Joint Slot Filling and Intent Detection via Capsule Neural Networks
This work addresses a key challenge in natural language understanding for applications like virtual assistants, though it appears incremental as it builds on prior joint models with a novel architectural tweak.
The paper tackles the problem of joint slot filling and intent detection in natural language understanding by proposing a capsule-based neural network model that exploits semantic hierarchy through dynamic routing, achieving improved performance on two real-world datasets compared to existing models and services.
Being able to recognize words as slots and detect the intent of an utterance has been a keen issue in natural language understanding. The existing works either treat slot filling and intent detection separately in a pipeline manner, or adopt joint models which sequentially label slots while summarizing the utterance-level intent without explicitly preserving the hierarchical relationship among words, slots, and intents. To exploit the semantic hierarchy for effective modeling, we propose a capsule-based neural network model which accomplishes slot filling and intent detection via a dynamic routing-by-agreement schema. A re-routing schema is proposed to further synergize the slot filling performance using the inferred intent representation. Experiments on two real-world datasets show the effectiveness of our model when compared with other alternative model architectures, as well as existing natural language understanding services.