Filters








9 Hits in 3.9 sec

VGCN-BERT: Augmenting BERT with Graph Embedding for Text Classification [article]

Zhibin Lu, Pan Du, Jian-Yun Nie
2020 arXiv   pre-print
In this paper, we propose VGCN-BERT model which combines the capability of BERT with a Vocabulary Graph Convolutional Network (VGCN).  ...  Much progress has been made recently on text classification with methods based on neural networks.  ...  The final classification results by BERT is 0 (negative) while the true label is 1 (positive). Vanilla-VGCN-BERT concatenates graph embedding with BERT without interaction between them.  ... 
arXiv:2004.05707v1 fatcat:s3jtioywffcj3itewjhn2rncw4

VGCN-BERT: Augmenting BERT with Graph Embedding for Text Classification [chapter]

Zhibin Lu, Pan Du, Jian-Yun Nie
2020 Lecture Notes in Computer Science  
In this paper, we propose VGCN-BERT model which combines the capability of BERT with a Vocabulary Graph Convolutional Network (VGCN).  ...  Much progress has been made recently on text classification with methods based on neural networks.  ...  The final classification results by BERT is 0 (negative) while the true label is 1 (positive). Vanilla-VGCN-BERT concatenates graph embedding with BERT without interaction between them.  ... 
doi:10.1007/978-3-030-45439-5_25 fatcat:6kwtm2vov5dpzbfjfpspri2h5i

VGCN-BERT: Augmenting BERT with Graph Embedding for Text Classification

Zhibin Lu, Pan Du, Jian-Yun Nie
2020
In this paper, we propose VGCN-BERT model which combines the capability of BERT with a Vocabulary Graph Convolutional Network (VGCN).  ...  Much progress has been made recently on text classification with methods based on neural networks.  ...  The final classification results by BERT is 0 (negative) while the true label is 1 (positive). Vanilla-VGCN-BERT concatenates graph embedding with BERT without interaction between them.  ... 
doi:10.48550/arxiv.2004.05707 fatcat:oz6ylkgkgrcflctlppgk3mulb4

Multilingual Epidemiological Text Classification: A Comparative Study

Stephen Mutuvi, Emanuela Boros, Antoine Doucet, Gaël Lejeune, Adam Jatowt, Moses Odeo
2020 Zenodo  
Multilingual text classification models tend to perform differently across different languages (low- or high-resource), more particularly when the dataset is highly imbalanced, which is the case for epidemiological  ...  In this paper, we approach the multilingual text classification task in the context of the epidemiological field.  ...  We also test a graph convolutional networks (GCN) based-approach that augments BERT with graph embeddings (VGCN+BERT) (Lu and Nie, 2019) .  ... 
doi:10.5281/zenodo.4680667 fatcat:g77axjkehfb7hebydkgzer2qta

I-AID: Identifying Actionable Information from Disaster-related Tweets [article]

Hamada M. Zahera, Rricha Jalota, Mohamed A. Sherif, Axel N. Ngomo
2021 arXiv   pre-print
I-AID incorporates three main components: i) a BERT-based encoder to capture the semantics of a tweet and represent as a low-dimensional vector, ii) a graph attention network (GAT) to apprehend correlations  ...  The current version of VGCN-BERT cannot be directly used for multi-label classification.  ...  [20] leverage the combination between BERT embeddings and GAT to learn feature representation for text in a multi-label classification task.  ... 
arXiv:2008.13544v2 fatcat:6yjmtfq4tfec5pf6uly2cpgzoe

Multilingual Epidemiological Text Classification: A Comparative Study

Stephen Mutuvi, Emanuela Boros, Antoine Doucet, Gael Lejeune, Adam Jatowt, Moses Odeo
2021 Zenodo  
Multilingual text classification models tend to perform differently across different languages (low- or high-resourced), more particularly when the dataset is highly imbalanced, which is the case for epidemiological  ...  In this paper, we approach the multilingual text classification task in the context of the epidemiological field.  ...  We also test a graph convolutional networks (GCN) based-approach that augments BERT with graph embeddings (Lu and Nie, 2019) .  ... 
doi:10.5281/zenodo.4476039 fatcat:cnudnstepzbvbgb3g6yy2uwrji

An Analysis of a BERT Deep Learning Strategy on a Technology Assisted Review Task

Alexandros Ioannidis
2021 Zenodo  
Given the recent advances in DL (Deep Learning) methods applied to IR (Information Retrieval) tasks, I propose a DL document classification approach with BERT (Bidirectional Encoder Representations from  ...  Transformers) or PubMedBERT embeddings and a DL similarity search path using SBERT (Sentence-BERT) embeddings to reduce physicians' tasks of screening and classifying immense amounts of documents to answer  ...  [16] , Augmenting it with Graph Embedding (VGCN-BERT) for Text Classification by Lu et al. [18] and Alleviating Legal News Monitoring by Sanchez et al. [19] .  ... 
doi:10.5281/zenodo.4697891 fatcat:w4ks77xkdjfupi47vhsskoh6n4

MG-BERT: Multi-Graph Augmented BERT for Masked Language Modeling

Parishad BehnamGhader, Hossein Zakerinia, Mahdieh Soleymani Baghshah
2021 Proceedings of the Fifteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-15)   unpublished
In this paper, we first introduce a multi-graph including different types of relations between words. Then, we propose Multi-Graph augmented BERT (MG-BERT) model that is based on BERT.  ...  MG-BERT embeds tokens while taking advantage of a static multi-graph containing global word co-occurrences in the text corpus beside global real-world facts about words in knowledge graphs.  ...  For instance, Text GCN (Yao et al., 2018) applies Graph Convolutional Network (GCN) to the task of text classification.  ... 
doi:10.18653/v1/2021.textgraphs-1.12 fatcat:l5agfjdl5zek7eaofxcd6xsyz4

Multilingual Epidemiological Text Classification: A Comparative Study

Stephen Mutuvi, Emanuela Boros, Antoine Doucet, Adam Jatowt, Gaël Lejeune, Moses Odeo
2020 Proceedings of the 28th International Conference on Computational Linguistics   unpublished
Multilingual text classification models tend to perform differently across different languages (low-or high-resource), more particularly when the dataset is highly imbalanced, which is the case for epidemiological  ...  In this paper, we approach the multilingual text classification task in the context of the epidemiological field.  ...  We also test a graph convolutional networks (GCN) based-approach that augments BERT with graph embeddings (VGCN+BERT) (Lu and Nie, 2019) .  ... 
doi:10.18653/v1/2020.coling-main.543 fatcat:yqdr2bnjm5bk3lcnmkfxtpyxae