International Business Machines Corporation

Aaron T Smith

Andrew Ronald Freed

Ryan Brink

Joshua S Allen

Sorabh Murgai

Jason M Brown

Barton Wayne Emanuel

Jason Howard Cornpropst

Marco Noel

Vamshi Krishna Thotempudi

Rebecca Rose James

Vignesh Harish

Jasmeet Singh

Tibor Beres

Courtney Branson

Disclosed is a computer implemented method to identify relevant feedback. The method includes training, with a set of training data, a generative adversarial network (GAN), wherein the GAN includes a generator and a discriminator, and the set of training data is comprised of a plurality of feedback, each instance of feedback includes a value in a plurality of categories, the categories including a positivity value, and a validity value. The method also includes receiving, from a user, a new instance of feedback. The method further includes determining, by the discriminator, a first validity value and a first positivity value of the new instance of feedback. The method includes updating, in response to the first validity value being valid, and the first positivity value being negative, the GAN. The method further includes, displaying the new instance of feedback.

Feedback discriminator

A method retrains a cognitive interaction information system. One or more processors monitors an interactive communication between a user and the cognitive interactive information system. The processor(s) identifies an incorrect answer returned by the cognitive interactive information system to a question asked by the user; reevaluates the question utilizing alternative intent classifications to form alternative answers; and presents the alternative answers to the user. The processor(s) receive a selection from the alternative answers from the user; updates processing rules to generate updated processing rules that are based on the selection; and retrains the cognitive interaction information system based on the updated processing rules.

Retraining a conversation system based on negative feedback

In an approach for training data enhancement for an interactive response system, a processor retrieves a set of training data including a set of intents, a set of entities, and a set of utterances that map to each intent. A processor determines iteratively a root verb among the set of utterances for each intent. A processor to determine a set of new intents based on analysis of the determined root verb by performing a pairwise iteration and similarity score over the set of intents. A processor determines iteratively one or more new entities for each new intent. A processor generates a set of new training data based on the set of new intents and entities.

Training data enhancement

Embodiments for managing chatbots are provided. Chatbot interaction information is received. At least one chatbot interaction within the received chatbot interaction information is identified. The at least one identified chatbot interaction includes an initial utterance provided by a user, an unsuccessful response generated responsive to the initial utterance, a subsequent utterance provided by the user, and a successful response generated responsive to the subsequent utterance. The successful response is associated with a chatbot intent. A confidence score for associating the initial utterance with utilization of the chatbot intent by a chatbot is calculated.

Methods and systems for improving chatbot intent training by correlating user feedback provided subsequent to a failed response to an initial user intent

Monitoring and instigating shifts in visual focus by monitoring a first duration associated with a first focus point distance, determining that the first focus point distance satisfies a first distance threshold and that the first duration satisfies a first temporal threshold, instigating a change in the first focus point distance, yielding a second focus point distance, wherein the second focus point distance exceeds a second distance threshold, monitoring a second duration associated with the second focus point distance, determining that the second duration satisfies a second temporal threshold, and providing an output indicating satisfaction of the second distance threshold and second temporal threshold.

Monitoring and instigating shifts in visual focus

A set of documents is received for processing and extraction. A set of processing engines is received, and each processing engine has an expected benefit when processing a document with associated document metadata. The set of documents is analyzed to determine document metadata to be associated with the document. An expected benefit is determined for each of the documents of the set of document when the respective document is processed by a respective processing engine in the set processing engines. An expected cost for processing is determined for each of the documents in each of the set of processing engines. A processing plan for the set of documents is determined wherein the processing plan identifies a selection of documents to be run in respective processing engines of the set of processing engines based on a cost versus benefit analysis. The processing plan is executed extracting information from the identified selection of documents.

Intelligent use of extraction techniques

A method improves a functionality of a conversational agent that is generated by an artificial intelligence (AI) system. A conversational agent receives a first utterance from a first entity. The AI system identifies an unverified response to the first utterance; sends the unverified response to the first entity; and receives a positive feedback indication about the unverified response from the first entity. The AI system searches a data store in order to identify an entry for a second utterance by a second entity, where the second entity has sent a positive feedback for the unverified response. The AI system sends the second utterance and the unverified response to the first entity, and receives a positive feedback for the unverified response to the second utterance from the first entity in order to mark the unverified response as a verified response, which responds to future receipts of the first utterance.

Growing community of inventors

Raleigh, NC, United States of America

Aaron T Smith