The Bangla linguistic variety is a fascinating mix of regional dialects that adds to the cultural diversity of the Bangla-speaking community. Despite extensive study into translating Bangla to English, English to Bangla, and Banglish to Bangla in the past, there has been a noticeable gap in translating Bangla regional dialects into standard Bangla. In this study, we set out to fill this gap by creating a collection of 32,500 sentences, encompassing Bangla, Banglish, and English, representing five regional Bangla dialects. Our aim is to translate these regional dialects into standard Bangla and detect regions accurately. To achieve this, we proposed models known as mT5 and BanglaT5 for translating regional dialects into standard Bangla. Additionally, we employed mBERT and Bangla-bert-base to determine the specific regions from where these dialects originated. Our experimental results showed the highest BLEU score of 69.06 for Mymensingh regional dialects and the lowest BLEU score of 36.75 for Chittagong regional dialects. We also observed the lowest average word error rate of 0.1548 for Mymensingh regional dialects and the highest of 0.3385 for Chittagong regional dialects. For region detection, we achieved an accuracy of 85.86% for Bangla-bert-base and 84.36% for mBERT. This is the first large-scale investigation of Bangla regional dialects to Bangla machine translation. We believe our findings will not only pave the way for future work on Bangla regional dialects to Bangla machine translation, but will also be useful in solving similar language-related challenges in low-resource language conditions.

Efficient and accurate product relevance assessment is critical for user experiences and business success. Training a proficient relevance assessment model requires high-quality query-product pairs, often obtained through negative sampling strategies. Unfortunately, current methods introduce pooling bias by mistakenly sampling false negatives, diminishing performance and business impact. To address this, we present Bias-mitigating Hard Negative Sampling (BHNS), a novel negative sampling strategy tailored to identify and adjust for false negatives, building upon our original False Negative Estimation algorithm. Our experiments in the Instacart search setting confirm BHNS as effective for practical e-commerce use. Furthermore, comparative analyses on public dataset showcase its domain-agnostic potential for diverse applications.

The concept of updating a probability distribution in the light of new evidence lies at the heart of statistics and machine learning. Pearl's and Jeffrey's rule are two natural update mechanisms which lead to different outcomes, yet the similarities and differences remain mysterious. This paper clarifies their relationship in several ways: via separate descriptions of the two update mechanisms in terms of probabilistic programs and sampling semantics, and via different notions of likelihood (for Pearl and for Jeffrey). Moreover, it is shown that Jeffrey's update rule arises via variational inference. In terms of categorical probability theory, this amounts to an analysis of the situation in terms of the behaviour of the multiset functor, extended to the Kleisli category of the distribution monad.

We introduce a novel loss function to minimize the outage probability of an ML-based resource allocation system. A single-user multi-resource greedy allocation strategy constitutes our application scenario, for which an ML binary classification predictor assists in selecting a resource satisfying the established outage criterium. While other resource allocation policies may be suitable, they are not the focus of our study. Instead, our primary emphasis is on theoretically developing this loss function and leveraging it to train an ML model to address the outage probability challenge. With no access to future channel state information, this predictor foresees each resource's likely future outage status. When the predictor encounters a resource it believes will be satisfactory, it allocates it to the user. Our main result establishes exact and asymptotic expressions for this system's outage probability. These expressions reveal that focusing solely on the optimization of the per-resource outage probability conditioned on the ML predictor recommending resource allocation (a strategy that appears to be most appropriate) may produce inadequate predictors that reject every resource. They also reveal that focusing on standard metrics, like precision, false-positive rate, or recall, may not produce optimal predictors. With our result, we formulate a theoretically optimal, differentiable loss function to train our predictor. We then compare predictors trained using this and traditional loss functions namely, binary cross-entropy (BCE), mean squared error (MSE), and mean absolute error (MAE). In all scenarios, predictors trained using our novel loss function provide superior outage probability performance. Moreover, in some cases, our loss function outperforms predictors trained with BCE, MAE, and MSE by multiple orders of magnitude.

Existing evaluations of entity linking systems often say little about how the system is going to perform for a particular application. There are two fundamental reasons for this. One is that many evaluations only use aggregate measures (like precision, recall, and F1 score), without a detailed error analysis or a closer look at the results. The other is that all of the widely used benchmarks have strong biases and artifacts, in particular: a strong focus on named entities, an unclear or missing specification of what else counts as an entity mention, poor handling of ambiguities, and an over- or underrepresentation of certain kinds of entities. We provide a more meaningful and fair in-depth evaluation of a variety of existing end-to-end entity linkers. We characterize their strengths and weaknesses and also report on reproducibility aspects. The detailed results of our evaluation can be inspected under https://elevant.cs.uni-freiburg.de/emnlp2023 . Our evaluation is based on several widely used benchmarks, which exhibit the problems mentioned above to various degrees, as well as on two new benchmarks, which address the problems mentioned above. The new benchmarks can be found under https://github.com/ad-freiburg/fair-entity-linking-benchmarks .

Synthesizing information from multiple data sources plays a crucial role in the practice of modern medicine. Current applications of artificial intelligence in medicine often focus on single-modality data due to a lack of publicly available, multimodal medical datasets. To address this limitation, we introduce INSPECT, which contains de-identified longitudinal records from a large cohort of patients at risk for pulmonary embolism (PE), along with ground truth labels for multiple outcomes. INSPECT contains data from 19,402 patients, including CT images, radiology report impression sections, and structured electronic health record (EHR) data (i.e. demographics, diagnoses, procedures, vitals, and medications). Using INSPECT, we develop and release a benchmark for evaluating several baseline modeling approaches on a variety of important PE related tasks. We evaluate image-only, EHR-only, and multimodal fusion models. Trained models and the de-identified dataset are made available for non-commercial use under a data use agreement. To the best of our knowledge, INSPECT is the largest multimodal dataset integrating 3D medical imaging and EHR for reproducible methods evaluation and research.

The persistent battle to decrease childhood mortality serves as a commonly employed benchmark for gauging advancements in the field of medicine. Globally, the under-5 mortality rate stands at approximately 5 million, with a significant portion of these deaths being avoidable. Given the significance of this problem, Machine learning-based techniques have emerged as a prominent tool for assessing fetal health. In this work, we have analyzed the classification performance of various machine learning models for fetal health analysis. Classification performance of various machine learning models, such as support vector machine (SVM), random forest(RF), and attentive interpretable tabular learning (TabNet) have been assessed on fetal health. Moreover, dimensionality reduction techniques, such as Principal component analysis (PCA) and Linear discriminant analysis (LDA) have been implemented to obtain better classification performance with less number of features. A TabNet model on a fetal health dataset provides a classification accuracy of 94.36%. In general, this technology empowers doctors and healthcare experts to achieve precise fetal health classification and identify the most influential features in the process.

Objective. Limited access to breast cancer diagnosis globally leads to delayed treatment. Ultrasound, an effective yet underutilized method, requires specialized training for sonographers, which hinders its widespread use. Approach. Volume sweep imaging (VSI) is an innovative approach that enables untrained operators to capture high-quality ultrasound images. Combined with deep learning, like convolutional neural networks (CNNs), it can potentially transform breast cancer diagnosis, enhancing accuracy, saving time and costs, and improving patient outcomes. The widely used UNet architecture, known for medical image segmentation, has limitations, such as vanishing gradients and a lack of multi-scale feature extraction and selective region attention. In this study, we present a novel segmentation model known as Wavelet_Attention_UNet (WATUNet). In this model, we incorporate wavelet gates (WGs) and attention gates (AGs) between the encoder and decoder instead of a simple connection to overcome the limitations mentioned, thereby improving model performance. Main results. Two datasets are utilized for the analysis. The public "Breast Ultrasound Images" (BUSI) dataset of 780 images and a VSI dataset of 3818 images. Both datasets contained segmented lesions categorized into three types: no mass, benign mass, and malignant mass. Our segmentation results show superior performance compared to other deep networks. The proposed algorithm attained a Dice coefficient of 0.94 and an F1 score of 0.94 on the VSI dataset and scored 0.93 and 0.94 on the public dataset, respectively.

In the growing world of artificial intelligence, federated learning is a distributed learning framework enhanced to preserve the privacy of individuals' data. Federated learning lays the groundwork for collaborative research in areas where the data is sensitive. Federated learning has several implications for real-world problems. In times of crisis, when real-time decision-making is critical, federated learning allows multiple entities to work collectively without sharing sensitive data. This distributed approach enables us to leverage information from multiple sources and gain more diverse insights. This paper is a systematic review of the literature on privacy-preserving machine learning in the last few years based on the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Specifically, we have presented an extensive review of supervised/unsupervised machine learning algorithms, ensemble methods, meta-heuristic approaches, blockchain technology, and reinforcement learning used in the framework of federated learning, in addition to an overview of federated learning applications. This paper reviews the literature on the components of federated learning and its applications in the last few years. The main purpose of this work is to provide researchers and practitioners with a comprehensive overview of federated learning from the machine learning point of view. A discussion of some open problems and future research directions in federated learning is also provided.

This study aimed to utilize text processing and natural language processing (NLP) models to mine clinical notes for the diagnosis of periodontitis and to evaluate the performance of a named entity recognition (NER) model on different regular expression (RE) methods. Two complexity levels of RE methods were used to extract and generate the training data. The SpaCy package and RoBERTa transformer models were used to build the NER model and evaluate its performance with the manual-labeled gold standards. The comparison of the RE methods with the gold standard showed that as the complexity increased in the RE algorithms, the F1 score increased from 0.3-0.4 to around 0.9. The NER models demonstrated excellent predictions, with the simple RE method showing 0.84-0.92 in the evaluation metrics, and the advanced and combined RE method demonstrating 0.95-0.99 in the evaluation. This study provided an example of the benefit of combining NER methods and NLP models in extracting target information from free-text to structured data and fulfilling the need for missing diagnoses from unstructured notes.