Related papers: Word Embedding Perturbation for Sentence Classific…

Listening in noisy environments can be difficult even for individuals with a normal hearing thresholds. The speech signal can be masked by noise, which may lead to word misperceptions on the side of the listener, and overall difficulty to…

Despite consistent advancement in powerful deep learning techniques in recent years, large amounts of training data are still necessary for the models to avoid overfitting. Synthetic datasets using generative adversarial networks (GAN) have…

Practical sequence classification tasks in natural language processing often suffer from low training data availability for target classes. Recent works towards mitigating this problem have focused on transfer learning using embeddings…

We present a new theoretical perspective of data noising in recurrent neural network language models (Xie et al., 2017). We show that each variant of data noising is an instance of Bayesian recurrent neural networks with a particular…

Semantic textual similarity is one of the open research challenges in the field of Natural Language Processing. Extensive research has been carried out in this field and near-perfect results are achieved by recent transformer-based models…

We introduce a training method for both better word representation and performance, which we call GROVER (Gradual Rumination On the Vector with maskERs). The method is to gradually and iteratively add random noises to word embeddings while…

Unsupervised pre-training has led to much recent progress in natural language understanding. In this paper, we study self-training as another way to leverage unlabeled data through semi-supervised learning. To obtain additional data for a…

Removing background noise from speech audio has been the subject of considerable effort, especially in recent years due to the rise of virtual communication and amateur recordings. Yet background noise is not the only unpleasant disturbance…

Vector representations of natural language are ubiquitous in search applications. Recently, various methods based on contrastive learning have been proposed to learn textual representations from unlabelled data; by maximizing alignment…

This work presents a new and simple approach for fine-tuning pretrained word embeddings for text classification tasks. In this approach, the class in which a term appears, acts as an additional contextual variable during the fine tuning…

Imperfect labels are ubiquitous in real-world datasets. Several recent successful methods for training deep neural networks (DNNs) robust to label noise have used two primary techniques: filtering samples based on loss during a warm-up…

Contrastive learning has recently achieved compelling performance in unsupervised sentence representation. As an essential element, data augmentation protocols, however, have not been well explored. The pioneering work SimCSE resorting to a…

Online social media is rife with offensive and hateful comments, prompting the need for their automatic detection given the sheer amount of posts created every second. Creating high-quality human-labelled datasets for this task is difficult…

Although pre-trained language models show good performance on various natural language processing tasks, they often rely on non-causal features and patterns to determine the outcome. For natural language inference tasks, previous results…

A speech enhancement method based on probabilistic geometric approach to spectral subtraction (PGA) performed on short time magnitude spectrum is presented in this paper. A confidence parameter of noise estimation is introduced in the gain…

Pre-trained language models such as BERT have been proved to be powerful in many natural language processing tasks. But in some text classification applications such as emotion recognition and sentiment analysis, BERT may not lead to…

In this thesis, we investigate three problems involving the probabilistic modeling of language: smoothing n-gram models, statistical grammar induction, and bilingual sentence alignment. These three problems employ models at three different…

We examine how various types of noise in the parallel training data impact the quality of neural machine translation systems. We create five types of artificial noise and analyze how they degrade performance in neural and statistical…

Data augmentation is widely used in text classification, especially in the low-resource regime where a few examples for each class are available during training. Despite the success, generating data augmentations as hard positive examples…

Current neural network-based methods to the problem of document summarisation struggle when applied to datasets containing large inputs. In this paper we propose a new approach to the challenge of content-selection when dealing with…