Coupled Representation Learning for Domains, Intents and Slots in Spoken Language Understanding
This addresses representation learning for spoken language understanding systems, but it appears incremental as it builds on existing hierarchical dependencies.
The paper tackles the problem of learning hierarchical representations for domains, intents, and slots in spoken language understanding, resulting in improved performance on a contextual cross-domain reranking task.
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.