Self-Aware Feedback-Based Self-Learning in Large-Scale Conversational AI

04/29/2022
by   Pragaash Ponnusamy, et al.
1

Self-learning paradigms in large-scale conversational AI agents tend to leverage user feedback in bridging between what they say and what they mean. However, such learning, particularly in Markov-based query rewriting systems have far from addressed the impact of these models on future training where successive feedback is inevitably contingent on the rewrite itself, especially in a continually updating environment. In this paper, we explore the consequences of this inherent lack of self-awareness towards impairing the model performance, ultimately resulting in both Type I and II errors over time. To that end, we propose augmenting the Markov Graph construction with a superposition-based adjacency matrix. Here, our method leverages an induced stochasticity to reactively learn a locally-adaptive decision boundary based on the performance of the individual rewrites in a bi-variate beta setting. We also surface a data augmentation strategy that leverages template-based generation in abridging complex conversation hierarchies of dialogs so as to simplify the learning process. All in all, we demonstrate that our self-aware model improves the overall PR-AUC by 27.45 reduction of up to 31.22 preferences across a large number of customers.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/06/2019

Feedback-Based Self-Learning in Large-Scale Conversational AI Agents

Today, most large-scale conversational AI agents (e.g. Alexa, Siri, or G...
research
09/09/2023

Data Augmentation for Conversational AI

Advancements in conversational systems have revolutionized information a...
research
04/26/2021

Handling Long-Tail Queries with Slice-Aware Conversational Systems

We have been witnessing the usefulness of conversational AI systems such...
research
10/21/2020

Self-Supervised Contrastive Learning for Efficient User Satisfaction Prediction in Conversational Agents

Turn-level user satisfaction is one of the most important performance me...
research
08/29/2018

A Reinforcement Learning-driven Translation Model for Search-Oriented Conversational Systems

Search-oriented conversational systems rely on information needs express...
research
08/22/2023

Learning to generate and corr- uh I mean repair language in real-time

In conversation, speakers produce language incrementally, word by word, ...

Please sign up or login with your details

Forgot password? Click here to reset