Abstract: A method and system for determining a location of origin and a time period in which a document was written is disclosed. A text is received and a set of linguistic characteristics for the text are identified. A set of possible locations and time periods for the text are determined based on the set of linguistic characteristics. A set of reference documents are used to determine a proximity rating for the text based upon a determination of how close the text is to the reference documents. The potential locations and time periods are ranked and returned for presentation.

Abstract: A method is provided for analyzing log message content. The computer-implemented method may include detecting, by at least one processor, log messages in an application code, identifying a log level assigned to each of the log messages, and performing natural language processing (NLP) analysis on each of the log messages by using at least keyword and synonym matching percentage analysis criteria. The computer-implemented method may further include determining, in response to the NLP analysis, a severity score of each of the log messages, and reclassifying, based on the severity score, the assigned log level of one or more of the log messages to a different log level.

Abstract: Aspects of the present disclosure relate to identifying spans within unstructured electronic text. Natural language content is received. A part of speech and slot name of each word within the natural language content is identified. A parse tree representation is then generated based on the natural language content, wherein visual characteristics of each node of a plurality of nodes within the parse tree representation depend on the part of speech and slot name of each word. A bounding box identifying a span category is then generated around a set of nodes on the parse tree representation by a machine learning model.

Abstract: A method for de-identifying protected health information (PHI) associated with electronic medical records (EMRs) based on a common analysis structure (CAS) is provided. The method may include detecting a system event associated with a system comprising the EMRs. The method may further include in response to detecting the system event, detecting a first CAS associated with the EMRs. The method may further include extracting first CAS data associated with the first CAS, wherein the first CAS data comprises unstructured data associated with the EMRs and normalized annotations based on CAS objects that are associated with the unstructured data. The method may further include obfuscating the unstructured data associated with the first CAS. The method may also include generating a second CAS comprising the obfuscated unstructured data and a copied version of the normalized annotations, wherein the copied version of normalized annotations are correlated with the obfuscated unstructured data.

Abstract: A phrase may be received that includes a plurality of tokens in a natural language format. A plurality of levels relating to dependencies between tokens of the plurality of tokens within the phrase is determined. A matrix structure is generated for the phrase. The matrix structure utilizes a plurality of rows and a plurality of columns to store data of the phrase. The plurality of rows and the plurality of columns each indicate one of an order of tokens of the plurality of tokens or levels of the plurality of levels.

Abstract: An approach is disclosed for providing built-in consent permissions for users, groups, processes, and programs accessing a part of a filesystem. The method includes integrating a consent access control into a plurality of files in a filesystem. A first request from a first requestor to access information from a first file in the filesystem is received. A first access policy for the first requestor is determined. The first access policy includes a first selective data conversion. A second request from a second requestor to access information from the first file in the filesystem is received. A second access policy including a second selective data conversion for the second requestor different from the first access policy for the first requestor is determined. An access control mode that enables or inhibits enforcement of the built-in permissions is provided.

Abstract: Sentiment scores for a first set of text can be normalized based on a statistical measure of sentiment of a corpus of text authored by a set of authors having respective personality profiles similar to a personality profile of an author of the first set of text. The set of authors can be grouped in a first cluster based on a range of at least one metric of a personality profile. A plurality of respective sentiment scores for portions of the corpus can be generated for the first cluster. A statistical measure of the plurality of respective sentiment scores can be generated. The plurality of respective sentiment scores can be normalized based on the statistical measure. The plurality of respective normalized sentiment scores can be applied to the first set of text to generate one or more sentiment scores for the first set of text.

Abstract: An approach is provided that analyzes electronic document sets, each of the sets written by a different author. The analysis includes performing a normalized sentiment analysis of the documents which results in normalized sentiment scores that pertain to each of the authors. The normalize sentiment scores are stored in a data store that is accessible from a question answering (QA) system. The question answering system then receives a sentiment-based question. Responsively, the QA system generates a qualitative set of candidate answers, with the candidate answers based at least in part on the normalized sentiment scores retrieved from the data store.

Abstract: Resource provisioning to a process in a distributed computing system, such as a cloud computing system. An instruction to provision a resource is received. Portions of the resource are provisioned to the process as they become available, and prior to all portions becoming available, based on determining that the provisioning speed is greater than or equal to the use speed for the resource. If the use speed is faster, it may be actively slowed down.

Abstract: A method of machine learning that teaches a computer to determine likelihood that a medical journal article is classified as high value for an intended system. In some embodiments, the method includes procuring, in a medical articles database on the computer, a training set including medical articles recommended by subject matter experts associated with medical journals that have published the medical articles. The method can also include identifying, by a feature extraction controller of the computer, first features in the medical articles via a remote annotation service and a remote article information service. The method can also include identifying, by intended system services electronically available to the intended system, second features in the medical articles. The method can also include reducing, by the feature extraction controller, the first and second features to form a set of relevant features.

Abstract: Mechanisms are provided for implementing a disambiguation engine for disambiguating content. Electronic content is received from a corpus of electronic content, and analyzed to identify an ambiguous portion of content. The ambiguous portion of content is a portion of the electronic content whose meaning is not made explicit in the ambiguous portion of content. A context associated with the ambiguous portion of content is determined and a set of one or more context based ambiguous content interpretation rules associated with the determined context is applied to the ambiguous portion of content to generate an interpretation of the ambiguous portion of content. The ambiguous portion of content is annotated based on the interpretation to generate disambiguated electronic content which is stored for processing as part of a subsequent operation.

Abstract: A recommendation engine for works of literature uses patterns of flow and element similarities for scoring a first user-rated work of literature against one or more recommendation candidate works of literature. Cluster models are created using meta-data modeling the works of literature, the meta-data having literary element categories and instances within each category. Each instance is described by an index value (position in the literature) and significance value (e.g. weight or significance). Cluster finding process(es) invoked for each instance in each category find Similarity Concept clusters and Consistency Trend clusters, which are recorded into the cluster models representing each work of literature. The cluster model can be printed or displayed so that a user can visually understand the ebb and flow of each literary element in the literature, and may be digitally compared to other cluster models of other works of literature for potential recommendation to a user.

Abstract: Embodiments relate to a system, program product, and method for use with an intelligent computer platform to decipher analogical phrases. The method identifies A category is identified and a list of definitions is created for each parsed subcomponent of the phrase. The definitions are ranked in the list based on their relevance to the identified category and an outcome is identified based on the ranked relevance. A corpus is searched for evidence of an analogical pattern associated with the ranked list and each entry in the ranked list is scored based on congruence with the analogical pattern. An outcome is generated based on the scoring and is representative of the definition with the strongest congruence to the analogical pattern.

Abstract: A generator categorizes documents in one or more transactions into buckets, each identified by a separate category for an expected time window based on a separate relative age of each of the documents evaluated from one or more dates identified in the documents. The generator trains a document classifier with a model of the separate relative age of each of the documents as a temporal characteristic correlated with the respective category of a respective bucket of the buckets. The document classifier executes on a input documents to classify each of the input documents as a particular logical type identified by a particular category from among multiple logical types.

Abstract: Deep semantic analysis is performed on an electronic literary work in order to detect plot elements and optional other storyline elements such as characters within the work. Multiple levels of abstract are generated into a model representing the literary work, wherein each element in each abstraction level may be independently rated for preference by a user. Through comparison of multiple abstraction models and one or more user rating preferences, one or more alternative literary works may be automatically recommended to the user.

Abstract: A visualization of literary elements of a work of literature, such as a novel or short story, is generated from meta-data records representing a digital work of literature including literary elements (humor, drama, adventure, etc.), characters, and plot devices related to a position within the work of literature where each appears. A significance level is determined for each of the elements, characters and plot devices at each position within the work of literature, and these are plotted into a sequential graph having position (e.g. timeline) axis and a significance level axis. The sequential graph is then output for printing or display. Human-generated and machine-generated meta-data may be ingested equally well by the method. Colors, line thickness, and a broken line patterns may be employed for greater visual meaning. And, the sequential graph may be annotated according to segments (e.g. chapters, sections) and dominant genre within each segment.

Abstract: Mechanisms are provided for validating a candidate answer to an input question. A candidate answer to an input question is identified using a natural language processing of the input question and a corpus of information from which the candidate answer is identified. A validator is selected to apply to the candidate answer based on a characteristic of a correct answer for the input question. The validator is applied to the candidate answer to evaluate whether or not criteria of the validator are met by the candidate answer. Validation information is generated based the evaluation of whether or not criteria of the validator are met by the candidate answer. The validation information is stored in a validation status object associated with the input question.

Abstract: Mechanisms are provided for processing sources of content in a corpus of information associated with a domain. The mechanisms ingest a plurality of sources of content in the corpus of information associated with the domain and determine at least one temporal category for the domain based on identification of frequently occurring references to at least one of temporal terms or time spans specified in the plurality of sources of content in the corpus of information associated with the domain. The mechanisms store the at least one temporal category for the domain in association with the domain and process queries applied to the plurality of sources of content in the corpus of information associated with the domain based on the stored at least one temporal category for the domain.

Abstract: A classifier receives a digital scan of a document and converts the content of the document in the digital scan from an image into text. The classifier analyzes the text to determine one or more predicted roles of one or more signatories, each predicted role determined based on one or more signature elements in the content of the document executed by the one or more signatories. The classifier evaluates each of the one or more predicted roles in view of a plurality of expected signatory role characteristics of a plurality of categories of documents of a transaction to select a particular category associated with the document from among the plurality of categories. The classifier classifies the document within the transaction as a particular logical type identified by the particular category from among a plurality of logical types for the transaction.

Abstract: Techniques for content augmentation and assist are provided. A textual conversation between a first user and a plurality of recipients is analyzed to determine a first intent of the first user. A set of relationships is determined between the first user and the plurality of recipients, and a set of historical intents corresponding to each of the plurality of recipients is evaluated to identify similar intents to the first intent. A plurality of predefined messages is identified based on one or more similar intents that overlap between two or more of the plurality of recipients. A first predefined message is selected, from the plurality of predefined messages, based on the first intent and the determined set of relationships, and suggested content is provided based on the first predefined message.