A Co-Interactive Transformer for Joint Slot Filling and Intent Detection

Qin, Libo; Liu, Tailu; Che, Wanxiang; Kang, Bingbing; Zhao, Sendong; Liu, Ting

doi:10.1109/icassp39728.2021.9414110

Cited by 93 publications

(41 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Intent detection is an important component of dialogue system. Many methods have been proposed to solve this task in recent years [1]- [5] and most of these methods work well with the closed-world assumption. However, such an assumption is commonly violated in practical systems that are deployed in a dynamic or open environment.…”

Section: A Open Intent Classificationmentioning

confidence: 99%

Learning to Classify Open Intent via Soft Labeling and Manifold Mixup

Cheng¹,

Jiang²,

Yin³

et al. 2022

Preprint

View full text Add to dashboard Cite

Open intent classification is a practical yet challenging task in dialogue systems. Its objective is to accurately classify samples of known intents while at the same time detecting those of open (unknown) intents. Existing methods usually use outlier detection algorithms combined with K-class classifier to detect open intents, where K represents the class number of known intents. Different from them, in this paper, we consider another way without using outlier detection algorithms. Specifically, we directly train a (K+1)-class classifier for open intent classification, where the (K+1)-th class represents open intents. To address the challenge that training a (K+1)-class classifier with training samples of only K classes, we propose a deep model based on Soft Labeling and Manifold Mixup (SLMM). In our method, soft labeling is used to reshape the label distribution of the known intent samples, aiming at reducing model's overconfident on known intents. Manifold mixup is used to generate pseudo samples for open intents, aiming at well optimizing the decision boundary of open intents. Experiments on four benchmark datasets demonstrate that our method outperforms previous methods and achieves state-of-the-art performance. All the code and data of this work can be obtained at https://github.com/ zifengcheng/SLMM.

show abstract

Section: A Open Intent Classificationmentioning

confidence: 99%

Learning to Classify Open Intent via Soft Labeling and Manifold Mixup

Cheng¹,

Jiang²,

Yin³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Slot Filling and Intent Detection Recently, joint models (Zhang and Wang, 2016;Hakkani-Tür et al, 2016;Goo et al, 2018;Xia et al, 2018;E et al, 2019;Liu et al, 2019b;Qin et al, 2019;Zhang et al, 2019;Wu et al, 2020;Qin et al, 2021b;Ni et al, 2021) are proposed to consider the strong correlation between intent detection and slot filling have obtained remarkable success. Compared with their work, we focus on jointly modeling multiple intent detection and slot filling while they only consider the single-intent scenario.…”

Section: Related Workmentioning

confidence: 99%

GL-GIN: Fast and Accurate Non-Autoregressive Model for Joint Multiple Intent Detection and Slot Filling

Qin

Wei

Xie

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Multi-intent SLU can handle multiple intents in an utterance, which has attracted increasing attention. However, the state-of-the-art joint models heavily rely on autoregressive approaches, resulting in two issues: slow inference speed and information leakage. In this paper, we explore a non-autoregressive model for joint multiple intent detection and slot filling, achieving more fast and accurate. Specifically, we propose a Global-Locally Graph Interaction Network (GL-GIN) where a local slot-aware graph interaction layer is proposed to model slot dependency for alleviating uncoordinated slots problem while a global intentslot graph interaction layer is introduced to model the interaction between multiple intents and all slots in the utterance. Experimental results on two public datasets show that our framework achieves state-of-the-art performance while being 11.5 times faster.

show abstract

“…Motivated by this problem, the joint models [12,13,14] are developed for solving intent detection and slot filling tasks together. Besides, some work [15,5,16,17,18,19], tries to enhance the performance via multi-task learning. These joint models or multi-task learning methods link the two tasks implicitly via applying a joint loss function.…”

Section: Related Workmentioning

confidence: 99%

A Result based Portable Framework for Spoken Language Understanding

Cheng¹,

Jia

Yang

2021

Preprint

View full text Add to dashboard Cite

Spoken language understanding (SLU), which is a core component of the task-oriented dialogue system, has made substantial progress in the research of single-turn dialogue. However, the performance in multi-turn dialogue is still not satisfactory in the sense that the existing multi-turn SLU methods have low portability and compatibility for other single-turn SLU models. Further, existing multi-turn SLU methods do not exploit the historical predicted results when predicting the current utterance, which wastes helpful information. To gap those shortcomings, in this paper, we propose a novel Resultbased Portable Framework for SLU (RPFSLU). RPFSLU allows most existing single-turn SLU models to obtain the contextual information from multi-turn dialogues and takes full advantage of predicted results in the dialogue history during the current prediction. Experimental results on the public dataset KVRET have shown that all SLU models in baselines acquire enhancement by RPFSLU on multi-turn SLU tasks.

show abstract

A Co-Interactive Transformer for Joint Slot Filling and Intent Detection

Cited by 93 publications

References 18 publications

Learning to Classify Open Intent via Soft Labeling and Manifold Mixup

Learning to Classify Open Intent via Soft Labeling and Manifold Mixup

GL-GIN: Fast and Accurate Non-Autoregressive Model for Joint Multiple Intent Detection and Slot Filling

A Result based Portable Framework for Spoken Language Understanding

Contact Info

Product

Resources

About