相关论文: Exploring the Potential of Lexical Paraphrases for…

The abundance of data produced daily from large variety of sources has boosted the need of novel approaches on causal inference analysis from observational data. Observational data often contain noisy or missing entries. Moreover, causal…

Large language models (LLMs) sometimes demonstrate poor performance on knowledge-intensive tasks, commonsense reasoning is one of them. Researchers typically address these issues by retrieving related knowledge from knowledge graphs or…

Much of the success of modern language models depends on finding a suitable prompt to instruct the model. Until now, it has been largely unknown how variations in the linguistic expression of prompts affect these models. This study…

Lexical semantics theories differ in advocating that the meaning of words is represented as an inference graph, a feature mapping or a vector space, thus raising the question: is it the case that one of these approaches is superior to the…

Label noise is a critical factor that degrades the generalization performance of deep neural networks, thus leading to severe issues in real-world problems. Existing studies have employed strategies based on either loss or uncertainty to…

Learning optimal dictionaries for sparse coding has exposed characteristic sparse features of many natural signals. However, universal guarantees of the stability of such features in the presence of noise are lacking. Here, we provide very…

Natural language is compositional; the meaning of a sentence is a function of the meaning of its parts. This property allows humans to create and interpret novel sentences, generalizing robustly outside their prior experience. Neural…

We propose a novel framework for electrolaryngeal speech intelligibility enhancement through the use of robust linguistic encoders. Pretraining and fine-tuning approaches have proven to work well in this task, but in most cases, various…

The prosody of a spoken word is determined by its surrounding context. In incremental text-to-speech synthesis, where the synthesizer produces an output before it has access to the complete input, the full context is often unknown which can…

We consider the problem of training a model under the presence of label noise. Current approaches identify samples with potentially incorrect labels and reduce their influence on the learning process by either assigning lower weights to…

This letter proposes a new time domain absorption approach designed to reduce masking components of speech signals under noisy-reverberant conditions. In this method, the non-stationarity of corrupted signal segments is used to detect…

The goal of a Question Paraphrase Retrieval (QPR) system is to retrieve equivalent questions that result in the same answer as the original question. Such a system can be used to understand and answer rare and noisy reformulations of common…

Recent advances in eXplainable AI (XAI) have provided new insights into how models for vision, language, and tabular data operate. However, few approaches exist for understanding speech models. Existing work focuses on a few spoken language…

Automatic Speech Recognition (ASR) systems are pivotal in transcribing speech into text, yet the errors they introduce can significantly degrade the performance of downstream tasks like summarization. This issue is particularly pronounced…

We study the robustness of conformal prediction, a powerful tool for uncertainty quantification, to label noise. Our analysis tackles both regression and classification problems, characterizing when and how it is possible to construct…

Speech quality is one of the main foci of speech-related research, where it is frequently studied with speech intelligibility, another essential measurement. Band-level perceptual speech intelligibility, however, has been studied…

Implicit feedback, employed in training recommender systems, unavoidably confronts noise due to factors such as misclicks and position bias. Previous studies have attempted to identify noisy samples through their diverged data patterns,…

Explainable AI methods facilitate the understanding of model behaviour, yet, small, imperceptible perturbations to inputs can vastly distort explanations. As these explanations are typically evaluated holistically, before model deployment,…

Word embeddings have been demonstrated to benefit NLP tasks impressively. Yet, there is room for improvement in the vector representations, because current word embeddings typically contain unnecessary information, i.e., noise. We propose…

Given the great success of Deep Neural Networks(DNNs) and the black-box nature of it,the interpretability of these models becomes an important issue.The majority of previous research works on the post-hoc interpretation of a trained…