Related papers: Good-Enough Compositional Data Augmentation

Large language models are increasingly used as computational tools for modeling human-like behavior. We introduce a behavioral induction framework that modifies model policies through fine-tuning on structured decision-making tasks: using…

Common language models typically predict the next word given the context. In this work, we propose a method that improves language modeling by learning to align the given context and the following phrase. The model does not require any…

Dataset augmentation, the practice of applying a wide array of domain-specific transformations to synthetically expand a training set, is a standard tool in supervised learning. While effective in tasks such as visual recognition, the set…

This paper presents methods of making using of text supervision to improve the performance of sequence-to-sequence (seq2seq) voice conversion. Compared with conventional frame-to-frame voice conversion approaches, the seq2seq acoustic…

Structured language models for speech recognition have been shown to remedy the weaknesses of n-gram models. All current structured language models are, however, limited in that they do not take into account dependencies between…

We introduce a simple yet powerful framework for training large language models. In contrast to the standard autoregressive next-token prediction based on an exact prefix, we propose a perturbation-based procedure that first transforms the…

Existing deep learning based speech enhancement mainly employ a data-driven approach, which leverage large amounts of data with a variety of noise types to achieve noise removal from noisy signal. However, the high dependence on the data…

People can learn a new concept and use it compositionally, understanding how to "blicket twice" after learning how to "blicket." In contrast, powerful sequence-to-sequence (seq2seq) neural networks fail such tests of compositionality,…

Recent generative data augmentation methods conditioned on both image and text prompts struggle to balance between fidelity and diversity, as it is challenging to preserve essential image details while aligning with varied text prompts.…

Imbalanced data, where the positive samples represent only a small proportion compared to the negative samples, makes it challenging for classification problems to balance the false positive and false negative rates. A common approach to…

Deep artificial neural networks require a large corpus of training data in order to effectively learn, where collection of such training data is often expensive and laborious. Data augmentation overcomes this issue by artificially inflating…

Speech enhancement is a critical component of many user-oriented audio applications, yet current systems still suffer from distorted and unnatural outputs. While generative models have shown strong potential in speech synthesis, they are…

Data augmentations are useful in closing the sim-to-real domain gap when training on synthetic data. This is because they widen the training data distribution, thus encouraging the model to generalize better to other domains. Many image…

Data augmentation integrates domain knowledge into a dataset by making domain-informed modifications to existing data points. For example, image data can be augmented by duplicating images in different tints or orientations, thereby…

A recurrent issue in deep learning is the scarcity of data, in particular precisely annotated data. Few publicly available databases are correctly annotated and generating correct labels is very time consuming. The present article…

Current efficient fine-tuning methods (e.g., adapters, prefix-tuning, etc.) have optimized conditional text generation via training a small set of extra parameters of the neural language model, while freezing the rest for efficiency. While…

In this technique report, we aim to mitigate the overfitting problem of natural language by applying data augmentation methods. Specifically, we attempt several types of noise to perturb the input word embedding, such as Gaussian noise,…

We present a new method for large language models to solve compositional tasks. Although they have shown strong performance on traditional language understanding tasks, large language models struggle to solve compositional tasks, where the…

Existing NLP datasets contain various biases, and models tend to quickly learn those biases, which in turn limits their robustness. Existing approaches to improve robustness against dataset biases mostly focus on changing the training…

The use of deep learning for radio modulation recognition has become prevalent in recent years. This approach automatically extracts high-dimensional features from large datasets, facilitating the accurate classification of modulation…