Related papers: Learning to Perturb Word Embeddings for Out-of-dis…

Learning from noisy labels is an important and long-standing problem in machine learning for real applications. One of the main research lines focuses on learning a label corrector to purify potential noisy labels. However, these methods…

Deep learning models excel at many tasks but rely on the assumption that training and test data follow the same distribution. This assumption often does not hold in real-world speech systems, where distribution shifts are common due to…

The training of spoken language understanding (SLU) models often faces the problem of data scarcity. In this paper, we put forward a data augmentation method using pretrained language models to boost the variability and accuracy of…

Speech data has rich acoustic and paralinguistic information with important cues for understanding a speaker's tone, emotion, and intent, yet traditional large language models such as BERT do not incorporate this information. There has been…

In text classification, the traditional attention mechanisms usually focus too much on frequent words, and need extensive labeled data in order to learn. This paper proposes a perturbation-based self-supervised attention approach to guide…

Embedding retrofitting adjusts pre-trained word vectors using knowledge graph constraints to improve domain-specific retrieval. However, the effectiveness of retrofitting depends critically on knowledge graph quality, which in turn depends…

When the world changes, so does the text that humans write about it. How do we build language models that can be easily updated to reflect these changes? One popular approach is retrieval-augmented generation, in which new documents are…

Retraining modern deep learning systems can lead to variations in model performance even when trained using the same data and hyper-parameters by simply using different random seeds. We call this phenomenon model jitter. This issue is often…

The acquisition of large-scale, high-quality data is a resource-intensive and time-consuming endeavor. Compared to conventional Data Augmentation (DA) techniques (e.g. cropping and rotation), exploiting prevailing diffusion models for data…

Neural models with an encoder-decoder framework provide a feasible solution to Question Generation (QG). However, after analyzing the model vocabulary we find that current models (both RNN-based and pre-training based) have more than 23\%…

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…

Accurately quantifying uncertainty in large language models (LLMs) is crucial for their reliable deployment, especially in high-stakes applications. Current state-of-the-art methods for measuring semantic uncertainty in LLMs rely on strict…

In recent years, language models (LMs) have made remarkable progress in advancing the field of natural language processing (NLP). However, the impact of data augmentation (DA) techniques on the fine-tuning (FT) performance of these LMs has…

Current state-of-the-art neural dialogue models learn from human conversations following the data-driven paradigm. As such, a reliable training corpus is the crux of building a robust and well-behaved dialogue model. However, due to the…

End-to-end acoustic-to-word speech recognition models have recently gained popularity because they are easy to train, scale well to large amounts of training data, and do not require a lexicon. In addition, word models may also be easier to…

The knowledge that humans hold about a problem often extends far beyond a set of training data and output labels. While the success of deep learning mostly relies on supervised training, important properties cannot be inferred efficiently…

We propose TANDA, an effective technique for fine-tuning pre-trained Transformer models for natural language tasks. Specifically, we first transfer a pre-trained model into a model for a general task by fine-tuning it with a large and…

Existing literature on Question Answering (QA) mostly focuses on algorithmic novelty, data augmentation, or increasingly large pre-trained language models like XLNet and RoBERTa. Additionally, a lot of systems on the QA leaderboards do not…

Automatic subjective speech quality assessment (SSQA) traditionally estimates speech quality on an utterance or system level. While this resolution was adequate for older transmission or synthesis systems that produced speech signals of…

Data augmentation (DA) is commonly used during model training, as it significantly improves test error and model robustness. DA artificially expands the training set by applying random noise, rotations, crops, or even adversarial…