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

By H. E, Peiqing Niu, Zhongfu Chen, Meina Song. 2019

271 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Philip S. Yu
2. Ting-Wei Liu
3. Kang Liu
4. Jun Zhao
5. Shizhu He
6. Wanxiang Che
7. Congying Xia
8. Jiawei Zhang

Citations in the corpus

• Lifelong Intent Detection via Multi-Strategy Rebalancing (2021, background): “Intent detection is usually formulated as a multi-class classification task, which predicts an intent class for a given user utterance [5, 7, 10, 26].”
• Towards Incremental Transformers: An Empirical Analysis of Transformer Models for Incremental NLU (2021, methodology): “We use the preprocessed data and splits for SNIPS and ATIS made available by E et al. (2019).”
• A Stack-Propagation Framework with Token-Level Intent Detection for Spoken Language Understanding (2019, background): “E et al. (2019) introduce an SF-ID network to establish the interrelated mechanism for slot filling and intent detection tasks.”
• CG-BERT: Conditional Text Generation with BERT for Generalized Few-shot Intent Detection (2020, background): “State-of-the-art intent detection models (Haihong et al., 2019; Zhang et al., 2018; Goo et al., 2018) capitalize on large amounts of labeled data to train supervised deep learning classification models.”
• SLURP: A Spoken Language Understanding Resource Package (2020, unknown): “, 2019) and SF-ID (E et al., 2019).”