Related papers: Revisiting Adversarial Autoencoder for Unsupervise…
State-of-the-art methods for learning cross-lingual word embeddings have relied on bilingual dictionaries or parallel corpora. Recent studies showed that the need for parallel data supervision can be alleviated with character-level…
The goal of this work is to train robust speaker recognition models without speaker labels. Recent works on unsupervised speaker representations are based on contrastive learning in which they encourage within-utterance embeddings to be…
Multi-speaker TTS has to learn both linguistic embedding and text embedding to generate speech of desired linguistic content in desired voice. However, it is unclear which characteristic of speech results from speaker and which part from…
Cross-lingual word embeddings are vector representations of words in different languages where words with similar meaning are represented by similar vectors, regardless of the language. Recent developments which construct these embeddings…
Exposing diverse subword segmentations to neural machine translation (NMT) models often improves the robustness of machine translation as NMT models can experience various subword candidates. However, the diversification of subword…
This paper presents our latest effort on improving Code-switching language models that suffer from data scarcity. We investigate methods to augment Code-switching training text data by artificially generating them. Concretely, we propose a…
Recent research has shown that word embedding spaces learned from text corpora of different languages can be aligned without any parallel data supervision. Inspired by the success in unsupervised cross-lingual word embeddings, in this paper…
Adversarial training has emerged as an effective approach to train robust neural network models that are resistant to adversarial attacks, even in low-label regimes where labeled data is scarce. In this paper, we introduce a novel…
Deep learning models, while achieving state-of-the-art performance on many tasks, are susceptible to adversarial attacks that exploit inherent vulnerabilities in their architectures. Adversarial attacks manipulate the input data with…
Deep Neural Networks are vulnerable to adversarial attacks. Among many defense strategies, adversarial training with untargeted attacks is one of the most effective methods. Theoretically, adversarial perturbation in untargeted attacks can…
Adversarial training is an approach of increasing the robustness of models to adversarial attacks by including adversarial examples in the training set. One major challenge of producing adversarial examples is to contain sufficient…
Although temporal tagging is still dominated by rule-based systems, there have been recent attempts at neural temporal taggers. However, all of them focus on monolingual settings. In this paper, we explore multilingual methods for the…
In this paper, we investigate the use of adversarial learning for unsupervised adaptation to unseen recording conditions, more specifically, single microphone far-field speech. We adapt neural networks based acoustic models trained with…
Cross-lingual transfer learning has become an important weapon to battle the unavailability of annotated resources for low-resource languages. One of the fundamental techniques to transfer across languages is learning…
Injecting adversarial examples during training, known as adversarial training, can improve robustness against one-step attacks, but not for unknown iterative attacks. To address this challenge, we first show iteratively generated…
We propose a novel model architecture and training algorithm to learn bilingual sentence embeddings from a combination of parallel and monolingual data. Our method connects autoencoding and neural machine translation to force the source and…
Unsupervised on-the-fly back-translation, in conjunction with multilingual pretraining, is the dominant method for unsupervised neural machine translation. Theoretically, however, the method should not work in general. We therefore conduct…
Machine learning techniques in particle physics are most powerful when they are trained directly on data, to avoid sensitivity to theoretical uncertainties or an underlying bias on the expected signal. To be able to train on data in…
Sensitivity to adversarial noise hinders deployment of machine learning algorithms in security-critical applications. Although many adversarial defenses have been proposed, robustness to adversarial noise remains an open problem. The most…
Despite the success on few-shot learning problems, most meta-learned models only focus on achieving good performance on clean examples and thus easily break down when given adversarially perturbed samples. While some recent works have shown…