International Business Machines Corporation

Wipro Limited

Abhishek Shivkumar

Krishna Kummamuru

Amit P Bohra

Anand B Bhagwat

Swapnasarit Sahu

Donna Karen Byron

Dilip Krishnaswamy

Timothy P Winkler

Alexander Pikovsky

Akbar Abdulmalik Ladak

Harish Vijendran

A method for generating an appendix from document content is provided. Included is analyzing a structure of a document to identify at least one logical element in a content of a page of the document; identifying at least one relation within the identified at least one logical element to determine an appendix topic; determining a degree of relevance of the at least one relation identifying the appendix topic; extracting an appendix content from at least one source document, based on determining a relevance of the source document to the appendix topic; and formatting the appendix based on the extracted appendix content.

Analyzing document content and generating an appendix

A mechanism is provided in a data processing system for determining comprehensiveness of a question paper given a syllabus of topics. An answer and evidence generator of a question answering system executing on the data processing system finds one or more answers based on the syllabus of topics for each question in the question paper. The answer and evidence generator identifies evidence for the one or more answers in the syllabus for each question in the question paper. A concept identifier of the question answering system identifies a set of concepts in the syllabus corresponding to the evidence for each question in the question paper to form a plurality of sets of concepts. The mechanism determines a value for a comprehensiveness metric for the question paper with respect to the syllabus of topics based on the plurality of sets of concepts.

Determining comprehensiveness of question paper given syllabus

Methods, systems, and computer program products for context-aware cognitive processing are provided herein. A method includes creating a progressively increasing map of a knowledge state as a function of time based on one or more topics covered during a user session by utilizing one or more processing techniques to process at least one of (i) text input, (ii) audio input and (iii) video input derived from content of the user session; analyzing a knowledge base to determine a response to a user query submitted during the user session; and customizing the response to the user based on (i) the map of the knowledge state and (ii) a collection of one or more items of context information pertaining to the user.

Context-aware cognitive processing

Automatically augmenting online content with contextually relevant comments. Online content and associated comments are received. The comments are classified as chit-chat or informative. For each informative comment, a portion of the online content to which the comment is most relevant is determined, and the comment is associated with a position in the online content that corresponds to the determined portion of the online content. A subset of the informative comments is selected for presentation.

Annotating content with contextually relevant comments

A computing device receives one or more questions. The computing device determines at least one of an urgency factor, an importance factor, and a difficulty level associated with the received one or more questions and determines at least one of an availability factor, a skill factor, and a quality level associated with the received one or more questions. The computing device determines an incentive based on the determined at least one of an urgency factor, an importance factor, and a difficulty level associated with the received one or more questions, and the determined at least one of an availability factor, a skill factor, and a quality level associated with the received one or more questions.

Determining incentive for crowd sourced question

Mechanisms are provided for performing tabular data correction in a document. The mechanisms receive a natural language document comprising a portion of content and analyze the portion of content within the natural language document to identify an erroneous sub-portion comprising an erroneous or missing item of information. The mechanisms generate a semantic signature for the erroneous sub-portion and generate a query based on the semantic signature. The mechanisms apply the query to a knowledge base to identify a candidate sub-portion of content. The mechanisms correct the erroneous sub-portion using the identified candidate sub-portion of content to generate a corrected natural language document.

Error correction in tables using a question and answer system

A method, system and computer-usable medium are disclosed for identifying question-answer pair associations within a dialog. Natural language processing (NLP) is used to process a target dialog to identify questions and answers within the dialog. The relative positions of the identified questions and answers in the dialog are determined and then correlated to one another to generate question-answer pair associations. Sub-questions and their associated main questions are identified within the dialog, followed by the elimination of redundant question-answer pairs. Local cues contained in the dialog are then used in scoring and filtering processes to differentiate fact-based questions and answers from those that are opinionated.

Automatic generation of question-answer pairs from conversational text

A method, non-transitory computer readable medium, and data manager computing device comprises obtaining a plurality of entity profiles from one or more sources. The obtained plurality of entities are transformed to one or more standard formats. Further, the related and unrelated entity profiles are determined based on a comparison of the transformed entity profiles against each other and the determined related and unrelated entity profiles are provided.

Growing community of inventors

Bengaluru, India

Abhishek Shivkumar