A Stack-Propagation Framework with Token-Level Intent Detection for Spoken Language Understanding

Intent detection and slot filling are two main tasks for building a spoken language understanding (SLU) system. The two tasks are closely tied and the slots often highly depend on the intent. In this paper, we propose a novel framework for SLU to better incorporate the intent information, which further guides the slot filling. In our framework, we adopt a joint model with Stack-Propagation which can directly use the intent information as input for slot filling, thus to capture the intent semantic knowledge. In addition, to further alleviate the error propagation, we perform the token-level intent detection for the Stack-Propagation framework. Experiments on two publicly datasets show that our model achieves the state-of-the-art performance and outperforms other previous methods by a large margin. Finally, we use the Bidirectional Encoder Representation from Transformer (BERT) model in our framework, which further boost our performance in SLU task.

PDF Abstract IJCNLP 2019 PDF IJCNLP 2019 Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Intent Detection ATIS Stack-Propagation (+BERT) Accuracy 97.50 # 7
F1 96.10 # 2
Intent Detection SNIPS Stack-Propagation (+BERT) Intent Accuracy 99.0 # 1
Slot F1 Score 97.00 # 1
Intent Detection SNIPS Stack-Propagation Intent Accuracy 98.00 # 2
Slot F1 Score 94.20 # 2

Methods