Learning Improvised Chatbots from Adversarial Modifications of Natural Language Feedback

Makesh Narsimhan Sreedhar, Kun Ni, Siva Reddy

Abstract
The ubiquitous nature of dialogue systems 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%to 75.96% in ranking correct responses on the PERSONACHATdataset, a large improvement given that the original model is already trained on 131k samples.
Anthology ID:
2020.findings-emnlp.221
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2020
Month:
November
Year:
2020
Address:
Online
Editors:
Trevor Cohn, Yulan He, Yang Liu
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2445–2453
Language:
URL:
https://aclanthology.org/2020.findings-emnlp.221
DOI:
10.18653/v1/2020.findings-emnlp.221
Bibkey:
Cite (ACL):
Makesh Narsimhan Sreedhar, Kun Ni, and Siva Reddy. 2020. Learning Improvised Chatbots from Adversarial Modifications of Natural Language Feedback. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 2445–2453, Online. Association for Computational Linguistics.
Cite (Informal):
Learning Improvised Chatbots from Adversarial Modifications of Natural Language Feedback (Sreedhar et al., Findings 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/2020.findings-emnlp.221.pdf
Code
 ekunnii/adversarial-feedback-chatbot
PDF Search Code