Text Classification Framework Research Articles

GenerCTC: a general two-stage contrastive training framework for text classification

GenerCTC: a general two-stage contrastive training framework for text classification

GEML: a graph-enhanced pre-trained language model framework for text classification via mutual learning

GEML: a graph-enhanced pre-trained language model framework for text classification via mutual learning

An Analysis of Intelligent Turkish Text Classification Models for Routing Calls in Call Centers: A Case Study on the Republic of Turkiye Ministry of Trade Call Center

Call centers play a key role in the management of customer relationships in the modern business world. However, the growing demand for their services presents significant challenges, particularly in terms of staffing and handling increasing call volumes. This paper addresses these issues by presenting an AI-driven text classification framework tailored for the Republic of Turkiye Ministry of Trade Call Centre (MTCC), with the aim of automatically routing calls to relevant departments. Using a specific dataset of 20,000 phone call texts collected from the MTCC, the study employs TF-IDF, Word2Vec, and GloVe text vectorization techniques and applies various machine learning algorithms such as K-Nearest Neighbours, Naive Bayes, Support Vector Machines, Adaptive Boosting, Decision Tree and Random Forest for text classification. Through a comprehensive analysis, the study answers key research questions regarding optimal classifiers and vectorization methods. The proposed solution not only improves the efficiency of MTCC's call routing but also provides researchers with practical insights regarding Turkish text classification. The results indicate that a combination of the Random Forest classifier and Word2Vec text vectorization method is the optimal model that can manage to route calls in real-time.

Prompt-based learning framework for zero-shot cross-lingual text classification

Cross-lingual text classification is a challenging task that aims to train classifiers with data in one language, known as the source language, and apply the acquired knowledge to data in another language, referred to as the target language. Recent advancements in multilingual pre-trained language models (PLMs) have made significant progress in addressing cross-lingual issues, and the application of prompt-based learning has further improved task performance. However, these models still face challenges such as the gap between cross-lingual classification tasks and pre-training tasks of PLMs, as well as issues related to scarce resources and data noise, which hinder the full exploitation of the implicit knowledge in PLMs. In this paper, we propose a Prompt-based Cross-lingual Learning (PCL) framework that combines language-agnostic continuous prompt learning with self-learning process. Specifically, PCL framework leverages language-agnostic prompts and PLMs to achieve semantic transfer between source and target languages. To enhance the semantic relationship between prompts and category labels, a label attention module is introduced. Additionally, a set of self-training rules is proposed, which includes a scoring function. In a few-shot setting, noisy data is dynamically filtered through scoring and ranking of the data. During each training iteration, both the model and scoring function weights are updated, further improving the discrimination capability of the model. In summary, the proposed PCL framework builds upon cross-lingual prompt learning, effectively removing noisy data and applying it to zero-shot cross-lingual text classification, which is beneficial for engineering applications. The findings of this study have implications for prompt learning method. The PCL framework achieves state-of-the-art performance in cross-lingual text classification task, with a 14% performance improvement compared to basic soft prompt learning. This demonstrates its potential in addressing classification problems in resource-limited scenarios.

Research of news text classification method based on hierarchical semantics and prior correction

News text is an important branch of natural language processing. Compared to ordinary texts, news text has significant economic and scientific value. The characteristics of news text include structural hierarchy, diverse label categories, and limited high-quality annotation samples. Many machine learning and deep learning methods exist to analyze various forms of news text. However, due to label imbalance, hierarchical semantics, and confusing labels, current methods have limitations. Therefore, this paper proposes a news text classification framework based on hierarchical semantics and prior correction (HSPC). Firstly, data augmentation is used to enhance the diversity of the training set and adversarial learning is employed to improve the resistance of the model with its robustness. Then, a hierarchical feature extraction approach is employed to extract semantic features from different levels of news texts. Consequentially, a feature fusion method is designed to allow the model to focus on relevant hierarchical semantics for label classification. Finally, highly confusing label predictions are corrected to optimize the label prediction of the model and improve confidence. Multiple experiments are performed on four widely used public datasets. The experimental results indicate that HSPC achieves higher classification accuracy compared to other models. On the FCT, AGNews, THUCNews, and Ohsumed datasets, HSPC improves the accuracy by 1.03%, 1.38%, 2.55%, and 1.15%, respectively, compared to state-of-the-art methods. This validates the rationality and effectiveness of the designed mechanisms.

The COVID-19 Tweets Classification Based on Recurrent Neural Network

Due to its extensive use in both public and commercial contexts, sentiment analysis on Twitter has recently received much attention, particularly concerning tweets about COVID-19. Information about COVID-19 has been widely spread over social media, resulting in various views, opinions, and emotions about this pandemic, significantly impacting people's health. It is exceedingly challenging for the authorities to find these rumors on these public platforms manually. This paper proposes a framework for text classification using the RNN model and its updates, such as LSTM, BiLSTM, and GRU. This study aims to determine the best recurrent network model for handling cases of Twitter data classification. We utilized Twitter data relevant to COVID-19 and the lockdown with four classification classes (sad, joy, fear, and anger). In addition, this study aims to prove whether GloVe pre-trained word embedding can increase the accuracy of model predictions. The training and testing datasets were split into 80% and 20%, respectively. Therefore, in this experiment an early stopping technique was used with a limit of 15 epochs and a minimum delta of 0.01, meaning that training will be stopped if there is no improvement of 0.1% accuracy after 15 epochs. We used the f1-score average to measure the accuracy of the classification task results. The test results show that the BiLSTM model with GloVe word embedding yields the best f1-score compared to other models. Moreover, in all model testing, the f1-score value of the 'fear' class displays the highest accuracy compared to other classes.

Citespace-based Research on the Current Situation and Development Trend of the Art of “Sky Jumping” of the Zhuang on the Chinese-Vietnamese Border

Abstract China and Vietnam share both land and maritime borders, rendering the exchange and cooperation in ethnic arts along these frontiers crucial for their cultural evolution. This significance underscores the importance of organizing and analyzing the artistic expressions of the Zhuang people, particularly the “Tien Jumping” art form prevalent along the Sino-Vietnamese border. This study introduces an innovative method for text feature expansion utilizing Citespace, integrated with a deep learning-based text classification model, to establish a systematic framework for text classification within this cultural context. Furthermore, acknowledging the multidisciplinary nature of “Tien Jumping” art research, this paper develops a Citespace-based cross-collection system. This system harnesses a thematic network that amalgamates various disciplines to aggregate pertinent data efficiently. Empirical analysis validates the model’s robustness, evidencing an accuracy of 0.95, a recall of 0.87, and an F1 score of 0.91. The investigation into the current state and future trends of “Tien Jumping” research reveals a significant increase in publication volume, from 500 articles in 2013 to 1,108 in 2022— an increment of 608 articles. This growth highlights the strengthening focus on inheritance development, cultural preservation, and the artistry of the Zhuang people, with scores surpassing 7.5 in these emergent research areas. These findings affirm the effectiveness of the proposed methodologies in this study. The approach not only provides a rigorous analysis but also forecasts the trajectory of “Tien Jumping” art research along the Sino-Vietnamese border, offering a scientific foundation for future scholarly inquiries.

Convolutional Neural Network Algorithm–Based Novel Automatic Text Classification Framework for Construction Accident Reports

Convolutional Neural Network Algorithm–Based Novel Automatic Text Classification Framework for Construction Accident Reports

ConKgPrompt: Contrastive Sample Method Based on Knowledge-Guided Prompt Learning for Text Classification

Text classification aims to classify text according to pre-defined categories. Despite the success of existing methods based on the fine-tuning paradigm, there is a significant gap between fine-tuning and pre-training. Currently, prompt learning methods can bring state of the art (SOTA) performance to pre-trained language models (PLMs) in text classification and transform a classification problem into a masked language modeling problem. The crucial step of prompt learning is to construct a map between original labels and the label extension words. However, most mapping construction methods consider only labels themselves; relying solely on a label is not sufficient to achieve accurate prediction of mask tokens, especially in classification tasks where semantic features and label words are highly interrelated. Therefore, the accurate prediction of mask tokens requires one to consider additional factors beyond just label words. To this end, we propose a contrastive sample method based on knowledge-guided prompt learning framework (ConKgPrompt) for text classification. Specifically, this framework utilizes external knowledge bases (KBs) to expand the label vocabulary of verbalizers at multiple granularities. In the contrastive sample module, we incorporate supervised contrastive learning to make representations more expressive. Our approach was validated on four benchmark datasets, and extensive experimental results and analysis demonstrated the effectiveness of each module of the ConKgPrompt method.

Leveraging the meta-embedding for text classification in a resource-constrained language

This paper proposes an intelligent text classification framework for a resource-constrained language like Bengali, which is considered a challenging task due to the lack of standard corpora, appropriate hyper-parameter tuning method, and pre-trained language-specific embedding. The proposed framework comprises an average meta-embedding feature fusion module and a convolutions neural network module called AVG-M+CNN. This work also proposes an algorithm, i.e., automatic hyperparameter tuning and selection, for enhancing the performance of the AVG-M+CNN technique. All meta-embedding models are evaluated using the intrinsic, e.g., semantic, syntactic, relatedness word similarity, analogy tasks and extrinsic evaluators. The intrinsic evaluator evaluates 200 Bengali semantic, syntactic and relatedness word pairs. Spearman (ρˆ), Pearson (rˆ) and cosine similarity correlations are used to evaluate 18 individual embedding and 9 meta-embedding models. The 3COSADD and 3COSMUL evaluators evaluate the 300 analogy tasks. The extrinsic evaluator evaluates a total of 156 classification models on four corpora: BARD, IndicNLP, Prothom-Alo and BTCC11 (a newly developed corpus having eleven distinct categories). Among these, the AVG-M+CNN model achieves the highest accuracy regarding four Bengali corpora: 95.92±.001% for BARD, 93.10±.001% for Prothom-Alo, 90.07±.001% for BTCC11 and 87.44±.001% for IndicNLP, respectively.

Hierarchical graph-based text classification framework with contextual node embedding and BERT-based dynamic fusion

We propose a novel hierarchical graph-based text classification framework that leverages the power of contextual node embedding and BERT-based dynamic fusion to capture the complex relationships between the nodes in the hierarchical graph and generate a more accurate classification of text. The framework consists of seven stages: Linguistic Feature Extraction, Hierarchical Node Construction with Domain-Specific Knowledge, Contextual Node Embedding, Multi-Level Graph Learning, Dynamic Text Sequential Feature Interaction, Attention-Based Graph Learning, and Dynamic Fusion with BERT. The first stage, Linguistic Feature Extraction, extracts the linguistic features of the text, including part-of-speech tags, dependency parsing, and named entities. The second stage constructs a hierarchical graph based on the domain-specific knowledge, which is used to capture the relationships between nodes in the graph. The third stage, Contextual Node Embedding, generates a vector representation for each node in the hierarchical graph, which captures its local context information, linguistic features, and domain-specific knowledge. The fourth stage, Multi-Level Graph Learning, uses a graph convolutional neural network to learn the hierarchical structure of the graph and extract the features of the nodes in the graph. The fifth stage, Dynamic Text Sequential Feature Interaction, captures the sequential information of the text and generates dynamic features for each node. The sixth stage, Attention-Based Graph earning, uses an attention mechanism to capture the important features of the nodes in the graph. Finally, the seventh stage, Dynamic Fusion with BERT, combines the output from the previous stages with the output from a pre-trained BERT model to obtain the final integrated vector representation of the text. This approach leverages the strengths of both the proposed framework and BERT, allowing for better performance on the classification task. The proposed framework was evaluated on several benchmark datasets and compared to state-of-the-art methods, demonstrating significant improvements in classification accuracy.

Text classification framework for short text based on TFIDF-FastText

Text classification framework for short text based on TFIDF-FastText

A multi-semantic passing framework for semi-supervised long text classification

A multi-semantic passing framework for semi-supervised long text classification

A Submodular Optimization Framework for Imbalanced Text Classification With Data Augmentation

In the domain of text classification, imbalanced datasets are a common occurrence. The skewed distribution of the labels of these datasets poses a great challenge to the performance of text classifiers. One popular way to mitigate this challenge is to augment underwhelmingly represented labels with synthesized items. The synthesized items are generated by data augmentation methods that can typically generate an unbounded number of items. To select the synthesized items that maximize the performance of text classifiers, we introduce a novel method that selects items that jointly maximize the likelihood of the items belonging to their respective labels and the diversity of the selected items. Our proposed method formulates the joint maximization as a monotone submodular objective function, whose solution can be approximated by a tractable and efficient greedy algorithm. We evaluated our method on multiple real-world datasets with different data augmentation techniques and text classifiers and compared results with several baselines. The experimental results demonstrate the effectiveness and efficiency of the proposed method.

TextDC: Exploring Multidimensional Text Detection via a New Benchmark and Solution

Text detection has been significantly boosted by the development of deep neural networks but most existing methods focus on a single kind of text instance (i.e., overlaid text, layered text, scene text). In this paper, we expand the text detection task from a single dimension to multiple dimensions, thus providing multi-type text descriptions for the scene and content analysis of videos. Specifically, we establish a new task to detect and classify text instances simultaneously, termed TextDC. As far as we know, existing benchmarks cannot meet the requirements of the proposed task. To this end, we collect a large-scale text detection and classification dataset, named Text3C, which is annotated using multilingual labels, location information, and text categories. Together with the collected dataset, we introduce a multi-stage and strict evaluation metric, which penalizes detection approaches for missing text instances, false positive detection, inaccurate location boxes, and error text categories, developing a new benchmark for the proposed TextDC task. In addition, we extend several state-of-the-art detectors by modifying the prediction head to solve the new task. Then, a generalized text detection and classification framework is designed and formulated. Extensive experiments using the updated methods are conducted on the established benchmark to verify the solvability of the proposed task, the challenges of the dataset, and the effectiveness of the solution.

Supervised term-category feature weighting for improved text classification

Text classification is a central task in Natural Language Processing (NLP) that aims at categorizing text documents into predefined classes or categories. It requires appropriate features to describe the contents and meaning of text documents, and map them with their target categories. Existing text feature representations rely on a weighted representation of the document terms. Hence, choosing a suitable method for term weighting is of major importance and can help increase the effectiveness of the classification task. In this study, we provide a novel text classification framework for Category-based Feature Engineering titled CFE. It consists of a supervised weighting scheme defined based on a variant of the TF-ICF (Term Frequency-Inverse Category Frequency) model, embedded into three new lean classification approaches: (i) IterativeAdditive (flat), (ii) GradientDescentANN (1-layered), and (iii) FeedForwardANN (2-layered). The IterativeAdditive approach augments each document representation with a set of synthetic features inferred from TF-ICF category representations. It builds a term-category TF-ICF matrix using an iterative and additive algorithm that produces category vector representations and updates until reaching convergence. GradientDescentANN replaces the iterative additive process mentioned previously by computing the term-category matrix using a gradient descent ANN model. Training the ANN using the gradient descent algorithm allows updating the term-category matrix until reaching convergence. FeedForwardANN uses a feed-forward ANN model to transform document representations into the category vector space. The transformed document vectors are then compared with the target category vectors, and are associated with the most similar categories. We have implemented CFE including its three classification approaches, and we have conducted a large battery of tests to evaluate their performance. Experimental results on five benchmark datasets show that our lean approaches mostly improve text classification accuracy while requiring significantly less computation time compared with their deep model alternatives.

Investigating Prompt Learning for Chinese Few-Shot Text Classification with Pre-Trained Language Models

Text classification aims to assign predefined labels to unlabeled sentences, which tend to struggle in real-world applications when only a few annotated samples are available. Previous works generally focus on using the paradigm of meta-learning to overcome the classification difficulties brought by insufficient data, where a set of auxiliary tasks is given. Accordingly, prompt-based approaches are proposed to deal with the low-resource issue. However, existing prompt-based methods mainly focus on English tasks, which generally apply English pretrained language models that can not directly adapt to Chinese tasks due to structural and grammatical differences. Thus, we propose a prompt-based Chinese text classification framework that uses generated natural language sequences as hints, which can alleviate the classification bottleneck well in low-resource scenarios. In detail, we first design a prompt-based fine-tuning together with a novel pipeline for automating prompt generation in Chinese. Then, we propose a refined strategy for dynamically and selectively incorporating demonstrations into each context. We present a systematic evaluation for analyzing few-shot performance on a wide range of Chinese text classification tasks. Our approach makes few assumptions about task resources and expertise and therefore constitutes a powerful, task-independent approach for few-shot learning.

A sequence labeling framework for extracting drug-protein relations from biomedical literature.

https://github.com/lingluodlut/BioCreativeVII_DrugProt.

Contrast-Enhanced Semi-supervised Text Classification with Few Labels

Traditional text classification requires thousands of annotated data or an additional Neural Machine Translation (NMT) system, which are expensive to obtain in real applications. This paper presents a Contrast-Enhanced Semi-supervised Text Classification (CEST) framework under label-limited settings without incorporating any NMT systems. We propose a certainty-driven sample selection method and a contrast-enhanced similarity graph to utilize data more efficiently in self-training, alleviating the annotation-starving problem. The graph imposes a smoothness constraint on the unlabeled data to improve the coherence and the accuracy of pseudo-labels. Moreover, CEST formulates the training as a “learning from noisy labels” problem and performs the optimization accordingly. A salient feature of this formulation is the explicit suppression of the severe error propagation problem in conventional semi-supervised learning. With solely 30 labeled data per class for both training and validation dataset, CEST outperforms the previous state-of-the-art algorithms by 2.11% accuracy and only falls within the 3.04% accuracy range of fully-supervised pre-training language model fine-tuning on thousands of labeled data.

TkTC: A framework for top-k text classification of multimedia computing in wireless networks

TkTC: A framework for top-k text classification of multimedia computing in wireless networks