A joint model based on interactive gate mechanism for spoken language understanding

摘要

Slot filling and intent detection are two important tasks in a spoken language understanding (SLU) system, it is becoming a tendency that two tasks are jointing learn in SLU. However, many existing model only conduct join model by share parameters on the surface level rather than bi-directional interaction for slot filling and intent detection tasks. In this paper, we designed a dual interaction model based on the gate mechanism. First, We utilize a Dilated Convolutional Neural Networks (DCNN) block with self-attention to better capture the semantic of utterance. Besides, for the two tasks we adopt gate mechanism to get the interaction information of intent and slot, which can control the passing rate and make fully use of semantic relevance between slot filling and intent detection. Finally, the experiments results show that our model has significantly improved in the slot filling F1, intent detection accuracy on the ATIS and SNIPS datasets and overmatch other prior methods.