Data augmentation using virtual word insertion techniques in text classification tasks

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.

Knowledge enhanced pre-trained language models (K-PLMs) are shown to be effective for many public tasks in the literature, but few of them have been successfully applied in practice. To address this problem, we propose K-AID, a systematic approach that includes a low-cost knowledge acquisition process for acquiring domain knowledge, an effective knowledge infusion module for improving model performance, and a knowledge distillation component for reducing the model size and deploying K-PLMs on resource-restricted devices (e.g., CPU) for real-world application. Importantly, instead of capturing entity knowledge like the majority of existing K-PLMs, our approach captures relational knowledge, which contributes to better improving sentence-level text classification and text matching tasks that play a key role in question answering (QA). We conducted a set of experiments on five text classification tasks and three text matching tasks from three domains, namely E-commerce, Government, and Film&TV, and performed online A/B tests in E-commerce. Experimental results show that our approach is able to achieve substantial improvement on sentence-level question answering tasks and bring beneficial business value in industrial settings.

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.

In recent years, with the rapid development of large language models, optimizing BERT's performance on small-scale datasets using large language models has gradually become a research hotspot. To this end, this paper proposes a data augmentation method based on large language models to enhance BERT's performance in text classification tasks. Specifically, we first use large language models to back-translate the training data. By translating the text into other languages and then back into the original language, we generate new samples that are semantically consistent but have diverse expressions, thereby increasing the diversity of the training data. Subsequently, the augmented training set is used to train the BERT model, which significantly improves classification accuracy on the Reuters News Classification dataset. Experimental results show that this method effectively mitigates the limitations of small-scale datasets and significantly enhances the model's generalization ability, providing a novel and efficient solution for text classification tasks.

In recent years, contrastive learning has been very successful in unsupervised tasks of representation learning and has received a lot of attention in supervised tasks. In supervised tasks, the discrete nature of natural language makes the construction of sample pairs difficult and the models are poorly robust to adversarial samples, so it remains a challenge to make contrastive learning effective for text classification tasks and to guarantee the robustness of the models. This paper presents a contrastive adversarial learning framework built using data augmentation with labeled insertion data. Specifically,By adding perturbation to the word-embedding matrix, adversarial samples are generated as positive examples of contrastive learning, and external semantic information is introduced to construct negative examples. Contrastive learning is used to improve the sensitivity and generalization ability of the model, and adversarial training is used to improve robustness, thereby improving the classification accuracy. In addition, the momentum contrast from unsupervised tasks is also introduced into the text classification task to increase the number of sample pairs. Experimental results on several datasets show that the proposed approach outperforms the baseline comparison approach, and in addition some experiments are conducted to verify the effectiveness of the proposed framework under low-resource conditions.

Based on recent advances in natural language modeling and those in text generation capabilities, we propose a novel data augmentation method for text classification tasks. We use a powerful pre-trained neural network model to artificially synthesize new labeled data for supervised learning. We mainly focus on cases with scarce labeled data. Our method, referred to as language-model-based data augmentation (LAMBADA), involves fine-tuning a state-of-the-art language generator to a specific task through an initial training phase on the existing (usually small) labeled data. Using the fine-tuned model and given a class label, new sentences for the class are generated. Our process then filters these new sentences by using a classifier trained on the original data. In a series of experiments, we show that LAMBADA improves classifiers' performance on a variety of datasets. Moreover, LAMBADA significantly improves upon the state-of-the-art techniques for data augmentation, specifically those applicable to text classification tasks with little data.

Self-supervised representation learning can mitigate the limitations in recognition tasks with few manually labeled data but abundant unlabeled data—a common scenario in sound event research. In this work, we explore unsupervised contrastive learning as a way to learn sound event representations. To this end, we propose to use the pretext task of contrasting differently augmented views of sound events. The views are computed primarily via mixing of training examples with unrelated backgrounds, followed by other data augmentations. We analyze the main components of our method via ablation experiments. We evaluate the learned representations using linear evaluation, and in two in-domain downstream sound event classification tasks, namely, using limited manually labeled data, and using noisy labeled data. Our results suggest that unsupervised contrastive pre-training can mitigate the impact of data scarcity and increase robustness against noisy labels.

Causal reasoning and logical reasoning are two important types of reasoning abilities for human intelligence. However, their relationship has not been extensively explored under machine intelligence context. In this paper, we explore how the two reasoning abilities can be jointly modeled to enhance both accuracy and explainability of machine learning models. More specifically, by integrating two important types of reasoning ability--counterfactual reasoning and (neural) logical reasoning--we propose Counterfactual Collaborative Reasoning (CCR), which conducts counterfactual logic reasoning to improve the performance. In particular, we use recommender system as an example to show how CCR alleviate data scarcity, improve accuracy and enhance transparency. Technically, we leverage counterfactual reasoning to generate "difficult" counterfactual training examples for data augmentation, which--together with the original training examples--can enhance the model performance. Since the augmented data is model irrelevant, they can be used to enhance any model, enabling the wide applicability of the technique. Besides, most of the existing data augmentation methods focus on "implicit data augmentation" over users' implicit feedback, while our framework conducts "explicit data augmentation" over users explicit feedback based on counterfactual logic reasoning. Experiments on three real-world datasets show that CCR achieves better performance than non-augmented models and implicitly augmented models, and also improves model transparency by generating counterfactual explanations.

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.

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.

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.

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.

Tibetan Few‐Shot Learning Model With Deep Contextualised Two‐Level Word Embeddings

Incremental language learning, which involves retrieving pseudo-data from previous tasks, can alleviate catastrophic forgetting. However, previous methods require a large amount of pseudo-data to approach the performance of multitask learning, and the performance decreases dramatically when there is significantly less pseudo-data than new task data. This decrease occurs because the pseudo-data are learned inefficiently and deviate from the real data. To address these issues, we propose reminding the incremental language model via data-free self-distillation (DFSD), which includes 1) self-distillation based on the Earth mover’s distance (SD-EMD) and 2) hidden data augmentation (HDA). SD-EMD can increase the efficiency of the model by adaptively estimating the knowledge distribution in all GPT-2 layers and effectively transferring data from the teacher model to the student model via adaptive self-multilayer-to-multilayer mapping. HDA can reduce deviations by decomposing the generation process via data augmentation and bootstrapping. Our experiments on decaNLP and text classification tasks with low pseudo-data sampling ratios reveal that the DFSD model outperforms previous state-of-the-art incremental methods. The advantages of DFSD become more apparent when there is less pseudo-data and larger deviations.