A Novel Bi-directional Interrelated Model for Joint Intent Detection and Slot Filling
This work addresses a specific bottleneck in spoken language understanding systems for applications like voice assistants, representing an incremental improvement over existing joint models.
The paper tackles the problem of joint intent detection and slot filling in spoken language understanding by proposing a novel bi-directional interrelated model that establishes direct connections between the two tasks, resulting in relative improvements of 3.79% and 5.42% in sentence-level semantic frame accuracy on ATIS and Snips datasets compared to state-of-the-art models.
A spoken language understanding (SLU) system includes two main tasks, slot filling (SF) and intent detection (ID). The joint model for the two tasks is becoming a tendency in SLU. But the bi-directional interrelated connections between the intent and slots are not established in the existing joint models. In this paper, we propose a novel bi-directional interrelated model for joint intent detection and slot filling. We introduce an SF-ID network to establish direct connections for the two tasks to help them promote each other mutually. Besides, we design an entirely new iteration mechanism inside the SF-ID network to enhance the bi-directional interrelated connections. The experimental results show that the relative improvement in the sentence-level semantic frame accuracy of our model is 3.79% and 5.42% on ATIS and Snips datasets, respectively, compared to the state-of-the-art model.