International Business Machines Corporation

William G Visotski

David E Wilson

Christopher Munjal Nolan

Robert Leslie Yates

Kay Mueller

Stephen Arthur Boxwell

An approach is provided in which a knowledge manager generates term tokens from terms included in an original text stream, and generates annotation tokens with corresponding term location information. In turn, the knowledge manager generates a knowledge structure that indexes the term tokens into original text fields and indexes the annotation tokens into parallel fields that align to the original text fields based upon the term location information.

Framework for annotated-text search using indexed parallel fields

An approach is provided in which a knowledge manager generates syntactic annotation tokens that correspond to syntactic relationships between terms included in a source document. The knowledge manager creates a knowledge structure that stores the syntactic annotation tokens in parallel fields and stores the source document terms in original text fields, which align to the parallel fields. In turn, the knowledge manager utilizes the knowledge structure to generate answers to questions based upon the syntactic annotation tokens.

Augmented text search with syntactic information

Mechanisms are provided for performing context based synonym filtering for natural language processing. Content is parsed into one or more conceptual units, wherein each conceptual unit comprises a portion of text of the content that is associated with a single concept. For each conceptual unit, a term in the conceptual unit is identified that has a synonym to be utilized during natural language processing of the content. A first measure of relatedness of the term to at least one other term in the conceptual unit is determined. A second measure of relatedness of the synonym of the term to the at least one other term in the conceptual unit is determined. A determination whether or not to utilize the synonym when performing natural language processing on the conceptual unit is made based on the first and second measures of relatedness and natural language processing on the content is performed accordingly.

Context based synonym filtering for natural language processing systems

According to an aspect, a question answering computer system determines a set of search terms for a given question. A plurality of passages that each includes at least one search term in the set of search terms is identified in response to a search of a document for search terms in the set of search terms. A passage from the plurality of passages is selected. A context based score of the selected passage that indicates the likelihood that the selected passage contains an answer to the question is generated based on criteria that specify a relationship among the set of search terms, content of the passage, and content of at least one other passage in the plurality of passages.

Context based passage retreival and scoring in a question answering system

A mechanism is provided for retrieving candidate answers from a corpus of documents. The mechanism receives an input question for which an answer is sought. The mechanism extracts features of the input question based on a natural language processing. The mechanism executes a first search of the corpus of documents based on a first subset of the extracted features of the input question and an initial evaluation of a utility of the first subset of extracted features to generate a subset of documents. The mechanism executes a second search of a set of passages extracted from the subset of documents based on a second subset of the extracted features of the input question and a reevaluation of the utility of the second subset of extracted features thereby forming a subset of passages. The mechanism generates query results from the subset of passages matching from which candidate answers are identified.

Retrieving text from a corpus of documents in an information handling system

Context based passage retrieval and scoring in a question answering system

Mechanisms are provided for identifying commonalities between candidate answers generated by a Question and Answer (QA) system in response to an input question. The mechanisms receive a plurality of candidate answers for an input question from the QA system and identify terms present in the candidate answers. The mechanisms determine relationships between terms in each of the candidate answers and determine a common relationship between a first term and a second term, the common relationship being common amongst at least a subset of the plurality of candidate answers, based on the determined relationships between terms in each of the candidate answers. The mechanisms present the plurality of candidate answers and the common relationship to a user.

Growing community of inventors

Merrimack, NH, United States of America

William G Visotski