Words in Pairs Neural Networks for Text Classification

Wu, Yujia; Li, Jing; Song, Chengfang; Chang, Jun

doi:10.1049/cje.2020.03.005

Cited by 11 publications

(3 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Otherwise, we categorize it with the SVM classifier associated with the leaf node. SVM is a common two-classifier for sample classification by constructing hyperplane functions [20] . The specific steps are described as follows: a) Suppose a known training set:…”

Section: Y I X Y Imentioning

confidence: 99%

See 1 more Smart Citation

A Fine‐Grained Flash‐Memory Fragment Recognition Approach for Low‐Level Data Recovery

ZHANG

Hao

ZHANG

2022

Chinese J of Electronics

View full text Add to dashboard Cite

Section: Y I X Y Imentioning

confidence: 99%

“…At present, the standard machine learning algorithms for classification problems include naive Bayesian, support vector machine [ 20 ] , neural network [ 21 ] , decision tree [ 22 ] , k‐nearest neighbor, Adaboost and Bagging. Each machine learning algorithm has its unique characteristic [ 23 ] .…”

Section: The Proposed Approachmentioning

confidence: 99%

A Fine‐Grained Flash‐Memory Fragment Recognition Approach for Low‐Level Data Recovery

ZHANG

Hao

ZHANG

2022

Chinese J of Electronics

View full text Add to dashboard Cite

“…Text Classification is a classical problem in natur-al language processing (NLP), which is widely applied in sentiment analysis, medical diagnosis, semantic annotation, public opinion control and other fields. Many researchers study how to improve text classification performance via taking advantage of traditional machine learning methods [1]- [5]. At present, deep learning-based methods [6]- [8] have replaced traditional statistics-based methods in the field of NLP.…”

Section: Introductionmentioning

confidence: 99%

Rating Text Classification with Weighted Negative Supervision on Classifier Layer

Jun,

Longlong,

Fanfan

et al. 2023

Chinese J. Elect.

View full text Add to dashboard Cite

Bidirectional encoder representations from transformers (BERT) gives full play to the advantages of the attention mechanism, improves the performance of sentence representation, and provides a better choice for various natural language understanding (NLU) tasks. Many methods using BERT as the pre-trained model achieve state-of-the-art performance in almost various text classification scenarios. Among them, the multitask learning framework combining the negative supervision and the pre-trained model solves the issue of the model performance degradation that occurs as the semantic similarity of texts conflicts with the classification standards. The current model does not consider the degree of difference between labels, which leads to insufficient difference information learned by the model, and affects classification performance, especially in the rating classification tasks. On the basis of the multi-task learning model, this paper fully considers the degree of difference between labels, which is expressed by using weights to solve the above problems. We supervise negative samples on the classifier layer instead of the encoder layer, so that the classifier layer can also learn the difference information between the labels. Experimental results show that our model can not only performs well in 2-class and multi-class rating text classification tasks, but also performs well in different languages.

show abstract