Abstract: A computer-implemented method includes receiving a query referencing entities, and determining non-polar questions (NPQs) for the query. Each of the NPQs omits a respective target entity (TE) of the entities. The method includes determining, for each of the NPQs, whether the NPQ is a non-matching NPQ by determining whether a top ranked answer for the NPQ matches the TE of the NPQ. The method includes proceeding to determine an updated input statement (UIS) for a non-matching NPQ by replacing the TE of the non-matching NPQs with the top ranked answer for the non-matching NPQ, determine an updated NPQ for the UIS, and determine whether the top ranked answer for the updated NPQ matches the TE of the updated NPQ, in an iterative or recursive manner. The method includes outputting a UIS as a substitute statement for the query.

Abstract: A computer-implemented method includes dividing a textual representation of a media content into a plurality of portions separated at temporal boundaries of the media content and performing an analysis of each portion of the plurality of portions of the textual representation of the media content to determine a characteristic associated with each respective portion of the textual representation of the media content, generating a multi-dimensional model assigning each determined characteristic to each associated respective portion of the plurality of portions of the textual representation of the media content, the multi-dimensional model identifying each determined characteristic and the temporal boundaries to enable control of an environmental control device to modify an environment proximate to a user based on the multi-dimensional model, and transmitting the multi-dimensional model to a user equipment configured to control the environmental control device to modify the environment proximate to the user base

Abstract: A computer converts a question received in a natural language format into a string of text elements. The computer searches a corpus comprising unstructured passages with the string of the text elements as search terms to identify a selection of unstructured passages from the corpus relevant to the text elements. The computer annotates the selection of relevant unstructured passages with one or more annotations according to at least one natural language annotation type to generate an annotated selection knowledge base. The computer modifies the string of text elements by annotating at least one of the text elements according to the at least one natural language annotation type. The computer searches the annotated selection knowledge base using the modified string of text elements to generate a selection of ranked passages. The computer identifies an answer to the question based on the selection of ranked passages.

Abstract: A computer system evaluating an input segment of a communication, in parallel, by a baseline classification model trained with baseline passages indicating dictionary meaning and multiple generative sequence models each trained to classify a particular passage from among multiple indirect passages indicating usage with an indirect meaning, to receive a separate score from the baseline classification model and each of the generative sequence models, each separate score indicating a classification probability for the input segment. The computer system, responsive to one or more particular scores generated by one or more of the generative sequence models exceeding a baseline score generated by the baseline classification model summed with a tuning factor, flagging the input segment as having a potentially indirect meaning.

Abstract: Mechanisms are provided to minimize personally identifiable information (PII) in an electronic document. An iterative personally identifiable information minimization (IPIIM) engine receives an electronic document comprising natural language content having a mention of a protected entity and obfuscates the mention of the protected entity to thereby generate a minimized natural language content. A question answering system processes the minimized natural language content to generate a listing of candidate answers and corresponding confidence scores and the IPIIM engine determines whether or not the minimized natural language content is sufficiently obfuscated based on the listing of candidate answers and corresponding confidence scores. In response to determining that the minimized natural language content is sufficiently obfuscated, the minimized natural language content is provided for processing by a requestor computing device.

Abstract: A method trains and utilizes an artificial intelligence (AI) system. The AI system receives a question that has contextual features. The method trains the AI system to identify entries in a corpus that have one or more of the contextual features from the question. The method further trains the AI system to: form a set of answers to the question based on identified contextual entries in the corpus; identify and name an entry in the corpus that has a highest quantity of contextual features that match the contextual features in the question as an initial answer to the question; identify and merge multiple other answers to the question from the corpus; and replace the initial answer with the merged answer in order to create a fully trained AI system. The fully trained AI system is then utilized to answer the question with the merged answer.

Abstract: Embodiments relate to an intelligent computer platform to identify and evaluate candidate passages response data in natural language form. A passage is analyzed by applying input tokens against passage tokens. A structure representing the analyzed passage is populated with of matching input and passage tokens. The input and passage tokens are used to assess the leveraged structure. First and second counts of token matching criteria are determined, including a first count of matching token entries and a second count of evaluated token entries. An alignment of the passage to a candidate question is calculated and a ratio of the first and second counts assessed. Data from the passage is returned with the ratio.

Abstract: Embodiments relate to an intelligent computer platform to identify and evaluate candidate passages response data in natural language form. Natural language processing is applied to analyze a passage against one or more input tokens to identify matching content. A structure representing the analyzed passage is populated with of matching input and passage tokens. A first count of matching token entries and a second count of evaluated token entries are determined and qualified by closeness criteria. An alignment of the passage to a candidate question is calculated, including assessing a ratio of the first and second counts as a confidence value. Matching passage data is return from the passage with the confidence value.

Abstract: A mechanism is provided for routinely evaluating an accuracy of a request processing pipeline. A set of questions is executed through the request processing pipeline, producing a list of answers, supporting documents, and accuracy metrics. A determination is made as to whether a document contribution value of each document associated with the answer is equal to or above a document contribution threshold value. For those documents equal to or above the document contribution threshold value, a snapshot is stored in a training-data data structure. Based on a clustering of questions, for each question cluster, a determination is made of an average accuracy metric. A comparison is performed and a determination is made as to whether an accuracy metric delta exceeds the accuracy metric threshold value. If so, a differential report is generated indicating a review is needed of a training of the request processing pipeline.

Abstract: Embodiments relate to a computer platform and corresponding process and program code to assess multimedia files with respect to similarity and duplicate media content. Data streams are converted into sequences of events, and object representation within the streams is identified and subject to processing with respect to the event sequences. A similarity assessment is conducted between two or more of the data streams, and a corresponding distance measurement to quantify similarity is produced. Duplicate data is selectively identified in response to the similarity assessment and the produced distance measurement.

Abstract: Embodiments relate to a computer platform and corresponding process and program code to assess multimedia files with respect to similarity and duplicate media content. Data streams are converted into sequences of events, and audio representation with in the streams is identified and subject to processing with respect to the event sequences. A similarity assessment is conducted between two or more of the data streams, and a corresponding distance measurement to quantify similarity is produced. Duplicate data is selectively identified in response to the similarity assessment and the produced distance measurement.

Abstract: A system includes a memory having instructions stored therein. The system also includes at least one processor in communication with the memory. The at least one processor is configured to execute the instructions to receive an input question in a source language, generate a first similarity score based at least in part on a source-language operand, generate a target-language operand based at least in part on the source-language operand, generate a second similarity score based at least in part on the target-language operand, generate a semantic concept score based at least in part on the first similarity score and the second similarity score, generate a set of ranked answers to the input question (“ranked answer set”) based at least in part on the semantic concept score, and output the ranked answer set.

Abstract: An approach is provided that receives a question at a question-answering (QA) system. The received question includes one or more terms, and the question pertains to a subject matter domain that is supported by the QA system. Analyzing a number of expressions included in a set of question-answer pairs (QA pairs), with the QA pairs being ground-truths established to in support of the subject matter domain. The analysis identifies whether a selected term from the question is a synonym for any of the expressions. The expressions that are identified as synonyms are then used in a QA pipeline that generates one or more candidate answers to the received question.

Abstract: Embodiments provide a computer implemented method for identifying and correcting a misspelling in a question answering (QA) system, wherein the QA system is coupled to a document corpus, and the document corpus includes a plurality of documents related to a particular domain. The method includes the following steps: receiving an input question and a plurality of passages, wherein the plurality of passages are extracted from the document corpus by the QA system; providing at least one alternate form for each token extracted from the input question and the plurality of passages; identifying at least one misspelled token; and scoring at least one alternate form of each identified misspelled token.

Abstract: A method determines a relevancy of answers to questions based on token relevance in a system capable of answering questions. One or more processors receive a question that is composed of a set of tokens T (T1, T2, . . . , Tn). The processor(s) select tokens T? (T?1, T?2, . . . , T?m) from the tokens T (T1, T2, . . . , Tn), where each T?j from T? is a noun, and classify each T?j as a noun type. The processor(s) scan a corpus to identify passages with candidate answers to the question, and analyze the identified passages utilizing noun entries in the passages classified as the noun type. The processor(s) train an artificial intelligence (AI) system to associate a relevancy to the question for the identified passages based on noun types, and then utilize the trained AI system to provide an answer to the question based on an output of the trained AI system.

Abstract: Embodiments relate to an intelligent computer platform to use ground truth data to rate source reliability, and application of the source reliability. A computer system, computer program product, and computer implemented method apply the ground truth data to evaluate a source, assess source reliability, and dynamically apply the assessed reliability. The assessed reliability is dynamically applied to response data, with the application yielding selective presentation of the response data based on the applied reliability assessment.

Abstract: Embodiments relate to an intelligent computer platform to use ground truth data to rate source reliability, and application of the source reliability. A computer system, computer program product, and computer implemented method apply the ground truth data to evaluate a document and statements therein, and dynamically apply the assessed reliability. The assessed reliability is dynamically applied to a source, with the application yielding acceptance of the document to the source based on the applied reliability assessment.

Abstract: A method comprising receiving, by a question and answer system, a first question, generating, by the question and answer system, a first answer set corresponding to the first question, each answer in the first answer set including one or more evidence passages, identifying, by the question and answer system, a geospatial or temporal modifier in the evidence passages, generating, by the question and answer system, a second question based on the first question and the geospatial or temporal modifier, generating, by the question and answer system, a second answer set corresponding to the second question, and returning, by the question and answer system, a question answer set based on the second answer set to a user.

Abstract: A method of augmenting a knowledge graph includes obtaining the knowledge graph, which includes entities and relationships between the entities defining respective edges, clustering the entities into knowledge domains using semantic distances determined between the entities and a threshold on the semantic distances, identifying strengths of the relationships between adjacent entities in the knowledge graph, creating knowledge chains from node pairs in the knowledge graph, including generating a minimum spanning tree using the strengths of the relationships, pruning edges from the knowledge chain using a threshold on weights corresponding to the edges, defining a first knowledge index for each of the knowledge chains, defining a second knowledge index for each of the knowledge domains, and defining a third knowledge index for the knowledge graph as a harmonic mean of a sum of the first knowledge indexes and a sum of the second knowledge indexes.

Abstract: In response to receiving a second verification record of a second location and time at which a user is verified as present by a second internet of things (loT) device based on biometric input recognition, a proximity service maintains the second verification record in association with a user identifier only if travel between the second location and a first location previously recorded at a first time prior to the second time is feasible as determined by a mapping service. In response to receiving a verification request for verifying feasibility of the proximity of an authorized user of an account identifier at a third location at which the account identifier is presented with a transaction request and detecting the second verification record is maintained, the proximity service verifies the feasibility of the proximity of the authorized user as present at the third location in view of the second location and time.