Related papers: Topic Stability over Noisy Sources

Deep learning faces a formidable challenge when handling noisy labels, as models tend to overfit samples affected by label noise. This challenge is further compounded by the presence of instance-dependent noise (IDN), a realistic form of…

For multi-class classification under class-conditional label noise, we prove that the accuracy metric itself can be robust. We concretize this finding's inspiration in two essential aspects: training and validation, with which we address…

In this paper we present a model for unsupervised topic discovery in texts corpora. The proposed model uses documents, words, and topics lookup table embedding as neural network model parameters to build probabilities of words given topics,…

Robustness to environmental noise is important to creating automatic speech emotion recognition systems that are deployable in the real world. Prior work on noise robustness has assumed that systems would not make use of sample-by-sample…

We propose a new non-equilibrium model for spatial pattern formation on the basis of local information transfer. Unlike standard models of pattern formation it is not based on the Turing instability. Information is transmitted through the…

This paper focuses on resolving stability hallucinations (e.g., repetitive or omitted speech) in LLM-based Text-to-Speech (TTS) models by improving and leveraging the attention mechanism. First, we analyzed the alignment mechanism between…

Topic models are a class of unsupervised learning algorithms for detecting the semantic structure within a text corpus. Together with a subsequent dimensionality reduction algorithm, topic models can be used for deriving spatializations for…

Natural language processing systems are often downstream of unreliable inputs: machine translation, optical character recognition, or speech recognition. For instance, virtual assistants can only answer your questions after understanding…

Conditional diffusion models have the generative controllability by incorporating external conditions. However, their performance significantly degrades with noisy conditions, such as corrupted labels in the image generation or unreliable…

Despite recent advances, standard sequence labeling systems often fail when processing noisy user-generated text or consuming the output of an Optical Character Recognition (OCR) process. In this paper, we improve the noise-aware training…

As the rapidly advancing domain of natural language processing (NLP), large language models (LLMs) have emerged as powerful tools for interpreting human commands and generating text across various tasks. Nonetheless, the resilience of LLMs…

Character-based neural machine translation (NMT) models alleviate out-of-vocabulary issues, learn morphology, and move us closer to completely end-to-end translation systems. Unfortunately, they are also very brittle and easily falter when…

Topic modelling, as a well-established unsupervised technique, has found extensive use in automatically detecting significant topics within a corpus of documents. However, classic topic modelling approaches (e.g., LDA) have certain…

Reliability analysis aims at estimating the failure probability of an engineering system. It often requires multiple runs of a limit-state function, which usually relies on computationally intensive simulations. Traditionally, these…

A large fraction of textual data available today contains various types of 'noise', such as OCR noise in digitized documents, noise due to informal writing style of users on microblogging sites, and so on. To enable tasks such as…

Understanding simplicity biases in deep learning offers a promising path toward developing reliable AI. A common metric for this, inspired by Boolean function analysis, is average sensitivity, which captures a model's robustness to…

We propose a method for variable selection in the intensity function of spatial point processes that combines sparsity-promoting estimation with noise-robust model selection. As high-resolution spatial data becomes increasingly available…

Incorrect labels in training data occur when human annotators make mistakes or when the data is generated via weak or distant supervision. It has been shown that complex noise-handling techniques - by modeling, cleaning or filtering the…

This chapter considers the computational and statistical aspects of learning linear thresholds in presence of noise. When there is no noise, several algorithms exist that efficiently learn near-optimal linear thresholds using a small amount…

This paper proposes a topic modeling method that scales linearly to billions of documents. We make three core contributions: i) we present a topic modeling method, Tensor Latent Dirichlet Allocation (TLDA), that has identifiable and…