Search

Motivated by the burgeoning interest in cross-domain learning, we present a novel generative modeling challenge: generating counterfactual samples in a target domain based on factual observations from a source domain. Our approach operates within an unsupervised paradigm devoid of parallel or joint datasets, relying exclusively on distinct observational samples and causal graphs for each domain. This setting presents challenges that surpass those of conventional counterfactual generation. Central to our methodology is the disambiguation of exogenous causes into effect-intrinsic and domain-intrinsic categories. This differentiation facilitates the integration of domain-specific causal graphs into a unified joint causal graph via shared effect-intrinsic exogenous variables. We propose leveraging Neural Causal models within this joint framework to enable accurate counterfactual generation under standard identifiability assumptions. Furthermore, we introduce a novel loss function that effectively segregates effect-intrinsic from domain-intrinsic variables during model training. Given a factual observation, our framework combines the posterior distribution of effect-intrinsic variables from the source domain with the prior distribution of domain-intrinsic variables from the target domain to synthesize the desired counterfactuals, adhering to Pearl's causal hierarchy. Intriguingly, when domain shifts are restricted to alterations in causal mechanisms without accompanying covariate shifts, our training regimen parallels the resolution of a conditional optimal transport problem. Empirical evaluations on a synthetic dataset show that our framework generates counterfactuals in the target domain that very closely resemble the ground truth., Comment: 13 pages, 1 figure

Large Language Models revolutionized NLP and showed dramatic performance improvements across several tasks. In this paper, we investigated the role of such language models in text classification and how they compare with other approaches relying on smaller pre-trained language models. Considering 32 datasets spanning 8 languages, we compared zero-shot classification, few-shot fine-tuning and synthetic data based classifiers with classifiers built using the complete human labeled dataset. Our results show that zero-shot approaches do well for sentiment classification, but are outperformed by other approaches for the rest of the tasks, and synthetic data sourced from multiple LLMs can build better classifiers than zero-shot open LLMs. We also see wide performance disparities across languages in all the classification scenarios. We expect that these findings would guide practitioners working on developing text classification systems across languages., Comment: Pre-print

Explainable AI (XAI) in medical histopathology is essential for enhancing the interpretability and clinical trustworthiness of deep learning models in cancer diagnosis. However, the black-box nature of these models often limits their clinical adoption. We introduce GRAPHITE (Graph-based Interpretable Tissue Examination), a post-hoc explainable framework designed for breast cancer tissue microarray (TMA) analysis. GRAPHITE employs a multiscale approach, extracting patches at various magnification levels, constructing an hierarchical graph, and utilising graph attention networks (GAT) with scalewise attention (SAN) to capture scale-dependent features. We trained the model on 140 tumour TMA cores and four benign whole slide images from which 140 benign samples were created, and tested it on 53 pathologist-annotated TMA samples. GRAPHITE outperformed traditional XAI methods, achieving a mean average precision (mAP) of 0.56, an area under the receiver operating characteristic curve (AUROC) of 0.94, and a threshold robustness (ThR) of 0.70, indicating that the model maintains high performance across a wide range of thresholds. In clinical utility, GRAPHITE achieved the highest area under the decision curve (AUDC) of 4.17e+5, indicating reliable decision support across thresholds. These results highlight GRAPHITE's potential as a clinically valuable tool in computational pathology, providing interpretable visualisations that align with the pathologists' diagnostic reasoning and support precision medicine., Comment: 24 Pages, 9 Figures, 1 Tables

Solar irradiance and its variations in the ultraviolet (UV) control the photochemistry in Earth's atmosphere and influence Earth's climate. The variability of Mg II h and k core-to-wing ratio, also known as the Mg II index, is highly correlated with the solar UV irradiance variability. Because of this, Mg II index is routinely used as a proxy for solar UV irradiance variability, which can help to get insights into the influence of solar UV irradiance variability on Earth's climate. Measurements of the Mg II index, however, have only been carried out since 1978 and do not cover the climate relevant timescales longer than a few decades. Here we present a model to calculate the Mg II index and its variability based on the well-established SATIRE (Spectral And Total Irradiance REconstruction) model. We demonstrate that our model calculations yield an excellent agreement with the observed Mg II index variations, both on the solar activity cycle and on the solar rotation timescales. Using this model, we synthesize Mg II index timeseries on climate relevant timescales of decades and longer. Here we present the timeseries of the Mg II index spanning nearly three centuries., Comment: Accepted for publication in ApJ

This paper presents a new voice conversion model capable of transforming both speaking and singing voices. It addresses key challenges in current systems, such as conveying emotions, managing pronunciation and accent changes, and reproducing non-verbal sounds. One of the model's standout features is its ability to perform accent conversion on hybrid voice samples that encompass both speech and singing, allowing it to change the speaker's accent while preserving the original content and prosody. The proposed model uses an encoder-decoder architecture: the encoder is based on HuBERT to process the speech's acoustic and linguistic content, while the HiFi-GAN decoder audio matches the target speaker's voice. The model incorporates fundamental frequency (f0) features and singer embeddings to enhance performance while ensuring the pitch & tone accuracy and vocal identity are preserved during transformation. This approach improves how naturally and flexibly voice style can be transformed, showing strong potential for applications in voice dubbing, content creation, and technologies like Text-to-Speech (TTS) and Interactive Voice Response (IVR) systems., Comment: 7 pages, 5 figures, 2 tables

Early screening for cancer has proven to improve the survival rate and spare patients from intensive and costly treatments due to late diagnosis. Cancer screening in the healthy population involves an initial risk stratification step to determine the screening method and frequency, primarily to optimize resource allocation by targeting screening towards individuals who draw most benefit. For most screening programs, age and clinical risk factors such as family history are part of the initial risk stratification algorithm. In this paper, we focus on developing a blood marker-based risk stratification approach, which could be used to identify patients with elevated cancer risk to be encouraged for taking a diagnostic test or participate in a screening program. We demonstrate that the combination of simple, widely available blood tests, such as complete blood count and complete metabolic panel, could potentially be used to identify patients at risk for colorectal, liver, and lung cancers with areas under the ROC curve of 0.76, 0.85, 0.78, respectively. Furthermore, we hypothesize that such an approach could not only be used as pre-screening risk assessment for individuals but also as population health management tool, for example to better interrogate the cancer risk in certain sub-populations.

Ultrasound fetal imaging is beneficial to support prenatal development because it is affordable and non-intrusive. Nevertheless, fetal plane classification (FPC) remains challenging and time-consuming for obstetricians since it depends on nuanced clinical aspects, which increases the difficulty in identifying relevant features of the fetal anatomy. Thus, to assist with its accurate feature extraction, a lightweight artificial intelligence architecture leveraging convolutional neural networks and attention mechanisms is proposed to classify the largest benchmark ultrasound dataset. The approach fine-tunes from lightweight EfficientNet feature extraction backbones pre-trained on the ImageNet1k. to classify key fetal planes such as the brain, femur, thorax, cervix, and abdomen. Our methodology incorporates the attention mechanism to refine features and 3-layer perceptrons for classification, achieving superior performance with the highest Top-1 accuracy of 96.25%, Top-2 accuracy of 99.80% and F1-Score of 0.9576. Importantly, the model has 40x fewer trainable parameters than existing benchmark ensemble or transformer pipelines, facilitating easy deployment on edge devices to help clinical practitioners with real-time FPC. The findings are also interpreted using GradCAM to carry out clinical correlation to aid doctors with diagnostics and improve treatment plans for expectant mothers., Comment: Submitted to Computers in Biology and Medicine journal

The complementary information found in different modalities of patient data can aid in more accurate modelling of a patient's disease state and a better understanding of the underlying biological processes of a disease. However, the analysis of multi-modal, multi-omics data presents many challenges, including high dimensionality and varying size, statistical distribution, scale and signal strength between modalities. In this work we compare the performance of a variety of ensemble machine learning algorithms that are capable of late integration of multi-class data from different modalities. The ensemble methods and their variations tested were i) a voting ensemble, with hard and soft vote, ii) a meta learner, iii) a multi-modal Adaboost model using a hard vote, a soft vote and a meta learner to integrate the modalities on each boosting round, the PB-MVBoost model and a novel application of a mixture of experts model. These were compared to simple concatenation as a baseline. We examine these methods using data from an in-house study on hepatocellular carcinoma (HCC), along with four validation datasets on studies from breast cancer and irritable bowel disease (IBD). Using the area under the receiver operating curve as a measure of performance we develop models that achieve a performance value of up to 0.85 and find that two boosted methods, PB-MVBoost and Adaboost with a soft vote were the overall best performing models. We also examine the stability of features selected, and the size of the clinical signature determined. Finally, we provide recommendations for the integration of multi-modal multi-class data., Comment: 21 pages, 5 figures

The role of large language models (LLMs) in education is an increasing area of interest today, considering the new opportunities they offer for teaching, learning, and assessment. This cutting-edge tutorial provides an overview of the educational applications of NLP and the impact that the recent advances in LLMs have had on this field. We will discuss the key challenges and opportunities presented by LLMs, grounding them in the context of four major educational applications: reading, writing, and speaking skills, and intelligent tutoring systems (ITS). This COLING 2025 tutorial is designed for researchers and practitioners interested in the educational applications of NLP and the role LLMs have to play in this area. It is the first of its kind to address this timely topic., Comment: COLING 2025 Tutorial

Scientists increasingly recognize the importance of providing rich, standards-adherent metadata to describe their experimental results. Despite the availability of sophisticated tools to assist in the process of data annotation, investigators generally seem to prefer to use spreadsheets when supplying metadata, despite the limitations of spreadsheets in ensuring metadata consistency and compliance with formal specifications. In this paper, we describe an end-to-end approach that supports spreadsheet-based entry of metadata, while ensuring rigorous adherence to community-based metadata standards and providing quality control. Our methods employ several key components, including customizable templates that capture metadata standards and that can inform the spreadsheets that investigators use to author metadata, controlled terminologies and ontologies for defining metadata values that can be accessed directly from a spreadsheet, and an interactive Web-based tool that allows users to rapidly identify and fix errors in their spreadsheet-based metadata. We demonstrate how this approach is being deployed in a biomedical consortium known as HuBMAP to define and collect metadata about a wide range of biological assays.

We present an open source Python library for simulating overlapping (i.e., blended) images of galaxies and performing self-consistent comparisons of detection and deblending algorithms based on a suite of metrics. The package, named Blending Toolkit (BTK), serves as a modular, flexible, easy-to-install, and simple-to-use interface for exploring and analyzing systematic effects related to blended galaxies in cosmological surveys such as the Vera Rubin Observatory Legacy Survey of Space and Time (LSST). BTK has three main components: (1) a set of modules that perform fast image simulations of blended galaxies, using the open source image simulation package GalSim; (2) a module that standardizes the inputs and outputs of existing deblending algorithms; (3) a library of deblending metrics commonly defined in the galaxy deblending literature. In combination, these modules allow researchers to explore the impacts of galaxy blending in cosmological surveys. Additionally, BTK provides researchers who are developing a new deblending algorithm a framework to evaluate algorithm performance and make principled comparisons with existing deblenders. BTK includes a suite of tutorials and comprehensive documentation. The source code is publicly available on GitHub at https://github.com/LSSTDESC/BlendingToolKit., Comment: 15 pages, 9 figures, 2 tables, accepted to The Open Journal of Astrophysics

Retinal imaging has emerged as a promising method of addressing this challenge, taking advantage of the unique structure of the retina. The retina is an embryonic extension of the central nervous system, providing a direct in vivo window into neurological health. Recent studies have shown that specific structural changes in retinal vessels can not only serve as early indicators of various diseases but also help to understand disease progression. In this work, we present a lightweight retinal vessel segmentation network based on the encoder-decoder mechanism with region-guided attention. We introduce inverse addition attention blocks with region guided attention to focus on the foreground regions and improve the segmentation of regions of interest. To further boost the model's performance on retinal vessel segmentation, we employ a weighted dice loss. This choice is particularly effective in addressing the class imbalance issues frequently encountered in retinal vessel segmentation tasks. Dice loss penalises false positives and false negatives equally, encouraging the model to generate more accurate segmentation with improved object boundary delineation and reduced fragmentation. Extensive experiments on a benchmark dataset show better performance (0.8285, 0.8098, 0.9677, and 0.8166 recall, precision, accuracy and F1 score respectively) compared to state-of-the-art methods.

Skin diseases affect over a third of the global population, yet their impact is often underestimated. Automating skin disease classification to assist doctors with their prognosis might be difficult. Nevertheless, due to efficient feature extraction pipelines, deep learning techniques have shown much promise for various tasks, including dermatological disease identification. This study uses a skin disease dataset with 31 classes and compares it with all versions of Vision Transformers, Swin Transformers and DivoV2. The analysis is also extended to compare with benchmark convolution-based architecture presented in the literature. Transfer learning with ImageNet1k weights on the skin disease dataset contributes to a high test accuracy of 96.48\% and an F1-Score of 0.9727 using DinoV2, which is almost a 10\% improvement over this data's current benchmark results. The performance of DinoV2 was also compared for the HAM10000 and Dermnet datasets to test the model's robustness, and the trained model overcomes the benchmark results by a slight margin in test accuracy and in F1-Score on the 23 and 7 class datasets. The results are substantiated using explainable AI frameworks like GradCAM and SHAP, which provide precise image locations to map the disease, assisting dermatologists in early detection, prompt prognosis, and treatment., Comment: Submitted to Computers in Biology and Medicine

Animal populations worldwide are rapidly declining, and a technology that can accurately count endangered species could be vital for monitoring population changes over several years. This research focused on fine-tuning object detection models for drone images to create accurate counts of animal species. Hundreds of images taken using a drone and large, openly available drone-image datasets were used to fine-tune machine learning models with the baseline YOLOv8 architecture. We trained 30 different models, with the largest having 43.7 million parameters and 365 layers, and used hyperparameter tuning and data augmentation techniques to improve accuracy. While the state-of-the-art YOLOv8 baseline had only 0.7% accuracy on a dataset of safari animals, our models had 95% accuracy on the same dataset. Finally, we deployed the models on the Jetson Orin Nano for demonstration of low-power real-time species detection for easy inference on drones.

Named Entity Recognition (NER) is a well-studied problem in NLP. However, there is much less focus on studying NER datasets, compared to developing new NER models. In this paper, we employed three simple techniques to detect annotation errors in the OntoNotes 5.0 corpus for English NER, which is the largest available NER corpus for English. Our techniques corrected ~10% of the sentences in train/dev/test data. In terms of entity mentions, we corrected the span and/or type of ~8% of mentions in the dataset, while adding/deleting/splitting/merging a few more. These are large numbers of changes, considering the size of OntoNotes. We used three NER libraries to train, evaluate and compare the models trained with the original and the re-annotated datasets, which showed an average improvement of 1.23% in overall F-scores, with large (>10%) improvements for some of the entity types. While our annotation error detection methods are not exhaustive and there is some manual annotation effort involved, they are largely language agnostic and can be employed with other NER datasets, and other sequence labelling tasks., Comment: Unpublished report. Originally submitted to LREC 2022

The Universal Dependencies (UD) project aims to create a cross-linguistically consistent dependency annotation for multiple languages, to facilitate multilingual NLP. It currently supports 114 languages. Dravidian languages are spoken by over 200 million people across the word, and yet there are only two languages from this family in UD. This paper examines some of the morphological and syntactic features of Dravidian languages and explores how they can be annotated in the UD framework., Comment: unpublished report from 2021

Stochastic optimization algorithms have been successfully applied in several domains to find optimal solutions. Because of the ever-growing complexity of the integrated systems, novel stochastic algorithms are being proposed, which makes the task of the performance analysis of the algorithms extremely important. In this paper, we provide a novel ranking scheme to rank the algorithms over multiple single-objective optimization problems. The results of the algorithms are compared using a robust bootstrapping-based hypothesis testing procedure that is based on the principles of severity. Analogous to the football league scoring scheme, we propose pairwise comparison of algorithms as in league competition. Each algorithm accumulates points and a performance metric of how good or bad it performed against other algorithms analogous to goal differences metric in football league scoring system. The goal differences performance metric can not only be used as a tie-breaker but also be used to obtain a quantitative performance of each algorithm. The key novelty of the proposed ranking scheme is that it takes into account the performance of each algorithm considering the magnitude of the achieved performance improvement along with its practical relevance and does not have any distributional assumptions. The proposed ranking scheme is compared to classical hypothesis testing and the analysis of the results shows that the results are comparable and our proposed ranking showcases many additional benefits.

Accurate segmentation of anatomical structures and abnormalities in medical images is crucial for computer-aided diagnosis and analysis. While deep learning techniques excel at this task, their computational demands pose challenges. Additionally, some cutting-edge segmentation methods, though effective for general object segmentation, may not be optimised for medical images. To address these issues, we propose Mini-Net, a lightweight segmentation network specifically designed for medical images. With fewer than 38,000 parameters, Mini-Net efficiently captures both high- and low-frequency features, enabling real-time applications in various medical imaging scenarios. We evaluate Mini-Net on various datasets, including DRIVE, STARE, ISIC-2016, ISIC-2018, and MoNuSeg, demonstrating its robustness and good performance compared to state-of-the-art methods.

The prevalence of unwarranted beliefs, spanning pseudoscience, logical fallacies, and conspiracy theories, presents substantial societal hurdles and the risk of disseminating misinformation. Utilizing established psychometric assessments, this study explores the capabilities of large language models (LLMs) vis-a-vis the average human in detecting prevalent logical pitfalls. We undertake a philosophical inquiry, juxtaposing the rationality of humans against that of LLMs. Furthermore, we propose methodologies for harnessing LLMs to counter misconceptions, drawing upon psychological models of persuasion such as cognitive dissonance theory and elaboration likelihood theory. Through this endeavor, we highlight the potential of LLMs as personalized misinformation debunking agents., Comment: Under review

Given two images, we can estimate the relative camera pose between them by establishing image-to-image correspondences. Usually, correspondences are 2D-to-2D and the pose we estimate is defined only up to scale. Some applications, aiming at instant augmented reality anywhere, require scale-metric pose estimates, and hence, they rely on external depth estimators to recover the scale. We present MicKey, a keypoint matching pipeline that is able to predict metric correspondences in 3D camera space. By learning to match 3D coordinates across images, we are able to infer the metric relative pose without depth measurements. Depth measurements are also not required for training, nor are scene reconstructions or image overlap information. MicKey is supervised only by pairs of images and their relative poses. MicKey achieves state-of-the-art performance on the Map-Free Relocalisation benchmark while requiring less supervision than competing approaches.

Metadata play a crucial role in ensuring the findability, accessibility, interoperability, and reusability of datasets. This paper investigates the potential of large language models (LLMs), specifically GPT-4, to improve adherence to metadata standards. We conducted experiments on 200 random data records describing human samples relating to lung cancer from the NCBI BioSample repository, evaluating GPT-4's ability to suggest edits for adherence to metadata standards. We computed the adherence accuracy of field name-field value pairs through a peer review process, and we observed a marginal average improvement in adherence to the standard data dictionary from 79% to 80% (p<0.5). We then prompted GPT-4 with domain information in the form of the textual descriptions of CEDAR templates and recorded a significant improvement to 97% from 79% (p<0.01). These results indicate that, while LLMs may not be able to correct legacy metadata to ensure satisfactory adherence to standards when unaided, they do show promise for use in automated metadata curation when integrated with a structured knowledge base

Sentences containing multiple semantic operators with overlapping scope often create ambiguities in interpretation, known as scope ambiguities. These ambiguities offer rich insights into the interaction between semantic structure and world knowledge in language processing. Despite this, there has been little research into how modern large language models treat them. In this paper, we investigate how different versions of certain autoregressive language models -- GPT-2, GPT-3/3.5, Llama 2 and GPT-4 -- treat scope ambiguous sentences, and compare this with human judgments. We introduce novel datasets that contain a joint total of almost 1,000 unique scope-ambiguous sentences, containing interactions between a range of semantic operators, and annotated for human judgments. Using these datasets, we find evidence that several models (i) are sensitive to the meaning ambiguity in these sentences, in a way that patterns well with human judgments, and (ii) can successfully identify human-preferred readings at a high level of accuracy (over 90% in some cases)., Comment: To be published in Transactions of the Association for Computational Linguistics

Much of the research in online moderation focuses on punitive actions. However, emerging research has shown that positive reinforcement is effective at encouraging desirable behavior on online platforms. We extend this research by studying the "creator heart" feature on YouTube, quantifying their primary effects on comments that receive hearts and on videos where hearts have been given. We find that creator hearts increased the visibility of comments, and increased the amount of positive engagement they received from other users. We also find that the presence of a creator hearted comment soon after a video is published can incentivize viewers to comment, increasing the total engagement with the video over time. We discuss the potential for creators to use hearts to shape behavior in their communities by highlighting, rewarding, and incentivizing desirable behaviors from users. We discuss avenues for extending our study to understanding positive signals from moderators on other platforms.