International Business Machines Corporation

Timothy P Winkler

Donna Karen Byron

Alexander Pikovsky

John P Bufe, Iii

Florian Pinel

Carmine M DiMascio

Krishna Kummamuru

David George Radley

James W Murdock, Iv

Mary Swift

Suzanne L Estrada

Corville O Allen

Brian Robert Muras

Itzhack Goldberg

Lakshminarayanan Krishnamurthy

Scott N Gerard

Boaz Mizrachi

Anthony Tom Levas

Benjamin P Segal

Shantan Kethireddy

John Martin Prager

Benjamin L Johnson

Patrick A Wagstrom

Henry E Calzaretta

Jessica W Ramirez

Howard R Davidson

Fonda J Daniels

Ana Claudia Biazetti

Abhishek Shivkumar

Anand B Bhagwat

In an approach to personalizing a news feed, a computing device monitors a user accessing content. The computing device determines a personal knowledge graph for the user based on the accessed content. Responsive to receiving a new piece of content that the user has not accessed, the computing device determines a novelty score for the new piece of content based on the personal knowledge graph. The computing device filters the new piece of content based on the novelty score.

Method for personalized breaking news feed

A method, computer program product, and computer system for analyzing one or more existing book indexes to build a statistical model of term-to-text pairs. A document may be analyzed, wherein the document may include at least a portion of an instruction in a book. A term in the document may be identified. Whether the term is a candidate for an index of the book may be identified based upon, at least in part, the statistical model of term-to-text pairs.

System and method for identifying candidates for back-of-book index

One or more processors receive one or more variations to one or more first instruction elements in a first instruction set that indicate one or more second instruction elements of a second instruction set. One or more processors determine whether the one or more first instruction elements exceed a threshold of variability. One or more processors determine whether the one or more first instruction elements and the one or more second instruction elements are substantially equivalent. One or more processors determine whether a first outcome of the first instruction set is substantially similar to a second outcome of the second instruction set.

Instruction element variability

Aspects include real-time context based recipe recommendations including receiving, at a mobile device, an identifier of an available food item that is offered for purchase at a food marketplace. A request for recipes that specifies the identifier of the available food item and a list of identifiers of food items previously selected by the shopper for purchase is sent to a recipe application. At least one recipe selected by the recipe application is received at the mobile device and presented to the shopper. The recipe includes the available food item and at least a subset of the food times previously selected by the shopper. The identifier of the available food item is added to the list of food items previously selected by the shopper for purchase based on determining that the shopper has selected the available food item for purchase.

Real-time context based recipe recommendation system

An approach is provided for automatically generating user-specific interaction modes for processing question and answers at the information handling system by receiving a question from a user, extracting user context parameters identifying a usage scenario for the user, identifying first input and output presentation modes for the user based on the extracted user context parameters, monitoring user interaction with the system in relation to the question, and adjusting the first input and output presentation modes based on the extracted user context parameters and detected user interaction with the system.

Establishing user specified interaction modes in a question answering dialogue

Aspects include learning object/action pairs for recipe ingredients. A method includes extracting an ingredient list that includes a plurality of entries from a recipe stored in an electronic format. Each of the plurality of entries includes one or more words. For each multi-word entry in the ingredient list, an ingredient associated with the entry is identified by comparing words contained in the entry to terms in a lexicon of cooking domain terms. It is determined whether an action corresponds to the identified ingredient. The determining includes parsing the entry to locate a verb that is associated with the identified ingredient. Based on determining that an action corresponds to the identified ingredient, a food item action pair that includes the identified ingredient and the located verb is output.

Learning object/action pairs for recipe ingredients

A mechanism is provided in a data processing system for rating difficulty of a question. The mechanism receives an input question and generates one or more candidate answers from a corpus of knowledge using a pipeline of software engines. The pipeline of software engines generates a plurality of features extracted from the question, the one or more candidate answers, or the corpus of knowledge. The mechanism then generates a question difficulty score based on the plurality of features using a machine learning model. The machine learning model maps features to assigned weights for scaling the difficulty score.

Rating difficulty of questions

Mechanisms for automatically generating a set of test questions for use in generating a test to be administered to human test takers are provided. The mechanisms ingest a document from a corpus of documents to select a potential test question answer from the document and generate a candidate test question based on the potential test question answer. The mechanisms evaluate the candidate test question using a Question and Answer (QA) system to generate a result indicative of whether the candidate test question should be maintained for test generation. The mechanisms store the candidate test question in the set of test questions in response to a result indicating that the candidate test question should be maintained for test generation.

Dynamic identification and validation of test questions from a corpus

An approach is provided for an information handling system to present knowledge-based information. In the approach, a semantic analysis is performed on the document with the analysis resulting in various sets of semantic content. Each of the sets of semantic content corresponds to an area in the document. The areas of the document are visually highlighted using visual indicators that show the availability of the sets of semantic content to a user via a user interface. In response to a user selection, such as a selection using the user interface or a user specified configuration setting, a selected set of semantic content is displayed to the user using the interface.

Active knowledge guidance based on deep document analysis

A mechanism is provided in a data processing system for using paraphrase metrics for answering questions. The mechanism receives an input question and generating a candidate answer from a corpus of information. The candidate answer has a supporting passage from the corpus of information. The mechanism divides the input question into a first sequence of tokens and divides the supporting passage into a second sequence of tokens. The mechanism identifies a plurality of subsequences of tokens within the second sequence of tokens and applies a paraphrase metric to compare the first sequence of tokens to each of the plurality of subsequences of tokens to generate a plurality of paraphrase metric scores. The mechanism then determines a confidence score for the candidate answer based on a highest paraphrase metric score within the plurality of paraphrase metric scores.

Using paraphrase metrics for answering questions

A mechanism is provided, in a question answering (QA) system, for performing persona-based question answering is provided. An identification of a requested persona is received from a user along with a natural language question input specifying an input question to be answered by the QA system. Responsive to receiving the requested persona, components of the QA system are customized to answer questions from a viewpoint of the requested persona. An answer to the input question is generated from the viewpoint of the requested persona based on the customization of the components of the QA system. The answer to the input question is output in a form representative of the requested persona.

Answering questions via a persona-based natural language processing (NLP) system

A mechanism is provided for modifying an existing recipe to meet a set of desired colors for a final food dish. Responsive to receiving a request to modify the existing recipe to meet the set of desired colors, at least one of the set of existing colors to be changed to meet the desired set of colors is identified. An ingredient-action-sequence triplet associated with each at least one existing color to be changed in the existing recipe is identified and, from a corpus of ingredient-action-sequence triplets associated with other existing recipes, one or more candidates that can be added to produce the at least one target color are identified. The one or more candidates that can be added are ranked based on how each candidate pairs best with other ingredients in the existing recipe. Based on a selection of a candidate, the existing recipe is modified with the selected candidate.

Predicting a chromatic identity of an existing recipe and modifying the existing recipe to meet a desired set of colors by adding new elements to the recipe

Growing community of inventors

Clinton, MA, United States of America

Timothy P Winkler