相关论文: Analyzing and Mitigating Negation Artifacts using …

Existing NLP datasets contain various biases, and models tend to quickly learn those biases, which in turn limits their robustness. Existing approaches to improve robustness against dataset biases mostly focus on changing the training…

Entailment has been recognized as an important metric for evaluating natural language understanding (NLU) models, and recent studies have found that entailment pretraining benefits weakly supervised fine-tuning. In this work, we design a…

Developing neuromorphic intelligence on event-based datasets with Spiking Neural Networks (SNNs) has recently attracted much research attention. However, the limited size of event-based datasets makes SNNs prone to overfitting and unstable…

Counterfactual Data Augmentation (CDA) is a commonly used technique for improving robustness in natural language classifiers. However, one fundamental challenge is how to discover meaningful counterfactuals and efficiently label them, with…

Recent models have achieved human level performance on the Stanford Question Answering Dataset when using F1 scores to evaluate the reading comprehension task. Yet, teaching machines to comprehend text has not been solved in the general…

Negation is a common everyday phenomena and has been a consistent area of weakness for language models (LMs). Although the Information Retrieval (IR) community has adopted LMs as the backbone of modern IR architectures, there has been…

Data augmentation is a widely adopted technique for avoiding overfitting when training deep neural networks. However, this approach requires domain-specific knowledge and is often limited to a fixed set of hard-coded transformations.…

Adversarial training suffers from robust overfitting, a phenomenon where the robust test accuracy starts to decrease during training. In this paper, we focus on reducing robust overfitting by using common data augmentation schemes. We…

While retrieval-augmented generation (RAG) has been shown to enhance factuality of large language model (LLM) outputs, LLMs still suffer from hallucination, generating incorrect or irrelevant information. A common detection strategy…

With the rapid development and widespread use of advanced network systems, software vulnerabilities pose a significant threat to secure communications and networking. Learning-based vulnerability detection systems, particularly those…

We present semi-supervised models with data augmentation (SMDA), a semi-supervised text classification system to classify interactive affective responses. SMDA utilizes recent transformer-based models to encode each sentence and employs…

Data augmentation is often used to enlarge datasets with synthetic samples generated in accordance with the underlying data distribution. To enable a wider range of augmentations, we explore negative data augmentation strategies (NDA)that…

Data augmentation has shown its effectiveness in resolving the data-hungry problem and improving model's generalization ability. However, the quality of augmented data can be varied, especially compared with the raw/original data. To boost…

Automating the detection of regulatory compliance remains a challenging task due to the complexity and variability of legal texts. Models trained on one regulation often fail to generalise to others. This limitation underscores the need for…

With the growth of the Internet, buying habits have changed, and customers have become more dependent on the online opinions of other customers to guide their purchases. Identifying fake reviews thus became an important area for Natural…

Despite the impressive capabilities of large language models (LLMs), their performance on information extraction tasks is still not entirely satisfactory. However, their remarkable rewriting capabilities and extensive world knowledge offer…

Spoofed utterances always contain artifacts introduced by generative models. While several countermeasures have been proposed to detect spoofed utterances, most primarily focus on architectural improvements. In this work, we investigate how…

Sentence embedding tasks are important in natural language processing (NLP), but improving their performance while keeping them reliable is still hard. This paper presents a framework that combines pseudo-label generation and model ensemble…

Optimization of image transformation functions for the purpose of data augmentation has been intensively studied. In particular, adversarial data augmentation strategies, which search augmentation maximizing task loss, show significant…

This work describes a self-supervised data augmentation approach used to improve learning models' performances when only a moderate amount of labeled data is available. Multiple copies of the original model are initially trained on the…