AG Жаңалықтар
Related Papers
Assessing Robustness of Text Classification through Maximal Safe Radius Computation
AbstractNeural network NLP models are vulnerable to small modifications of the input that maintain the original meaning but result in a different prediction. In this paper, we focus on robustness …...
DATE: Detecting Anomalies in Text via Self-Supervision of Transformers
AbstractLeveraging deep learning models for Anomaly Detection (AD) has seen widespread use in recent years due to superior performances over traditional methods. Recent deep methods for anomalies in images learn …...
TAN-NTM: Topic Attention Networks for Neural Topic Modeling
AbstractTopic models have been widely used to learn text representations and gain insight into document corpora. To perform topic discovery, most existing neural models either take document bag-of-words (BoW) or …...
Improving the Adversarial Robustness of NLP Models by Information Bottleneck
AbstractExisting studies have demonstrated that adversarial examples can be directly attributed to the presence of non-robust features, which are highly predictive, but can be easily manipulated by adversaries to fool …...
Label Semantic Aware Pre-training for Few-shot Text Classification
AbstractIn text classification tasks, useful information is encoded in the label names. Label semantic aware systems have leveraged this information for improved text classification performance during fine-tuning and prediction. However, …...
Multi-Level Knowledge Distillation for Out-of-Distribution Detection in Text
AbstractSelf-supervised representation learning has proved to be a valuable component for out-of-distribution (OoD) detection with only the texts of in-distribution (ID) examples. These approaches either train a language model from …...