# Coupled Representation Learning for Domains, Intents and Slots in Spoken Language Understanding

## TL;DR

This paper introduces a novel hierarchical representation learning model for domains, intents, and slots in spoken language understanding, improving downstream task performance by capturing their dependencies.

## Contribution

It is the first to jointly learn hierarchical representations of domains, intents, and slots, leveraging their dependencies for better understanding.

## Key findings

- Improved performance on cross-domain reranking tasks.
- Effective joint learning of hierarchical representations.
- Demonstrated the model's superiority over existing methods.

## Abstract

Representation learning is an essential problem in a wide range of applications and it is important for performing downstream tasks successfully. In this paper, we propose a new model that learns coupled representations of domains, intents, and slots by taking advantage of their hierarchical dependency in a Spoken Language Understanding system. Our proposed model learns the vector representation of intents based on the slots tied to these intents by aggregating the representations of the slots. Similarly, the vector representation of a domain is learned by aggregating the representations of the intents tied to a specific domain. To the best of our knowledge, it is the first approach to jointly learning the representations of domains, intents, and slots using their hierarchical relationships. The experimental results demonstrate the effectiveness of the representations learned by our model, as evidenced by improved performance on the contextual cross-domain reranking task.