Few-shot Learning for Multi-label Intent Detection

02/02/2021

Few-shot Learning for Multi-label Intent Detection

Yutai Hou, Yongkui Lai, Yushan Wu, Wanxiang Che, Ting Liu

Keywords:

Abstract Paper Similar Papers

Abstract: In this paper, we study the few-shot multi-label classification for user intent detection. For multi-label intent detection, state-of-the-art work estimates label-instance relevance scores and uses a threshold to select multiple associated intent labels. To determine appropriate thresholds with only a few examples, we first learn universal thresholding experience on data-rich domains, and then adapt the thresholds to certain few-shot domains with a calibration based on nonparametric learning. For better calculation of label-instance relevance score, we introduce label name embedding as anchor points in representation space, which refines representations of different classes to be well-separated from each other. Experiments on two datasets show that the proposed model significantly outperforms strong baselines in both one-shot and five-shot settings.

The video of this talk cannot be embedded. You can watch it here:

https://slideslive.com/38949313

(Link will open in new window)

0

0

0

0

Share

This is an embedded video. Talk and the respective paper are published at AAAI 2021 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment

no comments yet

Similar Papers

04/07/2020

Few-shot Slot Tagging with Collapsed Dependency Transfer and Label-enhanced Task-adaptive Projection Network

Yutai Hou, Wanxiang Che, Yongkui Lai and
Zhihan Zhou, Yijia Liu, Han Liu, Ting Liu

Keywords Paper

slot tagging, Few-shot tagging, fewshot problems, Few-shot Tagging

0

0

0

0

12:00

06/12/2020

Multilabel Classification by Hierarchical Partitioning and Data-dependent Grouping

Shashanka Ubaru, Sanjeeb Dash, Arya Mazumdar, Oktay Gunluk

Keywords Paper

Optimization -> Non-Convex Optimization, Deep Learning -> Optimization for Deep Networks

0

0

0

0

3:22

07/09/2020

Weakly-supervised Salient Instance Detection

Xin Tian, Ke Xu, Xin Yang and
Baocai Yin, Rynson Lau

Keywords Paper

Salient Instance Detection, SID, weak supervision, saliency detection, subitizing

0

0

0

0

8:22

06/12/2020

Multifaceted Uncertainty Estimation for Label-Efficient Deep Learning

Weishi Shi, Xujiang Zhao, Feng Chen, Qi Yu

Keywords Paper

0

0

0

0

3:15

02/02/2021

Multi-task Learning by Leveraging the Semantic Information

Fan Zhou, Brahim Chaib-draa, Boyu Wang

Keywords Paper

0

0

0

0

16:53

18/11/2020

Proxy network for few shot learning

Bin Xiao, Chien-Liang Liu, Wen-Hoar Hsaio

Keywords Paper

0

0

0

0

9:50

14/06/2020

Domain-Aware Visual Bias Eliminating for Generalized Zero-Shot Learning

Shaobo Min, Hantao Yao, Hongtao Xie and
Chaoqun Wang, Zheng-Jun Zha, Yongdong Zhang

Keywords Paper

generalized zero-shot learning, domain detection, recognition, segmentation, margin loss, bilinear pooling, nas, transfer learning, domain adaption, computer vision.

0

0

0

0

0:58

13/04/2021

Active learning with maximum margin sparse gaussian processes

Weishi Shi, Qi Yu

Keywords Paper

0

0

0

0

3:00

03/05/2021

Bayesian Few-Shot Classification with One-vs-Each Pólya-Gamma Augmented Gaussian Processes

Jake Snell, Richard Zemel

Keywords Paper

uncertainty estimation, few-shot learning, bayesian deep learning, gaussian processes

0

0

0

0

4:58

22/09/2020

Content-collaborative disentanglement representation learning for enhanced recommendation

Yin Zhang, Ziwei Zhu, Yun He, James Caverlee

Keywords Paper

content-aware recommendation, disentangled representation learning, collaborative filtering

0

0

0

0

2:35

06/12/2021

Realistic evaluation of transductive few-shot learning

Olivier Veilleux, Malik Boudiaf, Pablo Piantanida, Ismail Ben Ayed

Keywords Paper

optimization, machine learning, few shot learning

0

0

0

0

10:21

03/05/2021

Multi-Class Uncertainty Calibration via Mutual Information Maximization-based Binning

Kanil Patel, William H Beluch, Bin Yang and
Michael Pfeiffer, Dan Zhang

Keywords Paper

deep neural networks, histogram binning, post-hoc calibration, uncertainty calibration, mutual information

0

0

0

0

5:13

14/06/2020

Fine-Grained Generalized Zero-Shot Learning via Dense Attribute-Based Attention

Dat Huynh, Ehsan Elhamifar

Keywords Paper

zero-shot learning, few-shot learning, fine-grained recognition, transfer learning, attention

0

0

0

0

1:01

06/12/2020

Exemplar Guided Active Learning

Jason Hartford, Kevin Leyton-Brown, Hadas Raviv and
Dan Padnos, Shahar Lev, Barak Lenz

Keywords Paper

Algorithms -> Multitask and Transfer Learning; Algorithms -> Representation Learning; Algorithms -> Semi-Supervised Learning; A, Algorithms -> Unsupervised Learning

0

0

0

0

3:23

22/11/2021

Few-shot Action Recognition with Prototype-centered Attentive Learning

Xiatian Zhu, Antoine S Toisoul, Juan-Manuel Perez-Rua and
Li Zhang, Brais Martinez, Tao Xiang

Keywords Paper

Few-shot learning, Video recognition, Action classification, Small training data, Model pre-training, Meta-learning, Transformer, Self-attention learning, Cross-attention learning, Prototype learning, Prototype-centered learning, Hybrid-attention learning

0

0

0

0

2:22

18/07/2021

Sparse Feature Selection Makes Batch Reinforcement Learning More Sample Efficient

Botao Hao, Yaqi Duan, Tor Lattimore and
Csaba Szepesvari, Mengdi Wang

Keywords Paper

Theory, Statistical Learning Theory

0

0

0

0

5:20

30/11/2020

MatchGAN: A Self-Supervised Semi-Supervised Conditional Generative Adversarial Network

Jiaze Sun, Binod Bhattarai, Tae-Kyun Kim

Keywords Paper

0

0

0

0

8:00

06/12/2021

Implicit Semantic Response Alignment for Partial Domain Adaptation

Wenxiao Xiao, Zhengming Ding, Hongfu Liu

Keywords Paper

domain adaptation, transfer learning

0

0

0

0

11:43

06/12/2020

Unsupervised Semantic Aggregation and Deformable Template Matching for Semi-Supervised Learning

Tao Han, Junyu Gao, Yuan Yuan, Qi Wang

Keywords Paper

0

0

0

0

3:22

19/10/2020

Enhance prototypical network with text descriptions for few-shot relation classification

Kaijia Yang, Nantao Zheng, Xinyu Dai and
Liang He, Shujian Huang, Jiajun Chen

Keywords Paper

text description, relation extraction, few shot

0

0

0

0

6:55

05/01/2021

Class-Wise Metric Scaling for Improved Few-Shot Classification

Ge Liu, Linglan Zhao, Wei Li and
Dashan Guo, Xiangzhong Fang

Keywords Paper

0

0

0

0

5:01

03/05/2021

Prototypical Contrastive Learning of Unsupervised Representations

Junnan Li, Pan Zhou, Caiming Xiong, Steven Hoi

Keywords Paper

self-supervised learning, unsupervised learning, representation learning, contrastive learning

0

0

0

0

4:51

14/06/2020

Multi-Scale Interactive Network for Salient Object Detection

Youwei Pang, Xiaoqi Zhao, Lihe Zhang, Huchuan Lu

Keywords Paper

saliency detection, salient object detection, feature interaction strategy, scale-insensitive loss, multi-scale features, multi-level features, fully convolutional network, deep learning

0

0

0

0

1:01

12/07/2020

Pretrained Generalized Autoregressive Model with Adaptive Probabilistic Label Cluster for Extreme Multi-label Text Classification

Hui Ye, Zhiyu Chen, Da-Han Wang, Brian Davison

Keywords Paper

Deep Learning - General

0

0

0

0

15:08

05/01/2021

Towards Fair Cross-Domain Adaptation via Generative Learning

Tongxin Wang, Zhengming Ding, Wei Shao and
Haixu Tang, Kun Huang

Keywords Paper

0

0

0

0

4:56

18/07/2021

Aggregating From Multiple Target-Shifted Sources

Changjian Shui, Zijian Li, Jiaqi Li and
Christian Gagne, Charles X. Ling, Boyu Wang

Keywords Paper

Theory, Spaces of Functions and Kernels, Optimization, Convex Optimization; Theory, Algorithms, Multitask, Transfer, and Meta Learning

0

0

0

0

5:04

22/11/2021

MMD-ReID: A Simple but Effective Solution for Visible-Thermal Person ReID

Chaitra S Jambigi, Ruchit Rawal, Anirban Chakraborty

Keywords Paper

person reidentification, cross modal reid, visible thermal reid, multimodal, domain adaptation, representation learning, metric learning

0

0

0

0

9:36

12/07/2020

Extreme Multi-label Classification from Aggregated Labels

Yanyao Shen, Hsiang-Fu Yu, Sujay Sanghavi, Inderjit Dhillon

Keywords Paper

Optimization - Large Scale, Parallel and Distributed

0

0

0

0

15:05

04/07/2020

Investigating Word-Class Distributions in Word Vector Spaces

Ryohei Sasano, Anna Korhonen

Keywords Paper

modeling distribution, centroid-based model, discriminative models, Word-Class Distributions

0

0

0

0

11:53

18/07/2021

Learning from Similarity-Confidence Data

Yuzhou Cao, Lei Feng, Yitian Xu and
Bo An, Gang Niu, Masashi Sugiyama

Keywords Paper

Algorithms, Semi-Supervised Learning

0

0

0

0

4:05

14/06/2020

Few-Shot Open-Set Recognition Using Meta-Learning

Bo Liu, Hao Kang, Haoxiang Li and
Gang Hua, Nuno Vasconcelos

Keywords Paper

open-set, few-shot, meta-learning

0

0

0

0

1:01

13/04/2021

Selective classification via one-sided prediction

Aditya Gangrade, Anil Kag, Venkatesh Saligrama

Keywords Paper

0

0

0

0

3:23

14/06/2020

Progressive Relation Learning for Group Activity Recognition

Guyue Hu, Bo Cui, Yuan He, Shan Yu

Keywords Paper

group activity recognition, relation learning, reinforcement learning, graph neural networks, action recognition

0

0

0

0

1:01

02/02/2021

Learning Intact Features by Erasing-Inpainting for Few-shot Classification

Junjie Li, Zilei Wang, Xiaoming Hu

Keywords Paper

0

0

0

0

15:15

18/07/2021

Multi-Dimensional Classification via Sparse Label Encoding

BINBIN JIA, Min-Ling Zhang

Keywords Paper

Algorithms, Supervised Learning

0

0

0

0

16:52

06/12/2021

Few-Shot Object Detection via Association and DIscrimination

Yuhang Cao, Jiaqi Wang, Ying Jin and
Tong Wu, Kai Chen, Ziwei Liu, Dahua Lin

Keywords Paper

deep learning, machine learning, vision

0

0

0

0

10:31

03/05/2021

Bowtie Networks: Generative Modeling for Joint Few-Shot Recognition and Novel-View Synthesis

Zhipeng Bao, Yu-Xiong Wang, Martial Hebert

Keywords Paper

adversarial training, computer vision, object recognition, few-shot learning, generative models

0

0

0

0

5:11

14/06/2020

Few-Shot Learning via Embedding Adaptation With Set-to-Set Functions

Han-Jia Ye, Hexiang Hu, De-Chuan Zhan, Fei Sha

Keywords Paper

few-shot learning, meta-learning, embedding learning, embedding adaptation, set-to-set

0

0

0

0

1:04

02/02/2021

Active Feature Selection for the Mutual Information Criterion

Shachar Schnapp, Sivan Sabato

Keywords Paper

0

0

0

0

15:03

19/08/2021

Cross-Domain Few-Shot Classification via Adversarial Task Augmentation

Haoqing Wang, Zhi-Hong Deng

Keywords Paper

Computer Vision, Recognition, Adversarial Machine Learning, Deep Learning

0

0

0

0

10:39