Few-Shot Charge Prediction with Data Augmentation and Feature Augmentation

The task of charge prediction is to predict the charge based on the fact description. Existing methods have a good effect on the prediction of high-frequency charges, but the prediction of low-frequency charges is still a challenge. Moreover, there exist some confusing charges that have relatively s...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Peipeng Wang, Xiuguo Zhang, Zhiying Cao
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	charge prediction Mixup graph convolutional network loss function Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
Acceso en línea:	https://doaj.org/article/d3be2c4d202a4a358d6c3013f0a1f9e4
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:d3be2c4d202a4a358d6c3013f0a1f9e4
record_format	dspace
spelling	oai:doaj.org-article:d3be2c4d202a4a358d6c3013f0a1f9e42021-11-25T16:38:33ZFew-Shot Charge Prediction with Data Augmentation and Feature Augmentation10.3390/app1122108112076-3417https://doaj.org/article/d3be2c4d202a4a358d6c3013f0a1f9e42021-11-01T00:00:00Zhttps://www.mdpi.com/2076-3417/11/22/10811https://doaj.org/toc/2076-3417The task of charge prediction is to predict the charge based on the fact description. Existing methods have a good effect on the prediction of high-frequency charges, but the prediction of low-frequency charges is still a challenge. Moreover, there exist some confusing charges that have relatively similar fact descriptions, which can be easily misjudged. Therefore, we propose a model with data augmentation and feature augmentation for few-shot charge prediction. Specifically, the model takes the text description as the input and uses the Mixup method to generate virtual samples for data augmentation. Then, the charge information heterogeneous graph is introduced, and a novel graph convolutional network is designed to extract distinguishability features for feature augmentation. A feature fusion network is used to effectively integrate the charge graph knowledge into the fact to learn semantic-enhanced fact representation. Finally, the semantic-enhanced fact representation is used to predict the charge. In addition, based on the distribution of each charge, a category prior loss function is designed to increase the contribution of low-frequency charges to the model optimization. The experimental results on real-work datasets prove the effectiveness and robustness of the proposed model.Peipeng WangXiuguo ZhangZhiying CaoMDPI AGarticlecharge predictionMixupgraph convolutional networkloss functionTechnologyTEngineering (General). Civil engineering (General)TA1-2040Biology (General)QH301-705.5PhysicsQC1-999ChemistryQD1-999ENApplied Sciences, Vol 11, Iss 10811, p 10811 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	charge prediction Mixup graph convolutional network loss function Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
spellingShingle	charge prediction Mixup graph convolutional network loss function Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999 Peipeng Wang Xiuguo Zhang Zhiying Cao Few-Shot Charge Prediction with Data Augmentation and Feature Augmentation
description	The task of charge prediction is to predict the charge based on the fact description. Existing methods have a good effect on the prediction of high-frequency charges, but the prediction of low-frequency charges is still a challenge. Moreover, there exist some confusing charges that have relatively similar fact descriptions, which can be easily misjudged. Therefore, we propose a model with data augmentation and feature augmentation for few-shot charge prediction. Specifically, the model takes the text description as the input and uses the Mixup method to generate virtual samples for data augmentation. Then, the charge information heterogeneous graph is introduced, and a novel graph convolutional network is designed to extract distinguishability features for feature augmentation. A feature fusion network is used to effectively integrate the charge graph knowledge into the fact to learn semantic-enhanced fact representation. Finally, the semantic-enhanced fact representation is used to predict the charge. In addition, based on the distribution of each charge, a category prior loss function is designed to increase the contribution of low-frequency charges to the model optimization. The experimental results on real-work datasets prove the effectiveness and robustness of the proposed model.
format	article
author	Peipeng Wang Xiuguo Zhang Zhiying Cao
author_facet	Peipeng Wang Xiuguo Zhang Zhiying Cao
author_sort	Peipeng Wang
title	Few-Shot Charge Prediction with Data Augmentation and Feature Augmentation
title_short	Few-Shot Charge Prediction with Data Augmentation and Feature Augmentation
title_full	Few-Shot Charge Prediction with Data Augmentation and Feature Augmentation
title_fullStr	Few-Shot Charge Prediction with Data Augmentation and Feature Augmentation
title_full_unstemmed	Few-Shot Charge Prediction with Data Augmentation and Feature Augmentation
title_sort	few-shot charge prediction with data augmentation and feature augmentation
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/d3be2c4d202a4a358d6c3013f0a1f9e4
work_keys_str_mv	AT peipengwang fewshotchargepredictionwithdataaugmentationandfeatureaugmentation AT xiuguozhang fewshotchargepredictionwithdataaugmentationandfeatureaugmentation AT zhiyingcao fewshotchargepredictionwithdataaugmentationandfeatureaugmentation
_version_	1718413105196695552

Few-Shot Charge Prediction with Data Augmentation and Feature Augmentation

Ejemplares similares