A review of semi-supervised learning for text classification

Duarte, José Márcio; Berton, Lilian

doi:10.1007/s10462-023-10393-8

Cited by 23 publications

(10 citation statements)

References 181 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Semi-supervised learning is a learning approach that combines supervised and unsupervised learning ( 30 ). In the presence of a small amount of labeled data, semi-supervised models infer the structure and features of unlabeled data to perform classification and prediction tasks, thereby enhancing model performance with limited labeled data ( 31 ).…”

Section: Methodsmentioning

confidence: 99%

sscNOVA: a semi-supervised convolutional neural network for predicting functional regulatory variants in autoimmune diseases

Li,

Yu,

et al. 2024

Front. Immunol.

View full text Add to dashboard Cite

Genome-wide association studies (GWAS) have identified thousands of variants in the human genome with autoimmune diseases. However, identifying functional regulatory variants associated with autoimmune diseases remains challenging, largely because of insufficient experimental validation data. We adopt the concept of semi-supervised learning by combining labeled and unlabeled data to develop a deep learning-based algorithm framework, sscNOVA, to predict functional regulatory variants in autoimmune diseases and analyze the functional characteristics of these regulatory variants. Compared to traditional supervised learning methods, our approach leverages more variants’ data to explore the relationship between functional regulatory variants and autoimmune diseases. Based on the experimentally curated testing dataset and evaluation metrics, we find that sscNOVA outperforms other state-of-the-art methods. Furthermore, we illustrate that sscNOVA can help to improve the prioritization of functional regulatory variants from lead single-nucleotide polymorphisms and the proxy variants in autoimmune GWAS data.

show abstract

Section: Methodsmentioning

confidence: 99%

sscNOVA: a semi-supervised convolutional neural network for predicting functional regulatory variants in autoimmune diseases

Li,

Yu,

et al. 2024

Front. Immunol.

View full text Add to dashboard Cite

show abstract

“…In Att-BILSTM, the attention mechanism can assign a weight to each input position, allowing the model to better focus on key parts and use softmax classifiers to predict labels from the discrete set of category Y in sentence S . The classifier takes hidden state h * as input ( Duarte & Berton, 2023 ):…”

Section: Fundamentals Of Research Theorymentioning

confidence: 99%

Transfer learning-based English translation text classification in a multimedia network environment

Zheng

2024

PeerJ Computer Science

View full text Add to dashboard Cite

In recent years, with the rapid development of the Internet and multimedia technology, English translation text classification has played an important role in various industries. However, English translation remains a complex and difficult problem. Seeking an efficient and accurate English translation method has become an urgent problem to be solved. The study first elucidated the possibility of the development of transfer learning technology in multimedia environments, which was recognized. Then, previous research on this issue, as well as the Bidirectional Encoder Representations from Transformers (BERT) model, the attention mechanism and bidirectional long short-term memory (Att-BILSTM) model, and the transfer learning based cross domain model (TLCM) and their theoretical foundations, were comprehensively explained. Through the application of transfer learning in multimedia network technology, we deconstructed and integrated these methods. A new text classification technology fusion model, the BATCL transfer learning model, has been established. We analyzed its requirements and label classification methods, proposed a data preprocessing method, and completed experiments to analyze different influencing factors. The research results indicate that the classification system obtained from the study has a similar trend to the BERT model at the macro level, and the classification method proposed in this study can surpass the BERT model by up to 28%. The classification accuracy of the Att-BILSTM model improves over time, but it does not exceed the classification accuracy of the method proposed in this study. This study not only helps to improve the accuracy of English translation, but also enhances the efficiency of machine learning algorithms, providing a new approach for solving English translation problems.

show abstract

“…Machine learning-based methods use traditional machine learning algorithms to extract features from corpus samples with sentiment labels (Duarte and Berton, 2023). The current approaches can be classified into two categories: supervised (Naz et al, 2018;Rathor et al, 2018;Wang and Zhao, 2020) and semi-supervised (Fu et al, 2019;Wu et al, 2021;Palanivinayagam et al, 2023;Duan et al, 2020).…”

Section: Text Emotion Classificationmentioning

confidence: 99%

A hierarchical topic-guided BertCNN model for emotion classification from social network texts

Yang

Huang

Chang

2023

Preprint

View full text Add to dashboard Cite

Online public opinion management in the post-truth era is a comprehensive project, and emotion is the kernel of public opinion. Previous studies have begun to employ a combination of topic and semantic information from documents to improve the effectiveness of emotion classification. But efficiently extracting and combining this information remains a challenge. In addition, the widespread utilization of pre-trained models has given rise to many issues, including a large number of model parameters and extended training times. This paper presents a novel end-to-end hierarchical topic-guided BertCNN model(To-BertCNN) for emotion detection. The model utilizes a pruned hierarchical Bert model to extract semantic information at various levels within documents. Then a neural topic model is constructed to acquire topic embedding vectors. To-BertCNN finally employs a bi-directional attention fusion mechanism to fuse document vectors and topic features for emotion classification comprehensively. Experiments are conducted on three publicly available datasets, revealing that the classification performance of the To-BertCNN model surpasses that of the current state-of-the-art research, simultaneously enhancing the temporal efficiency of the model. The model fully adopts an end-to-end training approach, generating more coherent topic features and, consequently, higher interpretability.

show abstract

A review of semi-supervised learning for text classification

Cited by 23 publications

References 181 publications

sscNOVA: a semi-supervised convolutional neural network for predicting functional regulatory variants in autoimmune diseases

sscNOVA: a semi-supervised convolutional neural network for predicting functional regulatory variants in autoimmune diseases

Transfer learning-based English translation text classification in a multimedia network environment

A hierarchical topic-guided BertCNN model for emotion classification from social network texts

Contact Info

Product

Resources

About