Punctuation restoration is a crucial step after Automatic Speech Recognition (ASR) systems to enhance transcript readability and facilitate subsequent NLP tasks. Nevertheless, conventional lexical-based approaches are inadequate for solving the punctuation restoration task in Spanish, where ambiguity can be often found between unpunctuated declaratives and questions. In this study, we propose a novel hybrid acoustic-lexical punctuation restoration system for Spanish transcription, which consolidates acoustic and lexical signals through a modular process. Our experiment results show that the proposed system can effectively improve F1 score of question marks and overall punctuation restoration on both public and internal Spanish conversational datasets. Additionally, benchmark comparison against LLMs (Large Language Model) indicates the superiority of our approach in accuracy, reliability and latency. Furthermore, we demonstrate that the Word Error Rate (WER) of the ASR module also benefits from our proposed system.

Using unlabeled data to regularize the machine learning models has demonstrated promise for improving safety and reliability in detecting out-of-distribution (OOD) data. Harnessing the power of unlabeled in-the-wild data is non-trivial due to the heterogeneity of both in-distribution (ID) and OOD data. This lack of a clean set of OOD samples poses significant challenges in learning an optimal OOD classifier. Currently, there is a lack of research on formally understanding how unlabeled data helps OOD detection. This paper bridges the gap by introducing a new learning framework SAL (Separate And Learn) that offers both strong theoretical guarantees and empirical effectiveness. The framework separates candidate outliers from the unlabeled data and then trains an OOD classifier using the candidate outliers and the labeled ID data. Theoretically, we provide rigorous error bounds from the lens of separability and learnability, formally justifying the two components in our algorithm. Our theory shows that SAL can separate the candidate outliers with small error rates, which leads to a generalization guarantee for the learned OOD classifier. Empirically, SAL achieves state-of-the-art performance on common benchmarks, reinforcing our theoretical insights. Code is publicly available at https://github.com/deeplearning-wisc/sal.

In this paper, we present Partially Stochastic Infinitely Deep Bayesian Neural Networks, a novel family of architectures that integrates partial stochasticity into the framework of infinitely deep neural networks. Our new class of architectures is designed to improve the limitations of existing architectures around computational efficiency at training and inference time. To do this, we leverage the advantages of partial stochasticity in the infinite-depth limit which include the benefits of full stochasticity e.g. robustness, uncertainty quantification, and memory efficiency, whilst improving their limitations around computational efficiency at training and inference time. We present a variety of architectural configurations, offering flexibility in network design including different methods for weight partition. We also provide mathematical guarantees on the expressivity of our models by establishing that our network family qualifies as Universal Conditional Distribution Approximators. Lastly, empirical evaluations across multiple tasks show that our proposed architectures achieve better downstream task performance and uncertainty quantification than their counterparts while being significantly more efficient.

This study proposes the use of Machine Learning models to predict the early onset of sepsis using deidentified clinical data from Montefiore Medical Center in Bronx, NY, USA. A supervised learning approach was adopted, wherein an XGBoost model was trained utilizing 80\% of the train dataset, encompassing 107 features (including the original and derived features). Subsequently, the model was evaluated on the remaining 20\% of the test data. The model was validated on prospective data that was entirely unseen during the training phase. To assess the model's performance at the individual patient level and timeliness of the prediction, a normalized utility score was employed, a widely recognized scoring methodology for sepsis detection, as outlined in the PhysioNet Sepsis Challenge paper. Metrics such as F1 Score, Sensitivity, Specificity, and Flag Rate were also devised. The model achieved a normalized utility score of 0.494 on test data and 0.378 on prospective data at threshold 0.3. The F1 scores were 80.8\% and 67.1\% respectively for the test data and the prospective data for the same threshold, highlighting its potential to be integrated into clinical decision-making processes effectively. These results bear testament to the model's robust predictive capabilities and its potential to substantially impact clinical decision-making processes.

Infrared (IR) spectroscopy is a pivotal technique in chemical research for elucidating molecular structures and dynamics through vibrational and rotational transitions. However, the intricate molecular fingerprints characterized by unique vibrational and rotational patterns present substantial analytical challenges. Here, we present a machine learning approach employing a Structural Attention Mechanism tailored to enhance the prediction and interpretation of infrared spectra, particularly for diazo compounds. Our model distinguishes itself by honing in on chemical information proximal to functional groups, thereby significantly bolstering the accuracy, robustness, and interpretability of spectral predictions. This method not only demystifies the correlations between infrared spectral features and molecular structures but also offers a scalable and efficient paradigm for dissecting complex molecular interactions.

Out-of-Distribution (OoD) detection is vital for the reliability of Deep Neural Networks (DNNs). Existing works have shown the insufficiency of Principal Component Analysis (PCA) straightforwardly applied on the features of DNNs in detecting OoD data from In-Distribution (InD) data. The failure of PCA suggests that the network features residing in OoD and InD are not well separated by simply proceeding in a linear subspace, which instead can be resolved through proper nonlinear mappings. In this work, we leverage the framework of Kernel PCA (KPCA) for OoD detection, seeking subspaces where OoD and InD features are allocated with significantly different patterns. We devise two feature mappings that induce non-linear kernels in KPCA to advocate the separability between InD and OoD data in the subspace spanned by the principal components. Given any test sample, the reconstruction error in such subspace is then used to efficiently obtain the detection result with $\mathcal{O}(1)$ time complexity in inference. Extensive empirical results on multiple OoD data sets and network structures verify the superiority of our KPCA-based detector in efficiency and efficacy with state-of-the-art OoD detection performances.

A Normalizing Flow computes a bijective mapping from an arbitrary distribution to a predefined (e.g. normal) distribution. Such a flow can be used to address different tasks, e.g. anomaly detection, once such a mapping has been learned. In this work we introduce Normalizing Flows for Quantum architectures, describe how to model and optimize such a flow and evaluate our method on example datasets. Our proposed models show competitive performance for anomaly detection compared to classical methods, e.g. based on isolation forests, the local outlier factor (LOF) or single-class SVMs, while being fully executable on a quantum computer.

The increasing rate at which scientific knowledge is discovered and health claims shared online has highlighted the importance of developing efficient fact-checking systems for scientific claims. The usual setting for this task in the literature assumes that the documents containing the evidence for claims are already provided and annotated or contained in a limited corpus. This renders the systems unrealistic for real-world settings where knowledge sources with potentially millions of documents need to be queried to find relevant evidence. In this paper, we perform an array of experiments to test the performance of open-domain claim verification systems. We test the final verdict prediction of systems on four datasets of biomedical and health claims in different settings. While keeping the pipeline's evidence selection and verdict prediction parts constant, document retrieval is performed over three common knowledge sources (PubMed, Wikipedia, Google) and using two different information retrieval techniques. We show that PubMed works better with specialized biomedical claims, while Figure 1: The experimental setup of the study: scientific Wikipedia is more suited for everyday health claims are passed through a fixed pipeline using three concerns. Likewise, BM25 excels in retrieval different knowledge sources, resulting in different final precision, while semantic search in recall of relevant prediction performance (as measured by F1 score).

Public Graph Neural Networks (GNN) benchmark datasets facilitate the use of GNN and enhance GNN applicability to diverse disciplines. The community currently lacks public datasets of electrical power grids for GNN applications. Indeed, GNNs can potentially capture complex power grid phenomena over alternative machine learning techniques. Power grids are complex engineered networks that are naturally amenable to graph representations. Therefore, GNN have the potential for capturing the behavior of power grids over alternative machine learning techniques. To this aim, we develop a graph dataset for cascading failure events, which are the major cause of blackouts in electric power grids. Historical blackout datasets are scarce and incomplete. The assessment of vulnerability and the identification of critical components are usually conducted via computationally expensive offline simulations of cascading failures. Instead, we propose using machine learning models for the online detection of cascading failures leveraging the knowledge of the system state at the onset of the cascade. We develop PowerGraph, a graph dataset modeling cascading failures in power grids, designed for two purposes, namely, i) training GNN models for different graph-level tasks including multi-class classification, binary classification, and regression, and ii) explaining GNN models. The dataset generated via a physics-based cascading failure model ensures the generality of the operating and environmental conditions by spanning diverse failure scenarios. In addition, we foster the use of the dataset to benchmark GNN explainability methods by assigning ground-truth edge-level explanations. PowerGraph helps the development of better GNN models for graph-level tasks and explainability, critical in many domains ranging from chemistry to biology, where the systems and processes can be described as graphs.

Rapid development of disease detection computer vision models is vital in response to urgent medical crises like epidemics or events of bioterrorism. However, traditional data gathering methods are too slow for these scenarios necessitating innovative approaches to generate reliable models quickly from minimal data. We demonstrate our new approach by building a comprehensive computer vision model for detecting Human Papilloma Virus Genital warts using only synthetic data. In our study, we employed a two phase experimental design using diffusion models. In the first phase diffusion models were utilized to generate a large number of diverse synthetic images from 10 HPV guide images explicitly focusing on accurately depicting genital warts. The second phase involved the training and testing vision model using this synthetic dataset. This method aimed to assess the effectiveness of diffusion models in rapidly generating high quality training data and the subsequent impact on the vision model performance in medical image recognition. The study findings revealed significant insights into the performance of the vision model trained on synthetic images generated through diffusion models. The vision model showed exceptional performance in accurately identifying cases of genital warts. It achieved an accuracy rate of 96% underscoring its effectiveness in medical image classification. For HPV cases the model demonstrated a high precision of 99% and a recall of 94%. In normal cases the precision was 95% with an impressive recall of 99%. These metrics indicate the model capability to correctly identify true positive cases and minimize false positives. The model achieved an F1 Score of 96% for HPV cases and 97% for normal cases. The high F1 Score across both categories highlights the balanced nature of the model precision and recall ensuring reliability and robustness in its predictions.