Towards a Fully Unsupervised Framework for Intent Induction in Customer Support Dialogues

TL;DR

This paper introduces a fully unsupervised method for identifying user intents in customer support dialogues, eliminating the need for annotated data and enhancing applicability across various industries.

Contribution

It presents a novel unsupervised framework for intent induction in dialogues, including preprocessing techniques and dialogue flow extraction, applicable to any domain without prior knowledge.

Findings

Effective intent induction without labeled data

Improved results with dialogue corpus preprocessing

Applicable to diverse customer support scenarios

Abstract

State of the art models in intent induction require annotated datasets. However, annotating dialogues is time-consuming, laborious and expensive. In this work, we propose a completely unsupervised framework for intent induction within a dialogue. In addition, we show how pre-processing the dialogue corpora can improve results. Finally, we show how to extract the dialogue flows of intentions by investigating the most common sequences. Although we test our work in the MultiWOZ dataset, the fact that this framework requires no prior knowledge make it applicable to any possible use case, making it very relevant to real world customer support applications across industry.