Regularized Graph Convolutional Networks for Short Text Classification

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

doi:10.18653/v1/2020.coling-industry.22

Cited by 10 publications

(5 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, Beery et al (2018) [2] demonstrated a network that accurately recognizes cows in a typical context (e.g., pasture) consistently misclassifies cows in a non-typical context (e.g., beach). Similar heuristics also arise in visual question answering systems [1] and researchers proposed graph generative modeling schemes [13] (inspired by graph convolutional networks [30]) to handle the problem implicitly. In this paper, we study this problem within the Natural Language Inference (NLI): the task of determining whether a premise sentence entails (i.e., implies the truth of) a hypothesis sentence [7,8,4].…”

Section: Introductionmentioning

confidence: 89%

Understanding Out-of-distribution: A Perspective of Data Dynamics

Adila¹,

Kang²

2021

Preprint

View full text Add to dashboard Cite

Despite machine learning models' success in Natural Language Processing (NLP) tasks, predictions from these models frequently fail on out-of-distribution (OOD) samples. Prior works have focused on developing state-of-the-art methods for detecting OOD. The fundamental question of how OOD samples differ from indistribution samples remains unanswered. This paper explores how data dynamics in training models can be used to understand the fundamental differences between OOD and in-distribution samples in extensive detail. We found that syntactic characteristics of the data samples that the model consistently predicts incorrectly in both OOD and in-distribution cases directly contradict each other. In addition, we observed preliminary evidence supporting the hypothesis that models are more likely to latch on trivial syntactic heuristics (e.g., overlap of words between two sentences) when making predictions on OOD samples. We hope our preliminary study accelerates the data-centric analysis on various machine learning phenomena.

show abstract

Section: Introductionmentioning

confidence: 89%

Understanding Out-of-distribution: A Perspective of Data Dynamics

Adila¹,

Kang²

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…This model uses the HIN framework to model short texts, which can contain any additional information and capture rich relationships between texts and additional information. Tayal et al [39] proposed a regularized GCN for short text classification that uses extra knowledge between text and labels to enhance short text information. Wang et al [40] modelled the short text dataset as a hierarchical heterogeneous graph consisting of three type graphs which introduce more semantic and syntactic information, and then dynamically learned to facilitate effective label propagation.…”

Section: Short Text Classification Based Gcnmentioning

confidence: 99%

Concept and dependencies enhanced graph convolutional networks for short text classification

Zhang,

Bai,

2023

IFS

View full text Add to dashboard Cite

Short text classification task is a special kind of text classification task in that the text to be classified is generally short, typically generating a sparse text representation that lacks rich semantic information. Given this shortcoming, scholars worldwide have explored improved short text classification methods based on deep learning. However, existing methods cannot effectively use concept knowledge and long-distance word dependencies. Therefore, based on graph neural networks from the perspective of text composition, we propose concept and dependencies enhanced graph convolutional networks for short text classification. First, the co-occurrence relationship between words is obtained by sliding window, the inclusion relationship between documents and words is obtained by TF-IDF, long-distance word dependencies is obtained by Stanford CoreNLP, and the association relationship between concepts in the concept graph with entities in the text is obtained through Microsoft Concept Graph. Then, a text graph is constructed for an entire text corpus based on the four relationships. Finally, the text graph is input into graph convolutional neural networks, and the category of each document node is predicted after two layers of convolution. Experimental results demonstrate that our proposed method overall best on multiple classical English text classification datasets.

show abstract

Section: Short Text Classification Based Gcnmentioning

confidence: 99%

Concept and Dependencies Enhanced Graph Convolutional Networks for Short Text Classification

Zhang

Ping

2022

Preprint

View full text Add to dashboard Cite

Short text classification task is a special kind of text classification task in that the text to be classified is generally short, typically generating a sparse text representation that lacks rich semantic information. Given this shortcoming, scholars worldwide have explored improved short text classification methods based on deep learning. However, existing methods cannot effectively use concept knowledge and long-distance word dependencies. Therefore, based on graph neural networks from the perspective of text composition, we propose concept and dependencies enhanced graph convolutional networks for short text classification. First, the co-occurrence relationship between words, the inclusion relationship between documents and words, long-distance word dependencies, and the association relationship between external concepts and words are defined. Then, a text graph is constructed for an entire text corpus based on the four relationships. Finally, the text graph is input into graph convolutional neural networks, and the category of each document node is predicted after two layers of convolution. Experimental results show that our proposed method overall best on multiple classical English text classification datasets.

show abstract

Regularized Graph Convolutional Networks for Short Text Classification

Cited by 10 publications

References 13 publications

Understanding Out-of-distribution: A Perspective of Data Dynamics

Understanding Out-of-distribution: A Perspective of Data Dynamics

Concept and dependencies enhanced graph convolutional networks for short text classification

Concept and Dependencies Enhanced Graph Convolutional Networks for Short Text Classification

Contact Info

Product

Resources

About