A Novel Bi-directional Interrelated Model for Joint Intent Detection and Slot Filling

ACL 2019  ·  Haihong E, Peiqing Niu, Zhongfu Chen, Meina Song ·

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.

PDF Abstract ACL 2019 PDF ACL 2019 Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Slot Filling ATIS SF-ID F1 0.958 # 5
Intent Detection ATIS SF-ID Accuracy 97.76 # 5
Intent Detection ATIS SF-ID (BLSTM) network Accuracy 97.76 # 5
F1 95.80 # 4
Intent Detection SNIPS SF-ID (BLSTM) network Intent Accuracy 97.43 # 5
Slot F1 Score 92.23 # 4
Intent Detection SNIPS SF-ID Intent Accuracy 97.43 # 5
Slot F1 Score 92.23 # 4

Methods


No methods listed for this paper. Add relevant methods here