International Business Machines Corporation

Yasaman Khazaeni

Yara Rizk

Mayank Agarwal

Sohini Upadhyay

Marco Patricio Crasso

Tathagata Chakraborti

Mikhail Yurochkin

Zhongshen Zeng

Werner Geyer

Vatche Isahagian

Matthew Scott Davis

Scott Boag

Vinod Muthusamy

Pablo Pedemonte

Christian Muise

Djallel Bouneffouf

Shubham Agarwal

Trong Nghia Hoang

Falk Pollok

Soumya Ghosh

Praveen C Ravichandran

Kristjan Herbert Greenewald

Sarath Sreedharan

Calvin Phung

A novel formulation called the Context-Attentive Bandit with Observations (CABO) is described, where only a limited number of features can be accessed by the learner. The present invention is applicable to many problems including problems arising in clinical settings and dialog systems where it is not possible to reveal the whole feature set. The present invention adapts the standard contextual bandit algorithm known as Thompson Sampling with a novel algorithm, we call Context-Attentive Thompson Sampling with Observations (CATSO). Experimental results are included to demonstrate its effectiveness including a regret analysis and an empirical evaluation demonstrating advantages of the disclosed novel approach on several real-life datasets.

Feedback driven decision support in partially observable settings

Embodiments of the invention are directed to a programmable computer system that includes a processor system operable to perform processor system operations. The processor system operations include using a workflow composer to perform an automated workflow composition process that generates a composed workflow that is operable to, when executed by a host device, satisfy a target logical goal. Performing the automated workflow composition process includes using a workflow-metric model to control the automated workflow composition process such that the composed workflow is operable to, when executed by the host device, satisfy the target logical goal in a manner that optimizes a target metric goal. The target metric goal quantifies a performance feature of the composed workflow.

Automated workflow composer using unmodeled metric-based goals

Computer-implemented methods, computer program products, and computer systems for improving intent determination in a messaging dialog manager system. The computer-implemented method for improving intent determination in a messaging dialog manager system may include one or more processors configured for receiving first agent entry data corresponding to a first agent communicating in a messaging dialog interface, determining that the first agent entry data expects a response that is within a first response domain, determining that a first user entry entered in the messaging dialog interface is not within the first response domain. Further, the computer-implemented may include identifying a second agent configured with a second response domain that includes the first user entry and transmitting the first user entry to the second agent to facilitate a seamless transition of an established communicational flow between the first agent and a first user.

Intent determination in a messaging dialog manager system

In federated learning problems, data is scattered across different servers and exchanging or pooling it is often impractical or prohibited. A Bayesian nonparametric framework is presented for federated learning with neural networks. Each data server is assumed to provide local neural network weights, which are modeled through our framework. An inference approach is presented that allows us to synthesize a more expressive global network without additional supervision, data pooling and with as few as a single communication round. The efficacy of the present invention on federated learning problems simulated from two popular image classification datasets is shown.

Bayesian nonparametric learning of neural networks

A conversational interface generation method, system, and computer program product that includes determining a conversational artifact for a computer program from a specification of the computer program and generating a conversational interface for the computer program based on the conversational artifact for the computer program included in the specification.

Auto generation of conversational artifacts from specifications

The present disclosure describes systems and methods for a command line interface with artificial intelligence integration. Embodiments of the disclosure provide a command line orchestration component (e.g., including a reinforcement learning model) that provides a generic command line interface environment (e.g., that researchers can interface using a simple sense-act application programming interface (API)). For instance, a command line orchestration component receives commands (e.g., text input) from a user via a command line interface, and the command line orchestration component can identify command line plugins and candidate response from the command line plugins. Further, the command line orchestration component may select a response from the candidate responses based on user preferences, user characteristics, etc., thus providing a generic command line interface environment for various users (e.g., including artificial intelligence developers and researchers).

System and method for the orchestration of plugins on the command line

Using a natural language analysis, it is determined that a compendium requires a natural language response to a natural language query, the compendium comprising a set of stored natural language responses to natural language queries. A relevance of a portion of narrative text to the natural language query is scored according to a query relevance measure, the portion extracted from a corpus of narrative text. The compendium is enhanced according to the query relevance score with information in the portion.

Improving the accuracy of a compendium of natural language responses

A feature vector characterizing a system to be analyzed via online partially rewarded machine learning is obtained. Based on the feature vector, a decision is made, via the machine learning, using an online policy. The system is observed for environmental feedback. In at least a first instance, wherein the observing indicates that the environmental feedback is available, the environmental feedback is obtained. In at least a second instance, wherein the observing indicates that the environmental feedback is missing, the environmental feedback is imputed via an online imputation method. the online policy is updated based on results of the obtained environmental feedback and the online imputation method. A decision is output based on the updated online policy.

Online partially rewarded learning

In one or more embodiments described herein, device, computer-implemented methods, and/or computer program products that facilitate enhancing test coverage of dialogue models. According to an embodiment, a system can comprise a processor that executes computer executable components stored in memory. The computer executable components can comprise a conversation processing component that receives and processes a first conversation. The computer executable components can further comprise a node marking component that tags a first node of a node map as an accessed node if the first node was accessed during processing of the first conversation. The computer executable components can further comprise a reporting component that generates a report comprising a list of nodes, wherein the list of nodes comprises one or more second nodes that were not accessed during processing of the first conversation.

Growing community of inventors

Needham, MA, United States of America

Yasaman Khazaeni