相关论文: Power in Numbers: Robust reading comprehension by …

We support scientific writers in determining whether a written sentence is scientific, to which section it belongs, and suggest paraphrasings to improve the sentence. Firstly, we propose a regression model trained on a corpus of scientific…

Speech is a common and effective way of communication between humans, and modern consumer devices such as smartphones and home hubs are equipped with deep learning based accurate automatic speech recognition to enable natural interaction…

Real-world natural language processing systems need to be robust to human adversaries. Collecting examples of human adversaries for training is an effective but expensive solution. On the other hand, training on synthetic attacks with small…

Adversarial examples are helpful for analyzing and improving the robustness of text classifiers. Generating high-quality adversarial examples is a challenging task as it requires generating fluent adversarial sentences that are semantically…

Recent research studies revealed that neural networks are vulnerable to adversarial attacks. State-of-the-art defensive techniques add various adversarial examples in training to improve models' adversarial robustness. However, these…

Learning from a real-world data stream and continuously updating the model without explicit supervision is a new challenge for NLP applications with machine learning components. In this work, we have developed an adaptive learning system…

Deep neural models (e.g. Transformer) naturally learn spurious features, which create a ``shortcut'' between the labels and inputs, thus impairing the generalization and robustness. This paper advances the self-attention mechanism to its…

A major obstacle in reinforcement learning-based sentence generation is the large action space whose size is equal to the vocabulary size of the target-side language. To improve the efficiency of reinforcement learning, we present a novel…

Benefiting from large-scale pre-training, we have witnessed significant performance boost on the popular Visual Question Answering (VQA) task. Despite rapid progress, it remains unclear whether these state-of-the-art (SOTA) models are…

The integration of new literature into the English curriculum remains a challenge since educators often lack scalable tools to rapidly evaluate readability and adapt texts for diverse classroom needs. This study proposes to address this gap…

Adversarial examples are carefully constructed modifications to an input that completely change the output of a classifier but are imperceptible to humans. Despite these successful attacks for continuous data (such as image and audio…

We explore the idea of automatically crafting a tuning dataset for Statistical Machine Translation (SMT) that makes the hyper-parameters of the SMT system more robust with respect to some specific deficiencies of the parameter tuning…

Insensitivity to semantically-preserving variations of prompts (paraphrases) is crucial for reliable behavior and real-world deployment of large language models. However, language models exhibit significant performance degradation when…

The lack of labeled data is a major obstacle to learning high-quality sentence embeddings. Recently, self-supervised contrastive learning (SCL) is regarded as a promising way to address this problem. However, the existing works mainly rely…

Fine-tuning pretrained language models (PLMs) on downstream tasks has become common practice in natural language processing. However, most of the PLMs are vulnerable, e.g., they are brittle under adversarial attacks or imbalanced data,…

Fine-tuning Large Language Models (LLMs) typically involves updating at least a few billions of parameters. A more parameter-efficient approach is Prompt Tuning (PT), which updates only a few learnable tokens, and differently, In-Context…

Adversarial attacks can deceive neural networks by adding tiny perturbations to their input data. Ensemble defenses, which are trained to minimize attack transferability among sub-models, offer a promising research direction to improve…

Progress in text understanding has been driven by large datasets that test particular capabilities, like recent datasets for reading comprehension (Hermann et al., 2015). We focus here on the LAMBADA dataset (Paperno et al., 2016), a word…

Current neural-network-based classifiers are susceptible to adversarial examples. The most empirically successful approach to defending against such adversarial examples is adversarial training, which incorporates a strong self-attack…

Word-level textual adversarial attacks have demonstrated notable efficacy in misleading Natural Language Processing (NLP) models. Despite their success, the underlying reasons for their effectiveness and the fundamental characteristics of…