Continuous representations of intents for dialogue systems
This addresses the challenge of handling unseen intents in dialogue systems for applications like virtual assistants, but it is incremental as it builds on prior zero-shot learning work.
The paper tackles the problem of representing intents in dialogue systems as continuous points in an Intent Space, enabling analysis of relationships between seen intents and reliable representation of unseen intents with limited data, and experiments show it can add unseen intents with high accuracy while maintaining performance on seen intents.
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.