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.
@article{arxiv.1907.00390,
title = {A Novel Bi-directional Interrelated Model for Joint Intent Detection and Slot Filling},
author = {Haihong E and Peiqing Niu and Zhongfu Chen and Meina Song},
journal= {arXiv preprint arXiv:1907.00390},
year = {2019}
}
Comments
Accepted paper of ACL 2019 (short paper) with 5 pages