International Business Machines Corporation

Richard L Darden

Charles Evan Beller

Edward Graham Katz

Paul J Chase, Jr

Michael Drzewucki

Christopher Phipps

Aaron K Baughman

James E Ramirez

Aditya Anand Kalyanpur

James J Fan

Linda M Boyer

William G Dubyak

Christopher Frank Codella

Arnold Greenland

A method, computer system, and a computer program product for converting a plurality of factoid answers into a plurality of structured relations for storage in a structured knowledge base is provided. The present invention may include receiving a query from a user. The present invention may also include generating a plurality of possible factoid answers. The present invention may then include determining a plurality of confidence scores for the plurality of possible factoid answers. The present invention may then include generating a plurality of certain factoid answers from the plurality of possible factoid answers. The present invention may then include identifying a plurality of special target items. The present invention may further include generating a plurality of structured relations for each certain factoid answer and the identified plurality of special target items. The present include may also include storing the generated plurality of structured relations into the structured knowledge base.

Post-processor for factoid answer conversions into structured relations in a knowledge base

An apparatus comprising a memory and a processor configured for semi-autonomous natural language processing domain adaptation related activities. The processor coupled to the memory and configured to identify a corpus of documents of an evaluation domain and generate a first lexicon based on the corpus of documents of the evaluation domain, and determine a threshold that indicates a sufficiency of domain adaptation of the evaluation domain based at least in part on the first lexicon. The processor is further configured to identify a corpus of documents of a client domain, generate a second lexicon based on the corpus of documents of the client domain, determine a metric associated with the corpus of documents of the client domain and the second lexicon, and determine that domain adaptation of the client domain is complete when the metric exceeds the threshold.

Process for identifying completion of domain adaptation dictionary activities

Embodiments are directed to a watched questions threshold filtering system that functions to determine and deliver to a user relevant and significant data changes with respect to a user's goals, as defined by a notification threshold value provided by the user. The user is provided with an option to flag one or more queries for automatic re-querying. Confidence scores are processed on new data (i.e., data ingested after the original question was asked) by utilizing a confidence threshold for indicating if the new data warrants alerting a user.

Dynamic threshold filtering for watched questions

Mechanisms are provided for evaluating a temporal relevance of a candidate answer to an input natural language question. An input natural language question is received and analyzed to identify a temporal focus of the input natural language question. A corpus of documents is processed based on the input natural language question to generate candidate answers to the input natural language question, where each candidate answer is processed to identify at least one contextual temporal focus associated with the candidate answer. The at least one contextual temporal focus is compared with the temporal focus of the input natural language question and a measure of temporal relevance of the candidate answer based on results of the comparison is generated. A final answer to the input natural language question is output based on the measure of temporal relevance.

Evaluating temporal relevance in question answering

Large lists of domain-specific terms are classified as a particular kind of linguistic object, e.g., lexical answer type T versus canonical answer E, based on features from a domain-specific corpus which have been found to distinguish between the linguistic objects. The distinguishing features can be identified in the corpus based on sets of the linguistic objects derived from question-and-answer pairs. A classifier can be trained using the distinguishing features, and the classification carried out using that classifier. The distinguishing features can include one or more syntactic features or one or more lexical features. The linguistic objects (the T and E training sets) can be extracted from the question-and-answer pairs automatically via text analysis if manually curated lists are not available. The classified terms can be included in a domain-specific lexicon which facilitates a deep question answering system to yield an answer to a question.

Domain-specific method for distinguishing type-denoting domain terms from entity-denoting domain terms

A workload associated with a task is assessed with respect to each of a plurality of computing paradigms offered by a cloud computing environment. Adaptive learning is employed by maintaining a table of Q-values corresponding to the computing paradigms and the workload is distributed according to a ratio of Q-values. The Q-values may be adjusted responsive to a performance metric and/or a value, reward, and/or decay function. The workload is then assigned to available computing paradigms to be performed with improved utilization of resources.

Workload adaptive cloud computing resource allocation

An approach that provides hierarchical and index based watermarks represented as trees is described. In one embodiment, a watermark tree is formed from feature watermarks generated from a natural language processing (NLP) stack having NLP analytics. The watermark tree represents a hierarchical relationship between each of the feature watermarks. In particular, the watermark tree defines hierarchical pointers that point out inherited watermarks that exist between the feature watermarks according to the hierarchical relationship. Further, the watermark tree includes a time stamp specifying a time that a data set content residing in a corpus was accessed.

Growing community of inventors

Leesburg, VA, United States of America

Richard L Darden