Saying No is An Art: Contextualized Fallback Responses for Unanswerable Dialogue Queries

TL;DR

This paper introduces a neural fallback response system for dialogue agents that generates contextually appropriate, paraphrased, and diverse responses to unanswerable queries, enhancing user interaction and reducing monotony.

Contribution

It presents a novel neural approach using dependency parse rules and a transformer model fine-tuned on synthetic data to produce natural, relevant fallback responses in dialogue systems.

Findings

Generated responses are contextually relevant and grammatically correct.

The approach improves user engagement by providing diverse and paraphrased fallback responses.

Automatic and manual evaluations confirm the effectiveness of the method.

Abstract

Despite end-to-end neural systems making significant progress in the last decade for task-oriented as well as chit-chat based dialogue systems, most dialogue systems rely on hybrid approaches which use a combination of rule-based, retrieval and generative approaches for generating a set of ranked responses. Such dialogue systems need to rely on a fallback mechanism to respond to out-of-domain or novel user queries which are not answerable within the scope of the dialog system. While, dialog systems today rely on static and unnatural responses like "I don't know the answer to that question" or "I'm not sure about that", we design a neural approach which generates responses which are contextually aware with the user query as well as say no to the user. Such customized responses provide paraphrasing ability and contextualization as well as improve the interaction with the user and reduce dialogue monotonicity. Our simple approach makes use of rules over dependency parses and a text-to-text transformer fine-tuned on synthetic data of question-response pairs generating highly relevant, grammatical as well as diverse questions. We perform automatic and manual evaluations to demonstrate the efficacy of the system.