Search Results for author:
Found 18 papers, 7 papers with code
GrounDial: Human-norm Grounded Safe Dialog Response Generation
Current conversational AI systems based on large language models (LLMs) are known to generate unsafe responses, agreeing to offensive user input or including toxic content.
Data Augmentation for Improving Tail-traffic Robustness in Skill-routing for Dialogue Systems
Large-scale conversational systems typically rely on a skill-routing component to route a user request to an appropriate skill and interpretation to serve the request.
Scalable and Safe Remediation of Defective Actions in Self-Learning Conversational Systems
Off-Policy reinforcement learning has been a driving force for the state-of-the-art conversational AIs leading to more natural humanagent interactions and improving the user satisfaction for goal-oriented agents.
Constrained Policy Optimization for Controlled Self-Learning in Conversational AI Systems
Based on the experimental results, we demonstrate that the proposed approach is capable of achieving the best balance between the policy value and constraint satisfaction rate.
Scalable and Robust Self-Learning for Skill Routing in Large-Scale Conversational AI Systems
Skill routing is an important component in large-scale conversational systems.
Domain-Aware Contrastive Knowledge Transfer for Multi-domain Imbalanced Data
In many real-world machine learning applications, samples belong to a set of domains e. g., for product reviews each review belongs to a product category.
Real-Time Decentralized knowledge Transfer at the Edge
Transferring knowledge in a selective decentralized approach enables models to retain their local insights, allowing for local flavors of a machine learning model.
Self-Supervised Contrastive Learning for Efficient User Satisfaction Prediction in Conversational Agents
Moreover, a powerful satisfaction model can be used as an objective function that a conversational agent continuously optimizes for.
Group-Connected Multilayer Perceptron Networks
GMLP is based on the idea of learning expressive feature combinations (groups) and exploiting them to reduce the network complexity by defining local group-wise operations.
Cost-Sensitive Feature-Value Acquisition Using Feature Relevance
The chosen features should increase the prediction accuracy for a low cost, but determining which features will do that is challenging.
Unsupervised Representation for EHR Signals and Codes as Patient Status Vector
In this work, we present a two-step unsupervised representation learning scheme to summarize the multi-modal clinical time series consisting of signals and medical codes into a patient status vector.
Target-Focused Feature Selection Using a Bayesian Approach
In many real-world scenarios where data is high dimensional, test time acquisition of features is a non-trivial task due to costs associated with feature acquisition and evaluating feature value.
TAPER: Time-Aware Patient EHR Representation
The data contained in these records are irregular and contain multiple modalities such as notes, and medical codes.
Generative Imputation and Stochastic Prediction
In order to make imputations, we train a simple and effective generator network to generate imputations that a discriminator network is tasked to distinguish.
Cost-Sensitive Diagnosis and Learning Leveraging Public Health Data
Furthermore, based on the suggested dataset, we provide a comparison of recent and state-of-the-art approaches to cost-sensitive feature acquisition and learning.
Opportunistic Learning: Budgeted Cost-Sensitive Learning from Data Streams
The suggested method acquires features incrementally based on a context-aware feature-value function.
Dynamic Feature Acquisition Using Denoising Autoencoders
In real-world scenarios, different features have different acquisition costs at test-time which necessitates cost-aware methods to optimize the cost and performance trade-off.
ECG Heartbeat Classification: A Deep Transferable Representation
Electrocardiogram (ECG) can be reliably used as a measure to monitor the functionality of the cardiovascular system.
