Slot-Gated Modeling for Joint Slot Filling and Intent Prediction

By Chih-Wen Goo, Guang-Lai Gao, Yun-Kai Hsu, Chih-Li Huo, Tsung-Chieh Chen, Keng-Wei Hsu, Yun-Nung (Vivian) Chen. 2018

516 citations recorded by the source corpus.

Attention-based recurrent neural network models for joint intent detection and slot filling have achieved the state-of-the-art performance, while they have independent attention weights. Considering that slot and intent have the strong relationship, this paper proposes a slot gate that focuses on learning the relationship between intent and slot attention vectors in order to obtain better semantic frame results by the global optimization. The experiments show that our proposed model significantly improves sentence-level semantic frame accuracy with 4.2% and 1.9% relative improvement compared to the attentional model on benchmark ATIS and Snips datasets respectively

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

Citations in the corpus

A Progressive Model to Enable Continual Learning for Semantic Slot Filling (2019, background): “, 2019) or jointly with the other intent detection task in SLU (Guo et al., 2014; Liu and Lane, 2016; Zhang and Wang, 2016; Wang et al., 2018; Goo et al., 2018).”
Towards Open Intent Discovery for Conversational Text (2019, methodology): “Recent approaches have drawn upon progress in CNN, RNN, and CRF based language models to improve intent detection [11, 22, 24, 31, 36, 49, 52].”
Neural Data Augmentation via Example Extrapolation (2021, methodology): “6We use the preprocessed version from Goo et al. (2018) at https://github.com/MiuLab/SlotGated-SLU.”
Don’t Parse, Generate! A Sequence to Sequence Architecture for Task-Oriented Semantic Parsing (2020, methodology): “LMo) by 3.3%. It is close to the best ensemble approach (SR + ELMo + SVRank). Method Accuracy exact match intent Joint BiRNN [7] 73.20 96.90 Attention BiRNN [16] 74.10 96.70 Slot Gated Full Attention [5] 75.50 97.00 CapsuleNLU [36] 80.90 97.30 Seq2Seq-Ptr (no pretraining) 85.43 97.00 Seq2Seq-Ptr (BE”
Data Augmentation by Data Noising for Open-vocabulary Slots in Spoken Language Understanding (2019, methodology): “It is used in SLU studies (Goo et al., 2018; Yoo et al., 2018).”
Continual Few-shot Intent Detection (2022, background): “Popular approaches such as Goo et al. (2018); Qin et al. (2019); Mehri et al. (2020) have achieved promising performance.”
A Novel Bi-directional Interrelated Model for Joint Intent Detection and Slot Filling (2019, background): “Goo et al. (2018) proposed a slot-gated model which applies the intent information to slot ﬁlling task and achieved superior performance.”
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.”
BiToD: A Bilingual Multi-Domain Dataset For Task-Oriented Dialogue Modeling (2021, background): “They serve as effective benchmarks for SLU tasks, such as intent classification, slot filling [44, 45].”
Semantically Conditioned Dialog Response Generation via Hierarchical Disentangled Self-Attention (2019, background): “Canonical task-oriented dialog systems are built as pipelines of separately trained modules: (i) user intention classification (Shi et al., 2016; Goo et al., 2018), which is for understanding human intention.”
Data Augmentation for Spoken Language Understanding via Joint Variational Generation (2018, methodology): “Table 3: Mean data augmentation results on various SLU tasks tested using the slot-gated (Goo et al. 2018) SLU models.”
Deep Unknown Intent Detection with Margin Loss (2019, background): “DNN such as BiLSTM (Goo et al., 2018; Wang et al., 2018c) has demonstrated the ability to learn high-level semantic features of intents.”
BERT for Joint Intent Classification and Slot Filling (2019, methodology): “Recently, several joint learning meth-ods for intent classiﬁcation and slot ﬁlling were proposed to exploit and model the dependencies between the two tasks and improve the performance over independent models (Guo et al., 2014; Hakkani-T¨ur et al., 2016; Liu and Lane, 2016; Goo et al., 2018).”
Abstractive Dialogue Summarization with Sentence-Gated Modeling Optimized by Dialogue Acts (2018, background): “A gating mechanism is able to model the explicit relationship between two types of information [39].”
Simple is Better! Lightweight Data Augmentation for Low Resource Slot Filling and Intent Classification (2020, background): “Although neural-based models (Qin et al., 2019; Goo et al., 2018; Mesnil et al., 2015) have achieved stellar performance in slot filling (SF) and intent”
A Stack-Propagation Framework with Token-Level Intent Detection for Spoken Language Understanding (2019, methodology): “Table 4 gives the results of BERT model on ATIS and SNIPS datasets.”