Search

Clinnova, a collaborative initiative involving France, Germany, Switzerland, and Luxembourg, is dedicated to unlocking the power of precision medicine through data federation, standardization, and interoperability. This European Greater Region initiative seeks to create an interoperable European standard using artificial intelligence (AI) and data science to enhance healthcare outcomes and efficiency. Key components include multidisciplinary research centers, a federated biobanking strategy, a digital health innovation platform, and a federated AI strategy. It targets inflammatory bowel disease, rheumatoid diseases, and multiple sclerosis (MS), emphasizing data quality to develop AI algorithms for personalized treatment and translational research. The IHU Strasbourg (Institute of Minimal-invasive Surgery) has the lead in this initiative to develop the federated learning (FL) proof of concept (POC) that will serve as a foundation for advancing AI in healthcare. At its core, Clinnova-MS aims to enhance MS patient care by using FL to develop more accurate models that detect disease progression, guide interventions, and validate digital biomarkers across multiple sites. This technical report presents insights and key takeaways from the first cross-border federated POC on MS segmentation of MRI images within the Clinnova framework. While our work marks a significant milestone in advancing MS segmentation through cross-border collaboration, it also underscores the importance of addressing technical, logistical, and ethical considerations to realize the full potential of FL in healthcare settings.

As cities adopt sustainable mobility solutions, electric scooters (e-scooters) offer both challenges and opportunities for public transportation systems. This study, the first in Latin America, examines the effects of e-scooters on public transport demand in Santiago, Chile, focusing on two scenarios: "generation" of trips (trips starting in study zones) and "attraction" of trips (trips ending in study zones). A negative binomial regression model was applied to data from public transport smart cards and e-scooter GPS. The methodology included urban area clustering and a differences-in-differences approach. The findings reveal significant regional differences: in the Central Region, public transport trips decreased by 21.38% in the generation scenario, while bus trips increased by 76.39%. In the Intermediate Region, metro trips increased by 70.05%, and in the Peripheral Region, bus trips increased by 84.64%. These results suggest that e-scooters reduce public transport usage in highly accessible areas but increase it in less accessible regions., Comment: 62 pages, 12 figures. Submitted to Transport Research Part D

The task of determining whether two texts are paraphrases has long been a challenge in NLP. However, the prevailing notion of paraphrase is often quite simplistic, offering only a limited view of the vast spectrum of paraphrase phenomena. Indeed, we find that evaluating models in a paraphrase dataset can leave uncertainty about their true semantic understanding. To alleviate this, we release paraphrasus, a benchmark designed for multi-dimensional assessment of paraphrase detection models and finer model selection. We find that paraphrase detection models under a fine-grained evaluation lens exhibit trade-offs that cannot be captured through a single classification dataset.

Interplanetary shocks are one of the crucial dynamic phenomena in the Heliosphere. They accelerate particles to high energies, generate plasma waves, and can trigger geomagnetic storms in the terrestrial magnetosphere disturbing significantly our technological infrastructures. In this study, two IP shock events are selected to study the temporal variations of the shock parameters using magnetometer and ion plasma measurements of the STEREO$-$A and B, the Wind, Cluster fleet, and the ACE spacecraft. The shock normal vectors are determined using the minimum variance analysis (MVA) and the magnetic coplanarity methods. During the May 7, 2007 event, the shock parameters and the shock normal direction are consistent. The shock surface appears to be tilted almost the same degree as the Parker spiral, and the driver could be a Co--Rotating Interacting Region (CIR). During the April 23, 2007 event, the shock parameters do not change significantly except for the shock $\theta_{Bn}$ angle, however, the shape of the IP shock appears to be twisted along the perpendicular direction to the Sun-Earth line as well. The driver of this rippled shock is Stream Interaction Regions (SIRs)/CISs as well., Comment: 31 pages, 14 figures, 6 table, submitted to the Astrophysical Journal on July 17, 2024. arXiv admin note: substantial text overlap with arXiv:2307.03328

We review some recent development in the theory of spatial extremes related to Pareto Processes and modeling of threshold exceedances. We provide theoretical background, methodology for modeling, simulation and inference as well as an illustration to wave height modelling. This preprint is an author version of a chapter to appear in a collaborative book.

Objective: Federated Learning (FL) enables collaborative model training while keeping data locally. Currently, most FL studies in radiology are conducted in simulated environments due to numerous hurdles impeding its translation into practice. The few existing real-world FL initiatives rarely communicate specific measures taken to overcome these hurdles, leaving behind a significant knowledge gap. Minding efforts to implement real-world FL, there is a notable lack of comprehensive assessment comparing FL to less complex alternatives. Materials & Methods: We extensively reviewed FL literature, categorizing insights along with our findings according to their nature and phase while establishing a FL initiative, summarized to a comprehensive guide. We developed our own FL infrastructure within the German Radiological Cooperative Network (RACOON) and demonstrated its functionality by training FL models on lung pathology segmentation tasks across six university hospitals. We extensively evaluated FL against less complex alternatives in three distinct evaluation scenarios. Results: The proposed guide outlines essential steps, identified hurdles, and proposed solutions for establishing successful FL initiatives conducting real-world experiments. Our experimental results show that FL outperforms less complex alternatives in all evaluation scenarios, justifying the effort required to translate FL into real-world applications. Discussion & Conclusion: Our proposed guide aims to aid future FL researchers in circumventing pitfalls and accelerating translation of FL into radiological applications. Our results underscore the value of efforts needed to translate FL into real-world applications by demonstrating advantageous performance over alternatives, and emphasize the importance of strategic organization, robust management of distributed data and infrastructure in real-world settings.

Large Language Models (LLMs) have become capable of generating highly fluent text in certain languages, without modules specially designed to capture grammar or semantic coherence. What does this mean for the future of linguistic expertise in NLP? We highlight several aspects in which NLP (still) relies on linguistics, or where linguistic thinking can illuminate new directions. We argue our case around the acronym RELIES that encapsulates six major facets where linguistics contributes to NLP: Resources, Evaluation, Low-resource settings, Interpretability, Explanation, and the Study of language. This list is not exhaustive, nor is linguistics the main point of reference for every effort under these themes; but at a macro level, these facets highlight the enduring importance of studying machine systems vis-\`a-vis systems of human language.

Classification systems are evaluated in a countless number of papers. However, we find that evaluation practice is often nebulous. Frequently, metrics are selected without arguments, and blurry terminology invites misconceptions. For instance, many works use so-called 'macro' metrics to rank systems (e.g., 'macro F1') but do not clearly specify what they would expect from such a `macro' metric. This is problematic, since picking a metric can affect research findings, and thus any clarity in the process should be maximized. Starting from the intuitive concepts of bias and prevalence, we perform an analysis of common evaluation metrics. The analysis helps us understand the metrics' underlying properties, and how they align with expectations as found expressed in papers. Then we reflect on the practical situation in the field, and survey evaluation practice in recent shared tasks. We find that metric selection is often not supported with convincing arguments, an issue that can make a system ranking seem arbitrary. Our work aims at providing overview and guidance for more informed and transparent metric selection, fostering meaningful evaluation., Comment: appeared in TACL journal. MIT press publication available at https://doi.org/10.1162/tacl_a_00675

The Area Under Curve measure (AUC) seems apt to evaluate and compare diverse models, possibly without calibration. An important example of AUC application is the evaluation and benchmarking of models that predict faithfulness of generated text. But we show that the AUC yields an academic and optimistic notion of accuracy that can misalign with the actual accuracy observed in application, yielding significant changes in benchmark rankings. To paint a more realistic picture of downstream model performance (and prepare a model for actual application), we explore different calibration modes, testing calibration data and method., Comment: LREC-COLING 2024, added more details on data setups, fixed typo

At the heart of the Pyramid evaluation method for text summarization lie human written summary content units (SCUs). These SCUs are concise sentences that decompose a summary into small facts. Such SCUs can be used to judge the quality of a candidate summary, possibly partially automated via natural language inference (NLI) systems. Interestingly, with the aim to fully automate the Pyramid evaluation, Zhang and Bansal (2021) show that SCUs can be approximated by automatically generated semantic role triplets (STUs). However, several questions currently lack answers, in particular: i) Are there other ways of approximating SCUs that can offer advantages? ii) Under which conditions are SCUs (or their approximations) offering the most value? In this work, we examine two novel strategies to approximate SCUs: generating SCU approximations from AMR meaning representations (SMUs) and from large language models (SGUs), respectively. We find that while STUs and SMUs are competitive, the best approximation quality is achieved by SGUs. We also show through a simple sentence-decomposition baseline (SSUs) that SCUs (and their approximations) offer the most value when ranking short summaries, but may not help as much when ranking systems or longer summaries., Comment: 10 Pages, 3 Figures, 3 Tables, camera ready version accepted at NAACL 2024

We present statistical analysis of visual meteor data taken with networks of meteor cameras operating in Hungary between 2020 and 2023. We use three different camera systems: a set of traditional MetRec-based video cameras, a self-developed automated DSLR camera system and a network of newly installed AllSky7 camera stations. Similarities and differences between the data produced by the three systems, aimed at recording different types of meteor phenomena, are presented and discussed., Comment: accepted for publication in WGN, the Journal of the International Meteor Organization (IMO)

This research explores strategies for steering the output of large language models (LLMs) towards specific styles, such as sentiment, emotion, or writing style, by adding style vectors to the activations of hidden layers during text generation. We show that style vectors can be simply computed from recorded layer activations for input texts in a specific style in contrast to more complex training-based approaches. Through a series of experiments, we demonstrate the effectiveness of activation engineering using such style vectors to influence the style of generated text in a nuanced and parameterisable way, distinguishing it from prompt engineering. The presented research constitutes a significant step towards developing more adaptive and effective AI-empowered interactive systems., Comment: Will be published as findings paper at EACL2024 - 18th Conference of the European Chapter of the Association for Computational Linguistics

Environmental data science for spatial extremes has traditionally relied heavily on max-stable processes. Even though the popularity of these models has perhaps peaked with statisticians, they are still perceived and considered as the `state-of-the-art' in many applied fields. However, while the asymptotic theory supporting the use of max-stable processes is mathematically rigorous and comprehensive, we think that it has also been overused, if not misused, in environmental applications, to the detriment of more purposeful and meticulously validated models. In this paper, we review the main limitations of max-stable process models, and strongly argue against their systematic use in environmental studies. Alternative solutions based on more flexible frameworks using the exceedances of variables above appropriately chosen high thresholds are discussed, and an outlook on future research is given, highlighting recommendations moving forward and the opportunities offered by hybridizing machine learning with extreme-value statistics.

The surface molecular doping of organic semiconductors can play an important role in the development of organic electronic or optoelectronic devices. Single-crystal rubrene remains a leading molecular candidate for applications in electronics due to its high hole mobility. In parallel, intensive research into the fabrication of flexible organic electronics requires the careful design of functional interfaces to enable optimal device characteristics. To this end, the present work seeks to understand the effect of surface molecular doping on the electronic band structure of rubrene single crystals. Our angle-resolved photoemission measurements reveal that the Fermi level moves in the band gap of rubrene depending on the direction of surface electron-transfer reactions with the molecular dopants, yet the valence band dispersion remains essentially unperturbed. This indicates that surface electron-transfer doping of a molecular single crystal can effectively modify the near-surface charge density, while retaining good charge-carrier mobility., Comment: 28 pages, 11 figures

Citizen science mobilises many observers and gathers huge datasets but often without strict sampling protocols, resulting in observation biases due to heterogeneous sampling effort, which can lead to biased statistical inferences. We develop a spatiotemporal Bayesian hierarchical model for bias-corrected estimation of arrival dates of the first migratory bird individuals at a breeding site. Higher sampling effort could be correlated with earlier observed dates. We implement data fusion of two citizen-science datasets with fundamentally different protocols (BBS, eBird) and map posterior distributions of the latent process, which contains four spatial components with Gaussian process priors: species niche; sampling effort; position and scale parameters of annual first arrival date. The data layer includes four response variables: counts of observed eBird locations (Poisson); presence-absence at observed eBird locations (Binomial); BBS occurrence counts (Poisson); first arrival dates (Generalised Extreme-Value). We devise a Markov Chain Monte Carlo scheme and check by simulation that the latent process components are identifiable. We apply our model to several migratory bird species in the northeastern US for 2001--2021 and find that the sampling effort significantly modulates the observed first arrival date. We exploit this relationship to effectively bias-correct predictions of the true first arrivals.

With an increasing number of parameters and pre-training data, generative large language models (LLMs) have shown remarkable capabilities to solve tasks with minimal or no task-related examples. Notably, LLMs have been successfully employed as evaluation metrics in text generation tasks. Within this context, we introduce the Eval4NLP 2023 shared task that asks participants to explore prompting and score extraction for machine translation (MT) and summarization evaluation. Specifically, we propose a novel competition setting in which we select a list of allowed LLMs and disallow fine-tuning to ensure a focus on prompting. We present an overview of participants' approaches and evaluate them on a new reference-free test set spanning three language pairs for MT and a summarization dataset. Notably, despite the task's restrictions, the best-performing systems achieve results on par with or even surpassing recent reference-free metrics developed using larger models, including GEMBA and Comet-Kiwi-XXL. Finally, as a separate track, we perform a small-scale human evaluation of the plausibility of explanations given by the LLMs.

We introduce the extremal range, a local statistic for studying the spatial extent of extreme events in random fields on $\mathbb{R}^2$. Conditioned on exceedance of a high threshold at a location $s$, the extremal range at $s$ is the random variable defined as the smallest distance from $s$ to a location where there is a non-exceedance. We leverage tools from excursion-set theory to study distributional properties of the extremal range, propose parametric models and predict the median extremal range at extreme threshold levels. The extremal range captures the rate at which the spatial extent of conditional extreme events scales for increasingly high thresholds, and we relate its distributional properties with the bivariate tail dependence coefficient and the extremal index of time series in classical Extreme-Value Theory. Consistent estimation of the distribution function of the extremal range for stationary random fields is proven. For non-stationary random fields, we implement generalized additive median regression to predict extremal-range maps at very high threshold levels. An application to two large daily temperature datasets, namely reanalyses and climate-model simulations for France, highlights decreasing extremal dependence for increasing threshold levels and reveals strong differences in joint tail decay rates between reanalyses and simulations., Comment: 32 pages, 5 figures

We are interested in creating statistical methods to provide informative summaries of random fields through the geometry of their excursion sets. To this end, we introduce an estimator for the length of the perimeter of excursion sets of random fields on $\mathbb{R}^2$ observed over regular square tilings. The proposed estimator acts on the empirically accessible binary digital images of the excursion regions and computes the length of a piecewise linear approximation of the excursion boundary. The estimator is shown to be consistent as the pixel size decreases, without the need of any normalization constant, and with neither assumption of Gaussianity nor isotropy imposed on the underlying random field. In this general framework, even when the domain grows to cover $\mathbb{R}^2$, the estimation error is shown to be of smaller order than the side length of the domain. For affine, strongly mixing random fields, this translates to a multivariate Central Limit Theorem for our estimator when multiple levels are considered simultaneously. Finally, we conduct several numerical studies to investigate statistical properties of the proposed estimator in the finite-sample data setting., Comment: 35 pages, 17 figures

The effectiveness of compression in text classification ('gzip') has recently garnered lots of attention. In this note we show that `bag-of-words' approaches can achieve similar or better results, and are more efficient., Comment: improved writing, extended with more results

The task of natural language inference (NLI) asks whether a given premise (expressed in NL) entails a given NL hypothesis. NLI benchmarks contain human ratings of entailment, but the meaning relationships driving these ratings are not formalized. Can the underlying sentence pair relationships be made more explicit in an interpretable yet robust fashion? We compare semantic structures to represent premise and hypothesis, including sets of contextualized embeddings and semantic graphs (Abstract Meaning Representations), and measure whether the hypothesis is a semantic substructure of the premise, utilizing interpretable metrics. Our evaluation on three English benchmarks finds value in both contextualized embeddings and semantic graphs; moreover, they provide complementary signals, and can be leveraged together in a hybrid model., Comment: International Conference on Computational Semantics (IWCS 2023); v2 fixes an imprecise sentence below Eq. 5

Conditional language models still generate unfaithful output that is not supported by their input. These unfaithful generations jeopardize trust in real-world applications such as summarization or human-machine interaction, motivating a need for automatic faithfulness metrics. To implement such metrics, NLI models seem attractive, since they solve a strongly related task that comes with a wealth of prior research and data. But recent research suggests that NLI models require costly additional machinery to perform reliably across datasets, e.g., by running inference on a cartesian product of input and generated sentences, or supporting them with a question-generation/answering step. In this work we show that pure NLI models _can_ outperform more complex metrics when combining task-adaptive data augmentation with robust inference procedures. We propose: (1) Augmenting NLI training data to adapt NL inferences to the specificities of faithfulness prediction in dialogue; (2) Making use of both entailment and contradiction probabilities in NLI, and (3) Using Monte-Carlo dropout during inference. Applied to the TRUE benchmark, which combines faithfulness datasets across diverse domains and tasks, our approach strongly improves a vanilla NLI model and significantly outperforms previous work, while showing favourable computational cost., Comment: ACL 2023 (short paper)

Arguments often do not make explicit how a conclusion follows from its premises. To compensate for this lack, we enrich arguments with structured background knowledge to support knowledge-intense argumentation tasks. We present a new unsupervised method for constructing Contextualized Commonsense Knowledge Graphs (CCKGs) that selects contextually relevant knowledge from large knowledge graphs (KGs) efficiently and at high quality. Our work goes beyond context-insensitive knowledge extraction heuristics by computing semantic similarity between KG triplets and textual arguments. Using these triplet similarities as weights, we extract contextualized knowledge paths that connect a conclusion to its premise, while maximizing similarity to the argument. We combine multiple paths into a CCKG that we optionally prune to reduce noise and raise precision. Intrinsic evaluation of the quality of our graphs shows that our method is effective for (re)constructing human explanation graphs. Manual evaluations in a large-scale knowledge selection setup confirm high recall and precision of implicit CSK in the CCKGs. Finally, we demonstrate the effectiveness of CCKGs in a knowledge-insensitive argument quality rating task, outperforming strong baselines and rivaling a GPT-3 based system., Comment: Accepted at ACL 2023

The Smatch metric is a popular method for evaluating graph distances, as is necessary, for instance, to assess the performance of semantic graph parsing systems. However, we observe some issues in the metric that jeopardize meaningful evaluation. E.g., opaque pre-processing choices can affect results, and current graph-alignment solvers do not provide us with upper-bounds. Without upper-bounds, however, fair evaluation is not guaranteed. Furthermore, adaptions of Smatch for extended tasks (e.g., fine-grained semantic similarity) are spread out, and lack a unifying framework. For better inspection, we divide the metric into three modules: pre-processing, alignment, and scoring. Examining each module, we specify its goals and diagnose potential issues, for which we discuss and test mitigation strategies. For pre-processing, we show how to fully conform to annotation guidelines that allow structurally deviating but valid graphs. For safer and enhanced alignment, we show the feasibility of optimal alignment in a standard evaluation setup, and develop a lossless graph compression method that shrinks the search space and significantly increases efficiency. For improved scoring, we propose standardized and extended metric calculation of fine-grained sub-graph meaning aspects. Our code is available at https://github.com/flipz357/smatchpp, Comment: EACL 2023 findings, Code: https://github.com/flipz357/smatchpp