Regularized Graph Convolutional Networks for Short Text Classification

08/12/2020

Regularized Graph Convolutional Networks for Short Text Classification

Kshitij Tayal, Nikhil Rao, Saurabh Agarwal, Xiaowei Jia, Karthik Subbian, Vipin Kumar

Keywords:

Abstract Paper Similar Papers

Abstract: Short text classification is a fundamental problem in natural language processing, social network analysis, and e-commerce. The lack of structure in short text sequences limits the success of popular NLP methods based on deep learning. Simpler methods that rely on bag-of-words representations tend to perform on par with complex deep learning methods. To tackle the limitations of textual features in short text, we propose a Graph-regularized Graph Convolution Network (GR-GCN), which augments graph convolution networks by incorporating label dependencies in the output space. Our model achieves state-of-the-art results on both proprietary and external datasets, outperforming several baseline methods by up to 6% . Furthermore, we show that compared to baseline methods, GR-GCN is more robust to noise in textual features.

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

https://underline.io/lecture/9016-regularized-graph-convolutional-networks-for-short-text-classification

(Link will open in new window)

0

0

0

0

Share

This is an embedded video. Talk and the respective paper are published at COLING Workshops 2020 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

14/06/2020

Shoestring: Graph-Based Semi-Supervised Classification With Severely Limited Labeled Data

Wanyu Lin, Zhaolin Gao, Baochun Li

Keywords Paper

graph-based semi-supervised learning, few-shot learning, graph convolutional networks, graph embedding network, metric learning, label propagation, semantic similarity.

0

0

0

0

1:05

05/01/2021

AdarGCN: Adaptive Aggregation GCN for Few-Shot Learning

Jianhong Zhang, Manli Zhang, Zhiwu Lu, Tao Xiang

Keywords Paper

0

0

0

0

4:45

07/09/2020

Graph Density-Aware Losses for Novel Compositions in Scene Graph Generation

Boris Knyazev, Harm De Vries, Cătălina Cangea and
Graham Taylor, Aaron Courville, Eugene Belilovsky

Keywords Paper

scene graphs, scene graph generation, graph density, compositional generalization, visual genome, gqa, message passing

0

0

0

0

10:04

14/09/2020

Inductive Document Representation Learning for Short Text Clustering

Junyang Chen, Zhiguo Gong, Xiao Dong and
Wei Wang, Wei Wang, Weiwen Liu, Cong Wang, Xian Chen

Keywords Paper

0

0

0

0

10:45

25/07/2020

Item tagging for information retrieval: A tripartite graph neural network based approach

Kelong Mao, Xi Xiao, Jieming Zhu and
Biao Lu, Ruiming Tang, Xiuqiang He

Keywords Paper

item tagging, graph neural networks, information retrieval

0

0

0

0

16:53

03/05/2021

Universal Weakly Supervised Segmentation by Pixel-to-Segment Contrastive Learning

Tsung-Wei Ke, Jyh-Jing Hwang, Stella Yu

Keywords Paper

metric learning, representation learning for computer vision, weakly supervised representation learning, semantic segmentation

0

0

0

0

5:12

14/06/2020

Density-Aware Graph for Deep Semi-Supervised Visual Recognition

Suichan Li, Bin Liu, Dongdong Chen and
Qi Chu, Lu Yuan, Nenghai Yu

Keywords Paper

semi-supervised learning, density-aware graph, neighborhood aggregation, density-ascending path, label propagation

0

0

0

0

1:01

19/08/2021

TextGTL: Graph-based Transductive Learning for Semi-supervised Text Classification via Structure-Sensitive Interpolation

Chen Li, Xutan Peng, Hao Peng and
Jianxin Li, Lihong Wang

Keywords Paper

Machine Learning, Semi-Supervised Learning, Mining Graphs, Semi Structured Data, Complex Data

0

0

0

0

13:14

19/08/2021

CogTree: Cognition Tree Loss for Unbiased Scene Graph Generation

Jing Yu, Yuan Chai, Yujing Wang and
Yue Hu, Qi Wu

Keywords Paper

Computer Vision, Language and Vision

0

0

0

0

15:08

14/06/2020

Distribution-Induced Bidirectional Generative Adversarial Network for Graph Representation Learning

Shuai Zheng, Zhenfeng Zhu, Xingxing Zhang and
Zhizhe Liu, Jian Cheng, Yao Zhao

Keywords Paper

graph representation learning, generative adversarial network, graph neural network, unsupervised learning

0

0

0

0

1:01

06/12/2020

Rethinking Learnable Tree Filter for Generic Feature Transform

Lin Song, Yanwei Li, Zhengkai Jiang and
Zeming Li, Xiangyu Zhang, Hongbin Sun, Jian Sun, Nanning Zheng

Keywords Paper

Neuroscience and Cognitive Science -> Memory; Optimization -> Combinatorial Optimization; Optimization -> Submodular Optimizati, Neuroscience and Cognitive Science -> Human or Animal Learning

0

0

0

0

3:11

05/12/2020

Graph attention network with memory fusion for aspect-level sentiment analysis

Li Yuan, Jin Wang, Liang-Chih Yu, Xuejie Zhang

Keywords Paper

0

0

0

0

12:18

02/02/2021

Context-Aware Graph Convolution Network for Target Re-identification

Deyi Ji, Haoran Wang, Hanzhe Hu and
Weihao Gan, Wei Wu, Junjie Yan

Keywords Paper

0

0

0

0

13:44

05/01/2021

Multimodal Prototypical Networks for Few-Shot Learning

Frederik Pahde, Mihai Puscas, Tassilo Klein, Moin Nabi

Keywords Paper

0

0

0

0

4:56

02/02/2021

Communicative Message Passing for Inductive Relation Reasoning

Sijie Mai, Shuangjia Zheng, Yuedong Yang, Haifeng Hu

Keywords Paper

0

0

0

0

13:25

02/02/2021

PGNet: Real-time Arbitrarily-Shaped Text Spotting with Point Gathering Network

Pengfei Wang, Chengquan Zhang, Fei Qi and
Shanshan Liu, Xiaoqiang Zhang, Pengyuan Lyu, Junyu Han, Jingtuo Liu, Errui Ding, Guangming Shi

Keywords Paper

0

0

0

0

18:06

04/07/2020

pyBART: Evidence-based Syntactic Transformations for IE

Aryeh Tiktinsky, Yoav Goldberg, Reut Tsarfaty

Keywords Paper

IE, machine-learned tasks, downstream applications, data-driven transformations

0

0

0

0

14:02

26/04/2020

Unsupervised Clustering using Pseudo-semi-supervised Learning

Divam Gupta, Ramachandran Ramjee, Nipun Kwatra, Muthian Sivathanu

Keywords Paper

Unsupervised Learning, Unsupervised Clustering, Deep Learning

0

0

0

0

4:27

07/06/2020

Gossip and Attend: Context-Sensitive Graph Representation Learning

Zekarias T. Kefato, Sarunas Girdzijauskas

Keywords Paper

attention, communities, contexts, detection, graphs, learning, links, networks, nodes, predictions, representation learning, representations, structure

0

0

0

0

10:49

16/11/2020

Lightweight, Dynamic Graph Convolutional Networks for AMR-to-Text Generation

Yan Zhang, Zhijiang Guo, Zhiyang Teng and
Wei Lu, Shay B. Cohen, Zuozhu Liu, Lidong Bing

Keywords Paper

amr-to-text generation, graph representations, graph gcns, gcns

0

0

0

0

11:22

06/12/2020

Active Structure Learning of Causal DAGs via Directed Clique Trees

Chandler Squires, Sara Magliacane, Kristjan Greenewald and
Dmitriy Katz, Murat Kocaoglu, Karthikeyan Shanmugam

Keywords Paper

0

0

0

0

3:23

30/11/2020

Webly Supervised Semantic Embeddings for Large Scale Zero-Shot Learning

Yannick Le Cacheux, Adrian Popescu, Herve Le Borgne

Keywords Paper

0

0

0

0

8:08

03/05/2021

My Body is a Cage: the Role of Morphology in Graph-Based Incompatible Control

Vitaly Kurin, Maximilian Igl, Tim Rocktaeschel and
Wendelin Boehmer, Shimon Whiteson

Keywords Paper

Incompatible Environments, Continuous Control, Multitask Reinforcement Learning, Deep Reinforcement Learning, Graph Neural Networks

0

0

0

0

5:03

01/07/2020

Integrating Graph-Based and Transition-Based Dependency Parsers in the Deep Contextualized Era

Agnieszka Falenska, Anders Björkelund, Jonas Kuhn

Keywords Paper

0

0

0

0

14:03

03/05/2021

Simple Spectral Graph Convolution

Hao Zhu, Piotr Koniusz

Keywords Paper

Graph Convolutional Network, Oversmoothing

0

0

0

0

5:06

22/11/2021

A Simple Baseline for Weakly-Supervised Human-centric Relation Detection

Raghav Goyal, Leonid Sigal

Keywords Paper

weakly-supervised learning, human-object interaction

0

0

0

0

2:55

14/09/2020

Graph-Revised Convolutional Network

Donghan Yu, Ruohong Zhang, Zhengbao Jiang and
Yuexin Wu, Yiming Yang

Keywords Paper

graph convolutional network, graph learning, semi-supervised learning

0

0

0

0

14:47

05/01/2021

Transductive Visual Verb Sense Disambiguation

Sebastiano Vascon, Sinem Aslan, Gianluca Bigaglia and
Lorenzo Giudice, Marcello Pelillo

Keywords Paper

0

0

0

0

4:45

06/12/2021

Instance-dependent Label-noise Learning under a Structural Causal Model

Yu Yao, Tongliang Liu, Mingming Gong and
Bo Han, Gang Niu, Kun Zhang

Keywords Paper

deep learning, causality

0

0

0

0

11:12

19/04/2021

Combining deep generative models and multi-lingual pretraining for semi-supervised document classification

Yi Zhu, Ehsan Shareghi, Yingzhen Li and
Roi Reichart, Anna Korhonen

Keywords Paper

0

0

0

0

7:13

07/09/2020

Learning Effectively from Noisy Supervision for Weakly Supervised Semantic Segmentation

Wenbin Xie, Qiaoqiao Wei, Zheng Li, Hui Zhang

Keywords Paper

Semantic Segmentation, Weakly Supervised Semantic Segmentation, Self Attention

0

0

0

0

3:46

04/07/2020

Representations of Syntax [MASK] Useful: Effects of Constituency and Dependency Structure in Recursive LSTMs

Michael Lepori, Tal Linzen, R. Thomas McCoy

Keywords Paper

syntactic tasks, subject-verb task, fine-tuning, data augmentation

0

0

0

0

6:55

02/02/2021

Multi-level Distance Regularization for Deep Metric Learning

Yonghyun Kim, Wonpyo Park

Keywords Paper

0

0

0

0

12:19

19/08/2021

Graph Filter-based Multi-view Attributed Graph Clustering

Zhiping Lin, Zhao Kang

Keywords Paper

Machine Learning, Clustering, Multi-instance; Multi-label; Multi-view learning, Clustering, Unsupervised Learning

0

0

0

0

13:23

14/06/2020

Deep Semantic Clustering by Partition Confidence Maximisation

Jiabo Huang, Shaogang Gong, Xiatian Zhu

Keywords Paper

deep clustering, cluster separability, separability measurement, semantic plausibility

0

0

0

0

1:00

06/12/2020

Reliable Graph Neural Networks via Robust Aggregation

Simon Geisler, Daniel Zügner, Stephan Günnemann

Keywords Paper

0

0

0

0

3:16

06/12/2021

ReSSL: Relational Self-Supervised Learning with Weak Augmentation

Mingkai Zheng, Shan You, Fei Wang and
Chen Qian, Changshui Zhang, Xiaogang Wang, Chang Xu

Keywords Paper

self-supervised learning, contrastive learning

0

0

0

0

6:35

03/05/2021

Categorical Normalizing Flows via Continuous Transformations

Phillip Lippe, Stratis Gavves

Keywords Paper

Normalizing Flows, Graph Generation, Density Estimation

0

0

0

0

4:40

25/07/2020

Disentangled graph collaborative filtering

Xiang Wang, Hongye Jin, An Zhang and
Xiangnan He, Tong Xu, Tat-Seng Chua

Keywords Paper

explainable recommendation, disentangled representation learning, collaborative filtering, graph neural networks

0

0

0

0

15:17

30/11/2020

Few-Shot Zero-Shot Learning: Knowledge Transfer with Less Supervision

Nanyi Fei, Jiechao Guan, Zhiwu Lu, Yizhao Gao

Keywords Paper

0

0

0

0

7:37