Learning Improvised Chatbots from Adversarial Modifications of Natural Language Feedback

The ubiquitous nature of chatbots and their interaction with users generate an enormous amount of data. Can we improve chatbots using this data? A self-feeding chatbot improves itself by asking natural language feedback when a user is dissatisfied with its response and uses this feedback as an additional training sample. However, user feedback in most cases contains extraneous sequences hindering their usefulness as a training sample. In this work, we propose a generative adversarial model that converts noisy feedback into a plausible natural response in a conversation. The generator's goal is to convert the feedback into a response that answers the user's previous utterance and to fool the discriminator which distinguishes feedback from natural responses. We show that augmenting original training data with these modified feedback responses improves the original chatbot performance from 69.94 75.96 improvement given that the original model is already trained on 131k samples.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/23/2023

System-Level Natural Language Feedback

Natural language (NL) feedback contains rich information about the user ...
research
02/04/2022

Pre-Trained Neural Language Models for Automatic Mobile App User Feedback Answer Generation

Studies show that developers' answers to the mobile app users' feedbacks...
research
10/12/2020

SURF: Improving classifiers in production by learning from busy and noisy end users

Supervised learning classifiers inevitably make mistakes in production, ...
research
09/18/2023

SYNDICOM: Improving Conversational Commonsense with Error-Injection and Natural Language Feedback

Commonsense reasoning is a critical aspect of human communication. Despi...
research
06/07/2023

Improving Open Language Models by Learning from Organic Interactions

We present BlenderBot 3x, an update on the conversational model BlenderB...
research
05/27/2021

Generative Adversarial Imitation Learning for Empathy-based AI

Generative adversarial imitation learning (GAIL) is a model-free algorit...
research
05/12/2023

Text2Cohort: Democratizing the NCI Imaging Data Commons with Natural Language Cohort Discovery

The Imaging Data Commons (IDC) is a cloud-based database that provides r...

Please sign up or login with your details

Forgot password? Click here to reset