International Business Machines Corporation

Intematlonal Business Machlnes Corporation

Andrew Ronald Freed

Corville O Allen

Joseph N Kozhaya

Shikhar Kwatra

Albert Alexander Chung

Roberto Delima

Roderick Charles Henderson

Dorian B Miller

Christina R Carlson

Joshua S Allen

Sorabh Murgai

Robert L Nielsen

Richard A Salmon

Michael W Schroeder

Pamela D Andrejko

Elizabeth T Dettman

Kyle G Christianson

Lisa M Bradley

Lisa M W Bradley

Joel C Dubbels

Dwi Sianto Mansjur

Aaron T Smith

Isa M Torres

Tristan A TeNyenhuis

Marco Noel

Hassan Nadim

Shubhadip Ray

Indervir Singh Banipal

Norbert Herman

Michael Terry Payne

Cynthia M Murch

Ryan Brink

Charles S Skinner

Donna Karen Byron

Keith D Cramer

Stephan Joseph Roorda

Jan M Nordland

Humberto R Rivero

John Edward Petri

Dana Lea Price

Scott N Gerard

Victor Povar

Brien H Muschett

Barton Wayne Emanuel

Karl J Cama

David Contreras

Lalit Agarwalla

Avik Sanyal

Jason M Brown

Shane M Kilmon

Vamshi Krishna Thotempudi

Krishna Mahajan

Rebecca Rose James

Thai T La

Beata J Strack

Kyungae Lim

Jasmeet Singh

Craig M Trim

Eric Woods

Timothy James Hahn

Curtiss James Howard

Kimberly Diane Kenna

Niraj P Joshi

Ahmed M Nassar

Christopher Phipps

Mario J Lorenzo

Jason Howard Cornpropst

Paul Richard Chmielewski

Sujatha B Perepa

Javier Torres

Jerry Leroy Von Berge

Rodrigo Goulart Silva

Daniel Thornton Pierce

Jack Patern Yapi

Shannen B Lambdin

Nicolas B Lopez

Anuj Sharma

Eman Omar

Nicholas Tsang

Jeffrey Bernard Nowicki

John M Cusick

Jeremy John Salsman

Courtney Branson

Robert Michael Hervey

Diane Chalmers

Leo Mazzoli

Daniel Zyska

Mohammad Gorji-Sefidmazgi

Martha Holloman

Aishwarya Hariharan

Saul B Margolis

Jon A Baez

Adrianus P Vrouwenvelder

Troy Biesterfeld

Christopher R Weber

Allegra Larche

Jocelyn Kong

A system, program product, and method for processing challenges to potential artificial intelligence (AI) biases. The method includes injecting one or more first values associated with one or more respective variables into an AI platform, and generating, through the AI platform, one or more first outcomes. The method also includes collecting feedback with respect to the one or more outcomes, and parsing the feedback through a natural language understanding (NLU) application. The method further includes determining, subject to the parsing, one or more bias factors embedded within the AI platform.

Query-driven challenge of AI bias

A method for speech recognition using cadence patterns is provided. The method includes identifying speech cadence in user speech, which includes a plurality of sounds and pauses. At least one speech cadence pattern is identified from the plurality of sounds and pauses. The user speech is transcribed, and the transcribed user speech is modified based on the identified speech cadence pattern.

Speech recognition using cadence patterns

Altering an automated conversation system by receiving automatic conversation log data, generating a decision tree from the data, summarizing child node data for a node of the decision tree, generating node response variations according to the child node data of the node, and altering the automatic conversation according to the node response variations.

Altering automated conversation systems

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

A generator categorizes documents in one or more transactions into buckets, each identified by a separate category for an expected time window based on a separate relative age of each of the documents evaluated from one or more dates identified in the documents. The generator trains a document classifier with a model of the separate relative age of each of the documents as a temporal characteristic correlated with the respective category of a respective bucket of the buckets. The document classifier executes on a input documents to classify each of the input documents as a particular logical type identified by a particular category from among multiple logical types.

Classifying digital documents in multi-document transactions based on embedded dates

A classifier receives a digital scan of a document and converts the content of the document in the digital scan from an image into text. The classifier analyzes the text to determine one or more predicted roles of one or more signatories, each predicted role determined based on one or more signature elements in the content of the document executed by the one or more signatories. The classifier evaluates each of the one or more predicted roles in view of a plurality of expected signatory role characteristics of a plurality of categories of documents of a transaction to select a particular category associated with the document from among the plurality of categories. The classifier classifies the document within the transaction as a particular logical type identified by the particular category from among a plurality of logical types for the transaction.

Classifying digital documents in multi-document transactions based on signatory role analysis

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

A method, system, and computer program product for recognizing, and training to recognize, alphanumeric speech data inputs. The method may include segmenting a data input into a sequential n-gram chunks based on a predetermined rule, where the data input is received through speech recognition. The method may also include receiving metadata regarding characteristics of the data input. The method may also include generating a language model based on the metadata. The method may also include generating a first set of language model variations of the data input. The method may also include training the language model based on at least the first set of language model variations. The method may also include generating one or more alternatives for the data input using the trained language model. The method may also include transmitting an output including the one or more alternatives for the data input.

Speech recognition and training for data inputs

Methods, computer program products, and systems are presented. The methods, computer program products, and systems can include, for instance: determining, in performance of an interactive voice response (IVR) session, prompting data for presenting to a user, and storing text based data defining the prompting data into a data repository; presenting the prompting data to the user; receiving return voice string data from the user in response to the prompting data; generating a plurality of candidate text strings associated to the return voice string of the user; examining the text based data defining the prompting data; augmenting the plurality of candidate text strings in dependence on a result of the examining to provide a plurality of augmented candidate text strings associated to the return voice string data; and evaluating respective ones of the plurality of augmented candidate text strings associated to the return voice string data; and selecting one of the augmented candidate text strings as a returned transcription associated to the return voice string data.

Contextualized speech to text conversion

A processor may receive data regarding a context for a first dialog turn. The processor may monitor a voice input from a user for the first dialog turn. The processor may detect a first pause in the voice input, the first pause having a duration that satisfies a time threshold. The processor may receive, based on the first pause, first voice input data. The processor may analyze the first voice input data. The processor may determine that additional time is recommended for the voice input to be provided by the user.

Dynamic voice input detection for conversation assistants

A system and method for providing a text to speech output by receiving user audio data, determining a user region-specific-pronunciation classification according to the audio data, determining text for a response to the user according to the audio data, identifying a portion from the text, where a region specific-pronunciation dictionary includes the portion, and using a phoneme string, from the dictionary selected according to the user region-specific pronunciation classification, for the word in a text to speech output to the user.

Using speech to text data in training text to speech models

An approach is provided that receives a document and a document type of the document. The document type identifies a document category to which the received document belongs. A set of linguistic metrics are retrieved that correspond to the document type. A quality of the received document is automatically determined based on a set of linguistic features found in the document as compared to the retrieved set of linguistic metrics. The document is then ingested into a corpus that is utilized by a question-answering (QA) system. The ingestion of the document is based on the determined quality.

Document type-specific quality model

A request is received from a user to search a document for at least one search term. The document is analyzed to determine contextual meanings associated with the at least one search term. An ordered set of contexts of the at least one search term is constructed. An option of disambiguation is then prompted to the user to select a context of the ordered set of contexts. Search results are presented to the user associated with the selected context of the at least one search term.

Context-based text searching

A dialog change service builds a directed graph of nodes, each described by code for a conversational agent stored in source control, the code comprising one or more dialog-based features. The dialog change service, responsive to receiving a request for a dialog change to a particular node of the conversational agent, evaluates the directed graph to identify an additional selection of nodes that require a similar changes as the dialog change based on textual and structural content. The dialog change service updates the code for the particular node and the additional selection of nodes to propagate the dialog change in the conversational agent stored in source control.

Efficiently managing predictive changes for a conversational agent

A service identifies a level of specificity of one or more identified entities in a user input comprising a query, within one of multiple levels of a hierarchy of a hierarchical coding system. Responsive to determining that additional levels of specificity beyond the identified level of specificity are recommended to return a minimum answer set to the query, the service returns one or more answers requesting one or more additional inputs refining the query based on one or more values identified in a next level. Responsive to determining that no additional levels of specificity beyond the identified level of specificity are recommended to return the minimum answer set to the query, the service returns an answer set comprising a selection of information for the current level of specificity from an ingested corpus of knowledge mapped to the hierarchical coding system.

Automatically refining application of a hierarchical coding system to optimize conversation system dialog-based responses to a user

Growing community of inventors

Cary, NC, United States of America

Andrew Ronald Freed