Related papers: Rethinking Data Augmentation for Low-Resource Neur…

To investigate the role of linguistic knowledge in data augmentation (DA) for Natural Language Processing (NLP), we designed two adapted DA programs and applied them to LCQMC (a Large-scale Chinese Question Matching Corpus) for a binary…

In many cases of machine learning, research suggests that the development of training data might have a higher relevance than the choice and modelling of classifiers themselves. Thus, data augmentation methods have been developed to improve…

Data-Augmentation (DA) is known to improve performance across tasks and datasets. We propose a method to theoretically analyze the effect of DA and study questions such as: how many augmented samples are needed to correctly estimate the…

This paper presents a novel data augmentation technique for text-to-speech (TTS), that allows to generate new (text, audio) training examples without requiring any additional data. Our goal is to increase diversity of text conditionings…

The principal task in supervised neural machine translation (NMT) is to learn to generate target sentences conditioned on the source inputs from a set of parallel sentence pairs, and thus produce a model capable of generalizing to unseen…

Deep neural networks have emerged as very successful tools for image restoration and reconstruction tasks. These networks are often trained end-to-end to directly reconstruct an image from a noisy or corrupted measurement of that image. To…

In this thesis, we address the data scarcity and limitations of linguistic theory by proposing language-agnostic multi-task training methods. First, we introduce a meta-learning-based approach, meta-transfer learning, in which information…

Neural Machine Translation (NMT) systems struggle when translating to and from low-resource languages, which lack large-scale data corpora for models to use for training. As manual data curation is expensive and time-consuming, we propose…

There are several approaches for improving neural machine translation for low-resource languages: Monolingual data can be exploited via pretraining or data augmentation; Parallel corpora on related language pairs can be used via parameter…

Despite impressive empirical successes of neural machine translation (NMT) on standard benchmarks, limited parallel data impedes the application of NMT models to many language pairs. Data augmentation methods such as back-translation make…

Recently, data augmentation (DA) methods have been proven to be effective for pre-trained language models (PLMs) in low-resource settings, including few-shot named entity recognition (NER). However, conventional NER DA methods are mostly…

Large language models (LLMs) have demonstrated strong performance across various tasks, leveraging their exceptional in-context learning ability with only a few examples. Accordingly, the selection of optimal in-context examples has been…

We explore ways of incorporating bilingual dictionaries to enable semi-supervised neural machine translation. Conventional back-translation methods have shown success in leveraging target side monolingual data. However, since the quality of…

In many practical applications, it is often difficult and expensive to obtain large-scale labeled data to train state-of-the-art deep neural networks. Therefore, transferring the learned knowledge from a separate, labeled source domain to…

We propose a novel monolingual sentence paraphrasing method for augmenting the training data for statistical machine translation systems "for free" -- by creating it from data that is already available rather than having to create more…

Recent studies have demonstrated remarkable advancements in source code learning, which applies deep neural networks (DNNs) to tackle various software engineering tasks. Similar to other DNN-based domains, source code learning also requires…

Cross-lingual representation learning transfers knowledge from resource-rich data to resource-scarce ones to improve the semantic understanding abilities of different languages. However, previous works rely on shallow unsupervised data…

Back translation, as a technique for extending a dataset, is widely used by researchers in low-resource language translation tasks. It typically translates from the target to the source language to ensure high-quality translation results.…

Machine translation (MT) models used in industries with constantly changing topics, such as translation or news agencies, need to adapt to new data to maintain their performance over time. Our aim is to teach a pre-trained MT model to…

Data augmentation forms the cornerstone of many modern machine learning training pipelines; yet, the mechanisms by which it works are not clearly understood. Much of the research on data augmentation (DA) has focused on improving existing…