International Business Machines Corporation

Microsoft Technology Licensing, LLC

John P Bufe, Iii

Timothy P Winkler

Donna Karen Byron

Alexander Pikovsky

Mary Swift

Jesse Daniel Eskes Rusak

Jayant Sivarama Krishnamurthy

Jacob Daniel Andreas

Patrick A Wagstrom

Julius Goth, Iii

Jared M D Smythe

Alan Xinyu Guo

Yuchen Zhang

Andrei Vorobev

Srinivasa Phani K Gadde

Eric Woods

Srikanth Govindaraj Tamilselvam

Alexander J Kolmykov-Zotov

William Graham O'Keeffe

Branimir Konstantinov Boguraev

David Leo Wright Hall

Daniel Louis Klein

Edward Eugene Seabolt

Anand B Bhagwat

Adam David Pauls

David Ernesto Heekin Burkett

Jason Andrew Wolfe

Abhirut Gupta

Matthew T Hatem

A computer-implemented method of responding to a conversational event is presented. The method comprises receiving a conversational event at a conversational computing interface. Based on the received conversational event, an applicable generation rule of a plurality of candidate generation rules is selected. The applicable generation rule is configured with one or more parameters. A computer-executable plan is then selected based on the selected generation rule. The one or more parameters are passed from the selected generation rule to one or more additional generation rules. The one or more additional generation rules configured with the one or more parameters are recursively applied to extend the selected computer-executable plan. One or more candidate responses to the conversational event are output via the conversational computing interface based on the recursive application of the one or more additional generation rules configured with the one or more parameters.

Response generation for conversational computing interface

A computer-implemented method of responding to a conversational event. The method comprises enacting, by a conversational computing interface, an initial computer-executable plan based on a conversational event received by the conversational computing interface, wherein the initial computer-executable plan is configured to output an initial value based on the conversational event. The method further comprises selecting, by the conversational computing interface, an extended computer-executable plan based on determining that the initial value is insufficient for generating an extended description responsive to the conversational event. The method further comprises enacting, by the conversational computing interface, the extended computer-executable plan to output additional information beyond what the initial computer-executable plan is configured to output, the additional information sufficient for generating the extended description responsive to the conversational event. The method further comprises outputting, via the conversational computing interface, a response to the conversational event including the extended description.

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 technique for instance-specific feature-based cross-document sentiment aggregation includes analyzing input data to determine an entity referenced in the input data. One or more salient features of the entity are identified. Multiple documents that reference the entity are located. The salient features in each of the multiple documents are identified. Respective sentiment values are assigned to each of the salient features identified in the multiple documents. Respective sub-graphs are created for each of the multiple documents. The sub-graphs specify the sentiment values assigned to each of the salient features identified in an associated one of the multiple documents. The assigned sentiment values for each of the salient features are aggregated based on the sub-graphs. Finally, output data that is associated with the input data is generated. The output data provides an indication of the aggregated sentiment value for each of the salient features.

Techniques for instance-specific feature-based cross-document sentiment aggregation

A method, comprising recognizing a user utterance for processing. The method further comprises using a previously-trained code-generation machine to generate, from the user utterance, a data-flow program configured to produce a return value upon successful execution. The method further comprises beginning execution of the data-flow program. Responsive to reaching an error condition resulting from execution of the data-flow program, the method further comprises, prior to the data-flow program producing the return value, suspending execution of the data flow program. The method further comprises using the previously-trained code-generation machine to generate an error-handling data-flow program, wherein the error-handling data-flow program is configured to produce the return value; beginning execution of the error-handling data-flow program to produce the return value; and outputting the return value.

Error recovery for conversational systems

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

Software that uses machine-logic based algorithms to assess the value of idea descriptions by performing the following operations: (i) receiving an idea description pertaining to an idea; (ii) generating a density score for the idea, wherein the density score is based, at least in part, on one or more publication date densities of a set of works related to the idea description; (iii) generating a novelty score for the idea, wherein the novelty score is based, at least in part, on a comparison of the idea description to the set of works related to the idea description using natural language processing; and (iv) assessing the value of the idea based, at least in part, on the generated density score and the generated novelty score.

Value scorer in an automated disclosure assessment system

A question answering system that determines whether a question is off-topic by performing the following steps: (i) receiving, by a question answering system, a set of documents; (ii) identifying topical subset(s) for each document of the set of documents using named entity recognition, where each topical subset relates to a corresponding topic; (iii) assigning a set of topic score(s) for each topical subset using natural language processing, where each topic score relates to a corresponding probability associated with the respective topical subset under a probabilistic language model; and (iv) determining, based, at least in part, on the topic score(s) corresponding to the topical subset(s), whether a question input into the question answering system is off-topic.

Determining off-topic questions in a question answering system using probabilistic language models

Mechanisms are provided in a question answering (QA) system comprising a QA system pipeline that analyzes an input question and generates an answer to the input question, for pre-processing the input question. The mechanisms receive an input question and input the input question to a pre-processor flow path having one or more pre-processors. The one or more pre-processors transform the input question into a transformed question by correcting errors in a formulation of the input question that are determined to be detrimental to efficient and accurate processing of the input question by a QA system pipeline of the QA system. The transformed question is then input to the QA system pipeline of the QA system which processes the transformed question to generate and output an answer to the input question.

Question correction and evaluation mechanism for a question answering system

A mechanism is provided, in a data processing system comprising a processor and a memory configured to implement a natural language processing (NLP) system, for identifying content relationship for content copied by a content identification mechanism. The content identification mechanism identifies content from a website and then identifies relationship content information associated with a current web page where the content is found. The content identification mechanism modifies a file structure associated with the content with the relationship content information. The content identification mechanism identifies one or more classification identifiers in order to classify the content. Finally, the content identification mechanism transmits the content and the file structure to a specific corpus based on the one or more classification identifiers.

Identifying content and content relationship information associated with the content for ingestion into a corpus

Mechanisms are provided to implement a cognitive system collaboration identification and recommendation system (CSCIRS). The CSCIRS stores, in a cognitive system database, entries corresponding to a plurality of cognitive system instances. Each entry identifies operational characteristics of a corresponding cognitive system instance. The CSCIRS receives, from a requestor, a request to identify a potential collaborative cognitive system instance and identifies, based on the request and the cognitive system database, a candidate collaborative cognitive system instance. The CSCIRS generates a collaboration recommendation based on the identification and outputs an output corresponding to the collaboration recommendation.

Cognitive system comparison and recommendation engine

A mechanism is provided, in a data processing system comprising a processor and a memory configured to implement a question and answer system (QA), for providing confidence rankings based on temporal semantics. Responsive to receiving an input question, a set of candidate answers is identified from a knowledge domain based on a correlation between an identified one or more predicates and an identified one or more arguments to the knowledge domain. A confidence score is associated with each of the candidate answers and each confidence score associated with each candidate answer is refined based on a set of temporal characteristics identified in the input question. A set of temporally refined candidate answers is then provided to the user.

Growing community of inventors

Washington, DC, United States of America

John P Bufe, Iii