NLP systems, queries are compared to different data sources stored in a corpus to provide an answer to the query. However, the best data sources for answering the query may not currently be contained within the corpus or the data sources in the corpus may contain stale data that provides an inaccurate answer. When receiving a query, the NLP system may evaluate the query to identify a data source that is likely to contain an answer to the query. If the data source is not currently contained within the corpus, the NLP system may ingest the data source. If the data source is already within the corpus, however, the NLP may determine a time-sensitivity value associated with at least some portion of the query. This value may then be used to determine whether the data source should be re-ingested—e.g., the information contained in the corpus is stale.

Abstract: In some NLP systems, queries are compared to different data sources stored in a corpus to provide an answer to the query. However, the best data sources for answering the query may not currently be contained within the corpus or the data sources in the corpus may contain stale data that provides an inaccurate answer. When receiving a query, the NLP system may evaluate the query to identify a data source that is likely to contain an answer to the query. If the data source is not currently contained within the corpus, the NLP system may ingest the data source. If the data source is already within the corpus, however, the NLP may determine a time-sensitivity value associated with at least some portion of the query. This value may then be used to determine whether the data source should be re-ingested—e.g., the information contained in the corpus is stale.