International Business Machines Corporation

Avraham Ever Shinnar

Martin J Hirzel

Jerome Simeon

Louis Mandel

Mandana Vaziri

Kiran A Kate

Julian Timothy Dolby

Vijay Anand Saraswat

Kavitha Srinivas

Matthew R Arnold

Charles Francis Wiecha

Lionel A Villard

Marco Pistoia

Evelyn Duesterwald

Todd W Mummert

Alan Braz

Benjamin W Herta

Jason Tsay

Guillaume A Baudart

Anindya Banerjee

David Cunningham

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

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

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

Specifying a conversational computer agent and its outcome with a grammar

Automatic generation of a chat bot from an API specification to carry out a dialogue with a user and invoke an API call described in the API specification. Based on input API specification, a conversational bot specification representing a dialog flow is constructed. A natural language expression is received and transformed into instructions based on the conversational bot specification. Based on the instructions, a natural language prompt to the user and executable computer code for invoking the API call may be generated.

Generating chat bots from web API specifications

A method and a system for interpreting conversational authoring of information models. The system includes an understanding module, a managing module, and a generating module. The understanding module is configured to understand a natural language input to interpret an output. The managing module is configured to construct an information model based on the output of the understanding module. The generating module configured is to prompt, as a response to the natural language inputs, wherein the natural language inputs determine concepts and relationships of the concepts. The method includes receiving an interactive dialog between a conversational agent and an information model designer in natural language to produce an information model. The method can further include validating the information model using an information model management system. The method can include interpreting the information model with the use of an application.

Growing community of inventors

Hawthorne, NY, United States of America

Avraham Ever Shinnar