International Business Machines Corporation

International Business Machines Corporatton

Martin J Hirzel

Avraham Ever Shinnar

Jerome Simeon

Bugra Gedik

Mandana Vaziri

Kun-Lung Wu

Louis Mandel

Henrique Andrade

Julian Timothy Dolby

Robert J Soule

Rodric Rabbah

Andrew Lawrence Frenkiel

Scott A Schneider

Philippe Suter

Kiran A Kate

David Kevin Siegwart

Matthew R Arnold

Vibhore Kumar

Nicolas Changhai Ke

Christopher Hyland

Kavitha Srinivas

Todd W Mummert

Charles Francis Wiecha

Vijay Anand Saraswat

Alan Braz

Jason Tsay

Olivier L J Tardieu

Qiong Zou

Giuliano Losa

Olivier Tardieu

Lionel A Villard

Hua Wang

Wei Zhang

Anton Viktorovich Riabov

Peter Hans Westerink

Evelyn Duesterwald

Norman Bobroff

Peri L Tarr

Harold Leon Ossher

Judah M Diament

David Paul Grove

Huayong Wang

Chengliang Zhang

David John Piorkowski

Robert Grimm

Guillaume A Baudart

Jim Challenger

A computer-implemented method according to one embodiment includes identifying a machine learning pipeline and a plurality of training data batches; creating a plurality of tasks, based on the machine learning pipeline; and determining an order in which the plurality of tasks is executed, utilizing a resource usage-aware approach.

Performing batched training for machine-learning pipelines

In an approach to improve detecting and correcting errors in one or more machine learning pipelines. Embodiments comprise generating a plurality of test machine learning pipeline instances based upon a target machine learning pipeline and evaluating the plurality of test machine learning pipeline instances for failure in a task. Further, embodiments identify one or more root causes of error based upon the evaluated plurality of test machine learning pipeline instances and failure in the task, and create a remediated target machine learning pipeline based upon the identified one or more root causes of error. Additionally, embodiments output the remediated machine learning pipelines.

Repairing machine learning pipelines

Embodiments of the present invention provide a computer system a computer program product, and a method that comprises analyzing identified data for a determined conversion of the identified data, wherein the identified data is input data stored on an external database; automatically converting the analyzed data to a uniform domain by mapping a data route within the analyzed data, predicting a plurality of outcomes based on an application of a plurality of scenarios associated with the mapped data route, ranking the predicted outcomes based on a positive match percentage for the analyzed data, and converting the analyzed data associated with at least one ranked outcome using a relational algebra algorithm; and dynamically transmitting the converted, analyzed data into at least one section of a machine learning data pipeline.

Automatic conversion of data within data pipeline

Embodiments are disclosed for a method. The method includes identifying a prefix updated by a searcher of a machine learning model. The machine learning model is configured to generate source code in a programming language. The method also includes determining whether the prefix violates a semantic correctness property of the programming language. Additionally, the method includes instructing the searcher, in response to the determination, to prune the prefix from a set of prefixes under consideration by the searcher.

Reducing semantic errors in code generated by machine learning models

A machine-learning model task deduction method, system, and computer program product include extracting data schema of a machine-learning model and analyzing the data schema to determine an intended task of the machine-learning model.

Schema-based machine-learning model task deduction

An entity grammar that specifies a computer conversational agent may be received. User utterances are interpreted based on the entity grammar and prompts for the conversational agent to pose are determined based on the entity grammar. An outcome of the dialog is built by storing words in the user utterances and the prompts that match tokens in the entity grammar. The entity grammar specifies both a dialog flow and data structure of the outcome.

Conversational computer agent and outcome

Techniques facilitating guiding machine learning models and related components are provided. In one example, a computer-implemented method comprises identifying, by a device operatively coupled to a processor, a set of models, wherein the set of models includes respective model components; determining, by the device, one or more model relations among the respective model components, wherein the one or more model relations respectively comprise a vector of component relations between respective pairwise ones of the model components; and suggesting, by the device, a subset of the set of models based on a mapping of the component relations.

Guiding machine learning models and related components

A method and system are provided. The method includes separating a predicate that specifies a set of events into a temporal part and a non-temporal part. The method further includes comparing the temporal part of the predicate against a predicate of a known window type. The method also includes determining whether the temporal part of the predicate matches the predicate of the known window type. The method additionally includes replacing (i) the non-temporal part of the predicate by a filter, and (ii) the temporal part of the predicate by an instance of the known window type, responsive to the temporal part of the temporal predicate matching the predicate of the known window type. The instance is parameterized with substitutions used to match the temporal part of the predicate to the predicate of the known window type.

Discovering windows in temporal predicates

A computer-implemented conversational agent engages in a natural language conversation with a user, interpreting the natural language conversation by parsing and tokenizing utterances in the natural language conversation. Based on interpreting, a set of utterances in the natural language conversation to be recorded as a macro is determined. The macro is stored in a database with an associated macro identifier. Replaying of the macro executes a function specified in the set of utterances.

Personalization of conversational agents through macro recording

A computer natural language conversational agent authors an event-processing rule by carrying out a dialog in natural language with a user. A data model that customizes a dialog and building of the event-processing rule is received. A partial tree data structure is constructed based on a rule's grammar, and specialized based on tokens extracted from the data model. An utterance is received from a user and interpreted according to the grammar as specialized to the data model. Based on the interpreting of the utterance, the grammar, the data model, and context of interactions with the user, a natural language prompt is determined for the computer natural language conversational agent to output to the user. The partial tree data structure is filled based on the natural language prompt and the utterance from the user. The event-processing rule is generated based on the partial tree data structure filled during the dialog.

Conversational authoring of event processing applications

Database compiler with environment support may be provided. Database operators in a database compiler may be extended to include environment as an input parameter in addition to input data for native environment support. Environment operators may be added to the database compiler, which perform one or more of accessing and modifying the environment. Environment operators may include a return-environment operator, a map-with-environment operator and a compose-with-environment operator.

Database algebra and compiler with environments

Methods and systems are provided for configurable and non-invasive protection of private information in a user input to a software application that handles real-time information. A method includes detecting, by a filter in real-time, private information in the user input. The method further includes forming, by the filter, a filtered user input from the user input, by maintaining non-private information from the user input in the filtered user input, extracting and encrypting the private information in the user input and attaching the encrypted private information to the filtered user input, and replacing the private information in the user input with unique identifiers in the filtered user input. The unique identifiers are configured to be exploitable by the software application to achieve an intended function of the software application for the user. The method also includes transmitting, by a communications redirector, the filtered user input over a communication channel.

Configurable and non-invasive protection of private information for conversational agents

Systems and methods to generate a cognitive model are described. A particular example of a system includes a memory including program code having an application programming interface and a user interface, and a processor configured to access the memory and to execute the program code to generate a cognitive model, to run analysis on the cognitive model to determine a factor that is impacting a performance of the cognitive model, to determine an action based on the factor, to report at least one of the factor and the action to a user, and to use the action to generate a second cognitive model.

Conversational optimization of cognitive models

Specifying a conversational computer agent and its outcome with a grammar

Growing community of inventors

White Plains, NY, United States of America

Martin J Hirzel