An adaptive convolution with label embedding for text classification

Tan, Changgeng; Ren, Yuan; Wang, Chen

doi:10.1007/s10489-021-02702-x

Cited by 6 publications

(2 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Traditional machine learning methods require intricate feature engineering, such as sparse lexical features (e.g., bag-of-words models, N-grams) [9], and depend on large amounts of labeled data. Currently, most of the research on text classification has shifted towards deep learning methods, including convolutional neural networks (CNN) [10][11][12] and recurrent neural networks based on long short-term memory (LSTM) [13]. These models utilize sliding windows to extract syntactic and semantic information from N-grams, capturing the hidden information of each token through autoregressive modeling.…”

Section: Introductionmentioning

confidence: 99%

Innovative Label Embedding for Food Safety Comment Classification: Fusion of Self-Semantic and Self-Knowledge Features

Zhang,

Liu,

Feng

et al. 2024

HighTech. Innov. J.

View full text Add to dashboard Cite

Food safety comment classification represents a specialized task within the realm of text classification. The objective is to efficiently identify a large volume of food safety comments, aiding relevant authorities in timely food analysis and safety alerts. Traditional methods typically employ one-hot encoding for label processing. However, in real-world situations, classified labels often convey valuable semantic information and guidance. This paper introduces an innovative approach to enhance the classification performance of food safety comments by embedding label information. Initially, we extracted generic sentiment pivot words from various classification labels as label description information. Subsequently, we employ a joint embedding approach to integrate this label description information into the text. This process will pool the expressions of the pivot word into the corresponding sentiment labels in the known domains after averaging to get the embedded expression. This aims to acquire highly detailed self-semantic feature vectors and self-knowledge feature vectors that are integrated with labeled descriptive information. Then, feed the semantic representation of comments and the word-embedded representation of labeled description information into a time-step-based multilayer Bi-LSTM and a step-based multilayer CNN, respectively. Ultimately, we concatenate these two feature vectors to facilitate matching, thereby fusing the self-semantic and self-knowledge features of labeled description information to train a classification model for food safety comments. Experimental results on the food safety comment dataset showcase a noteworthy improvement of 1.74% and 1.27% in Macro_Precision and Macro_F1 metrics, respectively, compared to BERT, BERT-RNN, and BERT-CNN. Through extensive ablation experiments and additional studies, our method effectively embeds labeling information, demonstrating a clear advantage over traditional methods in the task of classifying food safety comments. Doi: 10.28991/HIJ-2024-05-01-013 Full Text: PDF

show abstract

Section: Introductionmentioning

confidence: 99%

Innovative Label Embedding for Food Safety Comment Classification: Fusion of Self-Semantic and Self-Knowledge Features

Zhang,

Liu,

Feng

et al. 2024

HighTech. Innov. J.

View full text Add to dashboard Cite

show abstract

“…With the support of massive subjective-opinion data and the development of artificial neural networks (ANNs), various neural networks, including recurrent neural networks (RNNs), memory networks, and convolutional neural networks (CNNs), have been widely applied in this field. In particular, following the remarkable success of CNNs across numerous fields, including computer vision, speech recognition, and signal processing, they have also been successfully applied to NLP tasks [1][2][3][4].…”

Section: Introductionmentioning

confidence: 99%

Position-Wise Gated Res2Net-Based Convolutional Network with Selective Fusing for Sentiment Analysis

Zhou

Zeng

Zou

et al. 2023

Entropy

View full text Add to dashboard Cite

Sentiment analysis (SA) is an important task in natural language processing in which convolutional neural networks (CNNs) have been successfully applied. However, most existing CNNs can only extract predefined, fixed-scale sentiment features and cannot synthesize flexible, multi-scale sentiment features. Moreover, these models’ convolutional and pooling layers gradually lose local detailed information. In this study, a new CNN model based on residual network technology and attention mechanisms is proposed. This model exploits more abundant multi-scale sentiment features and addresses the loss of locally detailed information to enhance the accuracy of sentiment classification. It is primarily composed of a position-wise gated Res2Net (PG-Res2Net) module and a selective fusing module. The PG-Res2Net module can adaptively learn multi-scale sentiment features over a large range using multi-way convolution, residual-like connections, and position-wise gates. The selective fusing module is developed to fully reuse and selectively fuse these features for prediction. The proposed model was evaluated using five baseline datasets. The experimental results demonstrate that the proposed model surpassed the other models in performance. In the best case, the model outperforms the other models by up to 1.2%. Ablation studies and visualizations further revealed the model’s ability to extract and fuse multi-scale sentiment features.

show abstract

A Lightweight Text Classification Model Based on Label Embedding Attentive Mechanism

Li,

Chen,

et al. 2023

Communications in Computer and Information Science

View full text Add to dashboard Cite

An adaptive convolution with label embedding for text classification

Cited by 6 publications

References 19 publications

Innovative Label Embedding for Food Safety Comment Classification: Fusion of Self-Semantic and Self-Knowledge Features

Innovative Label Embedding for Food Safety Comment Classification: Fusion of Self-Semantic and Self-Knowledge Features

Position-Wise Gated Res2Net-Based Convolutional Network with Selective Fusing for Sentiment Analysis

A Lightweight Text Classification Model Based on Label Embedding Attentive Mechanism

Contact Info

Product

Resources

About