Continuous representations of intents for dialogue systems

TL;DR

This paper introduces a novel continuous intent representation model for dialogue systems that improves unseen intent detection and relationship analysis, enabling reliable addition of new intents without retraining.

Contribution

The paper proposes a continuous intent space model that enhances unseen intent detection and allows incremental addition of intents without retraining.

Findings

High accuracy in adding unseen intents

Retains performance on seen intents

Enables intent relationship analysis

Abstract

Intent modelling has become an important part of modern dialogue systems. With the rapid expansion of practical dialogue systems and virtual assistants, such as Amazon Alexa, Apple Siri, and Google Assistant, the interest has only increased. However, up until recently the focus has been on detecting a fixed, discrete, number of seen intents. Recent years have seen some work done on unseen intent detection in the context of zero-shot learning. This paper continues the prior work by proposing a novel model where intents are continuous points placed in a specialist Intent Space that yields several advantages. First, the continuous representation enables to investigate relationships between the seen intents. Second, it allows any unseen intent to be reliably represented given limited quantities of data. Finally, this paper will show how the proposed model can be augmented with unseen intents without retraining any of the seen ones. Experiments show that the model can reliably add unseen intents with a high accuracy while retaining a high performance on the seen intents.