K-AID

Even if recent Transformer-based architectures, such as BERT, achieved impressive results in semantic processing tasks, their fine-tuning stage still requires large scale training resources. Usually, Data Augmentation (DA) techniques can help to deal with low resource settings. In Text Classification tasks, the objective of DA is the generation of well-formed sentences that i) represent the desired task category and ii) are novel with respect to existing sentences. In this paper, we propose a neural approach to automatically learn to generate new examples using a pre-trained sequence-to-sequence model. We first learn a task-oriented similarity function that we use to pair similar examples. Then, we use these example pairs to train a model to generate examples. Experiments in low resource settings show that augmenting the training material with the proposed strategy systematically improves the results on text classification and natural language inference tasks by up to 10% accuracy, outperforming existing DA approaches.

How to use advanced deep learning technology to build an effective and powerful text classification model, extract text semantic attributes and achieve good classification results on large-scale test datasets has always been the main problem and severe challenge of text classification tasks. The purpose of this paper is to study the application optimization of NLP system in text semantics and text classification based on deep learning technology. A WC-GCN classification algorithm combining GCN and Attention mechanism is proposed. The related tasks of text classification are discussed, including three typical text classification tasks, including sentiment analysis, topic analysis, and news classification. The algorithm model proposed in this paper is verified from the experimental point of view. Compared with other deep learning-based text classification methods, the proposed algorithm model performs better on the public datasets of three text classification tasks. The news text also achieved a high accuracy rate.

Large language models (LLMs) have recently made significant advances, excelling in tasks like question answering, summarization, and machine translation. However, their enormous size and hardware requirements make them less accessible to many in the machine learning community. To address this, techniques such as quantization, prefix tuning, weak supervision, low-rank adaptation, and prompting have been developed to customize these models for specific applications. While these methods have mainly improved text generation, their implications for the text classification task are not thoroughly studied. Our research intends to bridge this gap by investigating how variations like model size, pre-training objectives, quantization, low-rank adaptation, prompting, and various hyperparameters influence text classification tasks. Our overall conclusions show the following: 1—even with synthetic labels, fine-tuning works better than prompting techniques, and increasing model size does not always improve classification performance; 2—discriminatively trained models generally perform better than generatively pre-trained models; and 3—fine-tuning models at 16-bit precision works much better than using 8-bit or 4-bit models, but the performance drop from 8-bit to 4-bit is smaller than from 16-bit to 8-bit. In another scale of our study, we conducted experiments with different settings for low-rank adaptation (LoRA) and quantization, finding that increasing LoRA dropout negatively affects classification performance. We did not find a clear link between the LoRA attention dimension (rank) and performance, observing only small differences between standard LoRA and its variants like rank-stabilized LoRA and weight-decomposed LoRA. Additional observations to support model setup for classification tasks are presented in our analyses.

Text classification is one of the fundamental tasks in natural language processing. Recently, deep neural networks have achieved promising performance in the text classification task compared to shallow models. Despite of the significance of deep models, they ignore the fine-grained (matching signals between words and classes) classification clues since their classifications mainly rely on the text-level representations. To address this problem, we introduce the interaction mechanism to incorporate word-level matching signals into the text classification task. In particular, we design a novel framework, EXplicit interAction Model (dubbed as EXAM), equipped with the interaction mechanism. We justified the proposed approach on several benchmark datasets including both multilabel and multi-class text classification tasks. Extensive experimental results demonstrate the superiority of the proposed method. As a byproduct, we have released the codes and parameter settings to facilitate other researches.

In real-world scenarios, a text classification task often begins with a cold start, when labeled data is scarce. In such cases, the common practice of fine-tuning pre-trained models, such as BERT, for a target classification task, is prone to produce poor performance. We suggest a method to boost the performance of such models by adding an intermediate unsupervised classification task, between the pre-training and fine-tuning phases. As such an intermediate task, we perform clustering and train the pre-trained model on predicting the cluster labels. We test this hypothesis on various data sets, and show that this additional classification phase can significantly improve performance, mainly for topical classification tasks, when the number of labeled instances available for fine-tuning is only a couple of dozen to a few hundred.

Deep learning--based models have surpassed classical machine learning--based approaches in various text classification tasks, including sentiment analysis, news categorization, question answering, and natural language inference. In this article, we provide a comprehensive review of more than 150 deep learning--based models for text classification developed in recent years, and we discuss their technical contributions, similarities, and strengths. We also provide a summary of more than 40 popular datasets widely used for text classification. Finally, we provide a quantitative analysis of the performance of different deep learning models on popular benchmarks, and we discuss future research directions.

This paper describes a new approach for estimating term weights in a text classification task. The approach uses term co-occurrence as a measure of dependency between word features. A random walk model is applied on a graph encoding words and co-occurrence dependencies, resulting in scores that represent a quantification of how a particular word feature contributes to a given context. We argue that by modeling feature weights using these scores, as opposed to the traditional frequency-based scores, we can achieve better results in a text classification task. Experiments performed on four standard classification datasets show that the new random-walk based approach outperforms the traditional term frequency approach to feature weighting.

For many text classification tasks, there is a major problem posed by the lack of labeled data in a target domain. Although classifiers for a target domain can be trained on labeled text data from a related source domain, the accuracy of such classifiers is usually lower in the cross-domain setting. Recently, string kernels have obtained state-of-the-art results in various text classification tasks such as native language identification or automatic essay scoring. Moreover, classifiers based on string kernels have been found to be robust to the distribution gap between different domains. In this paper, we formally describe an algorithm composed of two simple yet effective transductive learning approaches to further improve the results of string kernels in cross-domain settings. By adapting string kernels to the test set without using the ground-truth test labels, we report significantly better accuracy rates in cross-domain English polarity classification.

Text classification is a fundamental task in many applications such as topic labeling, sentiment analysis, and spam detection. The text syntactic relationship and word sequence are important and useful for text classification. How to model and incorporate them to improve performance is one key challenge. Inspired by human behavior in understanding text. In this paper, we combine the syntactic relationship, sequence structure, and semantics for text representation, and propose an attention-enhanced capsule network-based text classification model. Specifically, we use graph convolutional neural networks to encode syntactic dependency trees, build multi-head attention to encode dependencies relationship in text sequence, merge with semantic information by capsule network at last. Extensive experiments on five datasets demonstrate that our approach can effectively improve the performance of text classification compared with state-of-the-art methods. The result also shows capsule network, graph convolutional neural network, and multi-headed attention has integration effects on text classification tasks.

Word embeddings have been successfully exploited in systems for NLP tasks, such as parsing and text classification. It is intuitive that word embeddings created from a larger corpus would provide a better coverage of vocabulary. Meanwhile, word embeddings trained on a corpus related to the given task or target domain would more effectively represent the semantics of terms. However, in some emerging domains (e.g. bio-surveillance using social media data), it may be difficult to find a domain corpus that is large enough for creating effective word embeddings. To deal with this problem, we propose novel approaches that use both word embeddings created from generic and target domain corpora. Our experimental results on sentence classification tasks show that our approaches significantly improve the performance of an existing convolutional neural network that achieved state-of-the-art performances on several text classification tasks.

Labelling multiple training examples for text classification models is usually time‐consuming and complex. Data augmentation can be used to automatically expand the dataset by transforming the original data. However, it may cause semantic changes without modifying the labels, which reduces the effectiveness of the classifiers. In this paper, we propose a data‐augmentation method called the virtual word insertion technique, which generates new sentences by randomly inserting virtual words into existing sentences. Two methods are used to achieve virtual word embedding: unweighted average and weighted average. Furthermore, a new concept of weight is proposed: the class deviation factor, which demonstrates the correlation between words and classes. Based on this new concept, different weights are assigned to words of different classes. Experiments are conducted on five different classification tasks. Ablation experiments are also performed to explore the effects of random operation and number of augmented sentences for classification results. The results of these experiments show that our method improves the classification performance and outperforms two other contrasting data‐augmentation methods in automatically augmenting the dataset. Compared to raw datasets, the average accuracy improvement of our method is 3.5% for a small‐scale dataset and 1% for a large‐scale dataset.

As one of the core tasks of natural language processing technology, text classification methods general-ly face the problems of insufficient global semantic capture and limited feature focusing ability when processing long texts or complex semantics. To address this issue, a deep learning model that integrates improved convolutional neural networks, unbalanced bidirectional long short-term memory networks, and multi-head attention mechanisms is proposed. Utilizing an improved bidirectional long short-term memory network to capture global semantic information, while dynamically focusing on key features through a multi head attention mechanism to enhance the model's adaptability to classification tasks. The performance of the model is validated through experiments on AG News (short text) and IMDb (long text) datasets. The results show that in short text classification, the proposed method has an accu-racy rate of 96% and a classification error rate of only 1.46%. In the task of long text classification, the method proposed in the study has a product under the curve of 0.98. In adversarial attack testing, the accuracy rates of adversarial samples generated by different methods are 92.85% and 90.63%, respec-tively, with the lowest robustness degradation rates of 3.72% and 5.49%, respectively. In cross domain generalization testing, it shows the least classification errors and superior cross domain adaptability. These results validate the high performance, robustness, and wide applicability of the method. The re-search indicates that this approach can validly improve the performance of text classification and pro-vide new solutions for natural language processing related tasks in long text and multi-category scenar-ios.

This article is focused on the influence of the learning rate parameter on the training results of pre-trained transformer models: BERT, DistilBERT, ALBERT, and XLM-RoBERTa. As data for models training and testing dataset from HuggingFace portal is used. This dataset contains labeled data for both testing and training purposes. Moreover, it contains unlabeled data for unsupervised models and algorithms. Instead of direct training and testing, Trainer and TrainingArgument classes from the HuggingFace portal were used. For batch formation, DataColator class was utilized. Different metrics of model training efficiency were considered: learning time, the output of validation and training loss functions. Work result allows comparing the efficiency of every observed model in binary text classification tasks standalone or in assembly with other models. Keywords : transformers, binary text classification, BERT, ALBERT, DistilBERT, XLM-RoBERTa.

This paper investigates whether the power of the models pre-trained on text data, such as BERT, can be transferred to general token sequence classification applications. To verify pre-trained models' transferability, we test the pre-trained models on text classification tasks with meanings of tokens mismatches, and real-world non-text token sequence classification data, including amino acid, DNA, and music. We find that even on non-text data, the models pre-trained on text converge faster, perform better than the randomly initialized models, and only slightly worse than the models using task-specific knowledge. We also find that the representations of the text and non-text pre-trained models share non-trivial similarities.

Short text classification plays an important role in NLP and its applications span a wide range of activities such as sentiment analysis, spam detection. Recently, attention mechanism is widely used in text classification task. Inspired by this, a text classification model based on multi-attention network(MAN) is proposed in this study, which perform well in extracting information related to text category. In our model, we combine the textual information based on multi-attention mechanism, which enables model to focus on global information of the sentence. We tested effectiveness of our model using several standard text classification datasets. Experiment told that our model achieved state-of-the-art results on all datasets.