A Novel Bi-directional Interrelated Model for Joint Intent Detection and Slot Filling
TL
TL;DR
A novel bi-directional interrelated model for joint intent detection and slot filling is proposed and an SF-ID network is introduced to establish direct connections for the two tasks to help them promote each other mutually.
Abstract
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.
References15 items
1
Slot-Gated Modeling for Joint Slot Filling and Intent Prediction
2
Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfaces
3
Syntax or semantics? knowledge-guided joint semantic frame parsing
4
End-to-End Memory Networks with Knowledge Carryover for Multi-Turn Spoken Language Understanding
5