Related papers: mask-Net: Learning Context Aware Invariant Feature…

Task oriented language understanding in dialog systems is often modeled using intents (task of a query) and slots (parameters for that task). Intent detection and slot tagging are, in turn, modeled using sentence classification and word…

Transformer models have been used in automatic speech recognition (ASR) successfully and yields state-of-the-art results. However, its performance is still affected by speaker mismatch between training and test data. Further finetuning a…

Adversarial vulnerability remains a major obstacle to constructing reliable NLP systems. When imperceptible perturbations are added to raw input text, the performance of a deep learning model may drop dramatically under attacks. Recent work…

We propose methods to strengthen the invariance properties of representations obtained by contrastive learning. While existing approaches implicitly induce a degree of invariance as representations are learned, we look to more directly…

Comprehending the overall intent of an utterance helps a listener recognize the individual words spoken. Inspired by this fact, we perform a novel study of the impact of explicitly incorporating intent representations as additional…

In this paper we propose a new family of algorithms, ATENT, for training adversarially robust deep neural networks. We formulate a new loss function that is equipped with an additional entropic regularization. Our loss function considers…

Recent work has shown the importance of adaptation of broad-coverage contextualised embedding models on the domain of the target task of interest. Current self-supervised adaptation methods are simplistic, as the training signal comes from…

Deep neural networks (DNNs) have a high capacity to completely memorize noisy labels given sufficient training time, and its memorization, unfortunately, leads to performance degradation. Recently, virtual adversarial training (VAT)…

Recently, empowered with the powerful capabilities of neural networks, reinforcement learning (RL) has successfully tackled numerous challenging tasks. However, while these models demonstrate enhanced decision-making abilities, they are…

Face images are subject to many different factors of variation, especially in unconstrained in-the-wild scenarios. For most tasks involving such images, e.g. expression recognition from video streams, having enough labeled data is…

This paper presents a new semantic frame parsing model, based on Berkeley FrameNet, adapted to process spoken documents in order to perform information extraction from broadcast contents. Building upon previous work that had shown the…

Adversarial Training (AT) has been found to substantially improve the robustness of deep learning classifiers against adversarial attacks. AT involves obtaining robustness by including adversarial examples in training a classifier. Most…

Previous studies demonstrate that word embeddings and part-of-speech (POS) tags are helpful for punctuation restoration tasks. However, two drawbacks still exist. One is that word embeddings are pre-trained by unidirectional language…

Deep neural network based speaker recognition systems can easily be deceived by an adversary using minuscule imperceptible perturbations to the input speech samples. These adversarial attacks pose serious security threats to the speaker…

Continual pretraining is a popular way of building a domain-specific pretrained language model from a general-domain language model. In spite of its high efficiency, continual pretraining suffers from catastrophic forgetting, which may harm…

Transformer-based language models have achieved significant success in various domains. However, the data-intensive nature of the transformer architecture requires much labeled data, which is challenging in low-resource scenarios (i.e.,…

Large language models (LLMs) remain vulnerable to adversarial prompting despite advances in alignment and safety, often exhibiting harmful behaviors under novel attack strategies. While adversarial training can improve robustness, existing…

Deep learning has undoubtedly offered tremendous improvements in the performance of state-of-the-art speech emotion recognition (SER) systems. However, recent research on adversarial examples poses enormous challenges on the robustness of…

Continual (or "incremental") learning approaches are employed when additional knowledge or tasks need to be learned from subsequent batches or from streaming data. However these approaches are typically adversary agnostic, i.e., they do not…

Previous studies investigating the syntactic abilities of deep learning models have not targeted the relationship between the strength of the grammatical generalization and the amount of evidence to which the model is exposed during…