Abstract: Embodiments provide a computer implemented method for ranking supporting passages in a question answering (QA) system. 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; identifying a plurality of candidate answer occurrences from the plurality of passages; assigning a plurality of first local features to each candidate answer occurrence; merging the plurality of candidate answer occurrences to generate a group of candidate answers; assigning a plurality of second local features and a plurality of nonlocal features to each candidate answer; ranking the group of candidate answers using a linear answer scoring model; and ranking the plurality of candidate answer occurrences using the linear answer scoring model.

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: A method trains a neural network to identify an event based on discrepancies in answers to factoid questions at different times. One or more processors identify answers to a series of factoid questions. The processor(s) compare the answers from the series of factoid questions in order to determine discrepancies in the answers at different times, and then train a neural network to identify an event based on the discrepancies in the answers at the different times.

Abstract: A question and answer (QA) system, computer program product, and computer-implemented method configured to determine an answer to a question that includes a measurement value. In one example, the QA system receives a question and analyzes the question to identify a measurement value specified in the question. The QA system determines relevant passages to the question. The QA system assigns a measurement value confidence score to a relevant passage based on a comparison of the measurement value specified in the question and a second measurement value specified in the relevant passage. The QA system determines an order of the relevant passages using the measurement value confidence score of each of the relevant passages. The QA system determines an answer to the question based on the order of the relevant passages.

Abstract: A method of augmenting an information retrieval method including receiving a query, parsing the query to generate an instance graph, providing a plurality of constraint graphs, organized into at least two ranks, each constraint graph associated with a focus, determining at least one of the constraint graphs matching a structure of the instance graph, and annotating the query with the focus of each matching constraint graph of a highest rank among all matching constraint graphs.

Abstract: Embodiments relate to an intelligent computer platform to identify and evaluate candidate passage 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 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 returned from the passage with the confidence value.

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 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: A method, apparatus and computer program product for creating parse trees from mixed records is described. A mixed record is received including a first entry containing a first natural language phrase and a second entry containing a first structured data entry. Using the first natural language phrase, a first parse tree structure is created joining words in the first natural language phrase with natural links indicating their semantic relationship within the first natural language phrase. A first synthetic node is created which represents the first structured data entry. The first synthetic is joined to the first parse tree structure using a synthetic link to a node in the parse tree to produce a pseudo parse tree. The pseudo parse tree is sent to a question answer system for answering user queries by reference to the pseudo parse tree.

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 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 for providing unsupervised entity resolution to a natural language processing system includes receiving a named entity for training from the natural language processing system, searching a corpus for a first undisambiguated named entity corresponding to the named entity, identifying a plurality of disambiguated named entities corresponding to the first undisambiguated named entity, identifying a plurality of aliases for each of the disambiguated named entities, training a classifier for the each of the disambiguated named entities utilizing the aliases identified for respective ones of the disambiguated named entities using the corpus, and resolving the named entity using the classifier, wherein resolving the named entity comprises selecting one of the disambiguated named entities from among the disambiguated named entities and returning, automatically, the selected disambiguated named entity to the natural language processing system.

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 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 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 is assessed. Data from the passage are returned with the ratio.

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: A cognitive system improves the accuracy of a natural language statement by analyzing relationships between entities in a knowledge graph for the statement. A natural language processing engine extracts entities and relationships in the statement, and a yes/no pipeline gauges the accuracy of the statement. If a statement is deemed inaccurate, the knowledge graph is used to identify a predominant relationship between certain entities, and a candidate phrase representing the predominant relationship is generated and presented to the user as a suggested replacement for a target phrase in the statement representing the relationship. The yes/no pipeline computes an accuracy score for the statement, and the statement is deemed inaccurate when the score is below a programmable threshold. The assertiveness of the system can be tuned by requiring the accuracy score of a proposed modified statement to be greater than the score of the original statement plus some tuning factor.

Abstract: A method includes receiving, by a computer system configured to generate search result, a query, identifying a plurality of entities in the query, determining, using a knowledge graph, a measure of a relationship between the entities in the query, identifying a replacement entity for a first entity of the entities in the query, wherein the replacement entity is determined to improve the measure of the relationship between the entities when the first entity is replaced by the replacement entity, and generating a search result using the query modified by the replacement entity, which replaces the first entity in the query.

Abstract: An approach is provided in which an information handling system identifies candidate answers from a knowledge base that correspond to a question comprising a lexical answer type (LAT). The information handling system determines sub-LATs corresponding to the LAT in a database that are child LATs of the LAT. The information handling system then identifies a set of the candidate answers that correspond to at least one of the sub-LATs and ranks the set of candidate answers based on one or more ranking criterion. In turn, the information handling system provides the ranked set of candidate answers to a user.

Abstract: Embodiments for processing questions based on equivalence classes in a cognitive question answering system. A plurality of syntactic representations of a plurality of questions asked of the cognitive question answering system are provided. A plurality of syntactic representations of a plurality of passages ingested by the cognitive question answering system are provided. Question focus to candidate passage pairs are mapped to form an equivalence class mapping, and the equivalence class mapping is used to determine an answer to one of the plurality of questions asked of the cognitive question answering system.

Abstract: A controller receives a multi-facet natural language question from a user at a question answering system and generates one or more inquiry questions to submit to the question answering system for an order type requirement of the multi-facet natural language question. The controller evaluates responses, each with a respective confidence score by the question answering system, to each of the one or more inquiry questions to identify a selection of answers from among the responses, the selection of answers capped at a number of specific answers assessed for the multi-facet natural language question. The controller merges the selection of answers into a single aggregated answer to return to the user in response to the multi-facet natural language question.