Search

The theory of interfacial properties in liquid-liquid or liquid-vapour systems is nearly 200 years old. The advent of computational tools has greatly advanced the field, mainly through the use of Molecular Dynamics simulations. Despite the successes and advances in the theory of interfacial phenomena for liquid-liquid systems, the study of solid-liquid interfaces remains a challenge both theoretically and experimentally. The main reason why the treatment of solid-liquid systems has fallen behind that of liquid-liquid systems is that there are complications that arise whenever an interface involving solid systems is considered involving both theory of the solid-liquid interface and the calculations using MD simulations. An example of the former is that, contrary to the liquid-liquid case, the interfacial properties of solids depend on the lattice orientation. The main complications in these calculations arise from the fact that for solids the ``mechanical route'' cannot be used. To overcome this problem, several numerical approaches were proposed. The main purpose of this review is to provide an overview of these different methodologies and to discuss their strengths and weaknesses. We classify these methodologies into two main groups: direct and indirect methods. Direct methods are those that can calculate directly the properties of interfaces, while in indirect approaches the properties of the interface are not the primary result of the simulations. We also included a discussion on the origin of the difficulties in considering solid interfaces from a thermodynamic point of view. In the second part of the review, we discuss two key related topics: nucleation theory and curved interfaces. They both represent an important problem in the study of interfaces and in the context of solid-liquid ones for which the research is still extremely active., Comment: 111 pages, 14 figures

The study of the structure and mechanical properties of complex fluid interfaces has gained increasing interest in recent decades as a result of its significant scientific relevance to the understanding of biological systems, drug development, and industrial applications. The in situ combination of molecular-level structural measurements with the assessment of dynamical (rheological) properties is particularly valuable, as comparing measurements conducted on separate samples under challenging-to-reproduce experimental conditions can be problematic. In this work, we present a new sample environment at the FIGARO instrument, the horizontal neutron reflectometer at the Institut Laue-Langevin, which includes an interfacial shear rheometer operating in the Double Wall-Ring (DWR) geometry, compatible with commercial rotational rheometers. This innovative setup enables simultaneous structural (neutron reflectometry) and dynamical (shear interfacial rheology) measurements on the same sample.

\textbf{Trial design} Crossover randomized controlled trial. \textbf{Methods} An AI tool, Easy-ICD, was developed to assist clinical coders and was tested for improving both accuracy and time in a user study in Norway and Sweden. Participants were randomly assigned to two groups, and crossed over between coding complex (longer) texts versus simple (shorter) texts, while using our tool versus not using our tool. \textbf{Results} Based on Mann-Whitney U test, the median coding time difference for complex clinical text sequences was 123 seconds (\emph{P}\textless.001, 95\% CI: 81 to 164), representing a 46\% reduction in median coding time when our tool is used. There was no significant time difference for simpler text sequences. For coding accuracy, the improvement we noted for both complex and simple texts was not significant. \textbf{Conclusions} This study demonstrates the potential of AI to transform common tasks in clinical workflows, with ostensible positive impacts on work efficiencies for complex clinical coding tasks. Further studies within hospital workflows are required before these presumed impacts can be more clearly understood., Comment: 13 pages, 4 figures, 4 tables

Evaluating diffusion-based image-editing models is a crucial task in the field of Generative AI. Specifically, it is imperative to assess their capacity to execute diverse editing tasks while preserving the image content and realism. While recent developments in generative models have opened up previously unheard-of possibilities for image editing, conducting a thorough evaluation of these models remains a challenging and open task. The absence of a standardized evaluation benchmark, primarily due to the inherent need for a post-edit reference image for evaluation, further complicates this issue. Currently, evaluations often rely on established models such as CLIP or require human intervention for a comprehensive understanding of the performance of these image editing models. Our benchmark, PixLens, provides a comprehensive evaluation of both edit quality and latent representation disentanglement, contributing to the advancement and refinement of existing methodologies in the field., Comment: 35 pages (17 main paper, 18 appendix), 22 figures

Speech recordings are being more frequently used to detect and monitor disease, leading to privacy concerns. Beyond cryptography, protection of speech can be addressed by approaches, such as perturbation, disentanglement, and re-synthesis, that eliminate sensitive information of the speaker, leaving the information necessary for medical analysis purposes. In order for such privacy protective approaches to be developed, clear and systematic specifications of assumptions concerning medical settings and the needs of medical professionals are necessary. In this paper, we propose a Scenario of Use Scheme that incorporates an Attacker Model, which characterizes the adversary against whom the speaker's privacy must be defended, and a Protector Model, which specifies the defense. We discuss the connection of the scheme with previous work on speech privacy. Finally, we present a concrete example of a specified Scenario of Use and a set of experiments about protecting speaker data against gender inference attacks while maintaining utility for Parkinson's detection., Comment: Accepted and published at SPSC Symposium 2024 4th Symposium on Security and Privacy in Speech Communication. Interspeech 2024

We investigate the impact of introducing a local cavity within the center of a topological chain, revealing profound effects on the system's quantum states. Notably, the cavity induces a scissor-like effect that bisects the chain, liberating Majorana zero modes (MZMs) within the bulk. Our results demonstrate that this setup enables the observation of non-trivial fusion rules and braiding -- key signatures of non-Abelian anyons -- facilitated by the spatially selective ultra-strong coupling of the cavity photon field. These MZM characteristics can be directly probed through fermionic parity readouts and photon Berry phases, respectively. Furthermore, by leveraging the symmetry properties of fermion modes within a two-site cavity, we propose a novel method for generating MZM-polariton Schr\"odinger cat states. Our findings present a significant advancement in the control of topological quantum systems, offering new avenues for both fundamental research and potential quantum computing applications., Comment: Main text: 6 pages, 5 Figures, Supplemental Material: 8 pages, 5 Figures

Parkinson's disease (PD), the second most prevalent neurodegenerative disorder worldwide, frequently presents with early-stage speech impairments. Recent advancements in Artificial Intelligence (AI), particularly deep learning (DL), have significantly enhanced PD diagnosis through the analysis of speech data. Nevertheless, the progress of research is restricted by the limited availability of publicly accessible speech-based PD datasets, primarily due to privacy concerns. The goal of this systematic review is to explore the current landscape of speech-based DL approaches for PD classification, based on 33 scientific works published between January 2020 and March 2024. We discuss their available resources, capabilities, and potential limitations, and issues related to bias, explainability, and privacy. Furthermore, this review provides an overview of publicly accessible speech-based datasets and open-source material for PD. The DL approaches identified are categorized into end-to-end (E2E) learning, transfer learning (TL), and deep acoustic feature extraction (DAFE). Among E2E approaches, Convolutional Neural Networks (CNNs) are prevalent, though Transformers are increasingly popular. E2E approaches face challenges such as limited data and computational resources, especially with Transformers. TL addresses these issues by providing more robust PD diagnosis and better generalizability across languages. DAFE aims to improve the explainability and interpretability of results by examining the specific effects of deep features on both other DL approaches and more traditional machine learning (ML) methods. However, it often underperforms compared to E2E and TL approaches., Comment: van Gelderen, L., & Tejedor-Garc\'ia, C. (2024). Innovative Speech-Based Deep Learning Approaches for Parkinson's Disease Classification: A Systematic Review. Applied Sciences, 14(17). doi:10.3390/app14177873 This research was funded by the NWO research programme NGF AiNed Fellowship Grants under the project Responsible AI for Voice Diagnostics (RAIVD) - grant number NGF.1607.22.013

Automatic reading diagnosis systems can benefit both teachers for more efficient scoring of reading exercises and students for accessing reading exercises with feedback more easily. However, there are limited studies on Automatic Speech Recognition (ASR) for child speech in languages other than English, and limited research on ASR-based reading diagnosis systems. This study investigates how efficiently state-of-the-art (SOTA) pretrained ASR models recognize Dutch native children speech and manage to detect reading miscues. We found that Hubert Large finetuned on Dutch speech achieves SOTA phoneme-level child speech recognition (PER at 23.1\%), while Whisper (Faster Whisper Large-v2) achieves SOTA word-level performance (WER at 9.8\%). Our findings suggest that Wav2Vec2 Large and Whisper are the two best ASR models for reading miscue detection. Specifically, Wav2Vec2 Large shows the highest recall at 0.83, whereas Whisper exhibits the highest precision at 0.52 and an F1 score of 0.52., Comment: Proc. INTERSPEECH 2024, 1-5 September 2024. Kos Island, Greece

Polar activity is shown here to induce a progressive local deformation of linear polymer chains, making a clear distinction between head and tail, while the overall chain conformation gets more compact. This breakdown of self-similarity, provoked by the accumulated tension on the polymer backbone induced by the activity, is shown to occur both in the absence and presence of inertia, although it is stronger in the latter case. Other properties like the relaxation time and diffusion are also largely influenced by the presence of a polar activity., Comment: 6 pages, 4 figures

The article by Hawila & Berg (2023) that is going to be commented presents four relevant problems, apart from other less important ones that are also cited. First, the title is incorrect, since it leads readers to believe that the confidence interval defined is exact when in fact it is asymptotic. Second, contrary to what is assumed by the authors of the article, the statistic that they define is not monotonic in delta. But it is fundamental that this property is verified, as the authors themselves recognize. Third, the inferences provided by the confidence interval proposed may be incoherent, which could lead the scientific community to reach incorrect conclusions in any practical application. For example, for fixed data it might happen that a certain delta value is within the 90%-confidence interval, but outside the 95%-confidence interval. Fourth, the authors do not validate its statistic through a simulation with diverse (and credible) values of the parameters involved. In fact, one of its two examples is for an alpha error of 70%!, Comment: 6 pages

Monochromatic gamma-ray signals constitute a potential smoking gun signature for annihilating or decaying dark matter particles that could relatively easily be distinguished from astrophysical or instrumental backgrounds. We provide an updated assessment of the sensitivity of the Cherenkov Telescope Array (CTA) to such signals, based on observations of the Galactic centre region as well as of selected dwarf spheroidal galaxies. We find that current limits and detection prospects for dark matter masses above 300 GeV will be significantly improved, by up to an order of magnitude in the multi-TeV range. This demonstrates that CTA will set a new standard for gamma-ray astronomy also in this respect, as the world's largest and most sensitive high-energy gamma-ray observatory, in particular due to its exquisite energy resolution at TeV energies and the adopted observational strategy focussing on regions with large dark matter densities. Throughout our analysis, we use up-to-date instrument response functions, and we thoroughly model the effect of instrumental systematic uncertainties in our statistical treatment. We further present results for other potential signatures with sharp spectral features, e.g.~box-shaped spectra, that would likewise very clearly point to a particle dark matter origin., Comment: 44 pages JCAP style (excluding author list and references), 19 figures; minor changes to match published version

In this paper we study the linear stability of selfinteracting boson stars in the nonrelativistic limit of the Einstein-Klein-Gordon theory. For this purpose, based on a combination of analytic and numerical methods, we determine the behavior of general linear perturbations around the stationary and spherically symmetric solutions of the Gross-Pitaevskii-Poisson system. In particular, we conclude that ground state configurations are linearly stable if the selfinteraction is repulsive, whereas there exist a state of maximum mass that divides the stable and the unstable branches in case the selfinteraction is attractive. Regarding the excited states, they are in general unstable under generic perturbations, although we identify a stability band in the first excited states of the repulsive theory. This result is independent of the mass of the scalar field and the details of the selfinteraction potential, and it is in contrast to the situation of vanishing selfinteraction, in which excited states are always unstable., Comment: 15+1 pages and 10 figures. Minor changes were made. It was accepted in journal Physical Review D

One of the main problems that local authorities of large cities have to face is the regulation of urban mobility. They need to provide the means to allow for the efficient movement of people and distribution of goods. However, the provisioning of transportation services needs to take into account general global objectives, like reducing emissions and having more healthy living environments, which may not always be aligned with individual interests. Urban mobility is usually provided through a transport infrastructure that includes all the elements that support mobility. On many occasions, the capacity of the elements of this infrastructure is lower than the actual demand and thus different transportation activities compete for their use. In this paper, we argue that scarce transport infrastructure elements should be assigned dynamically and in a prioritised manner to transport activities that have a higher utility from the point of view of society; for example, activities that produce less pollution and provide more value to society. In this paper, we define a general model for prioritizing the use of a particular type of transportation infrastructure element called time-unlimited elements, whose usage time is unknown a priori, and illustrate its dynamics through two use cases: vehicle-specific dynamic access restriction in city centres (i) based on the usage levels of available parking spaces and (ii) to assure sustained admissible air quality levels in the city centre. We carry out several experiments using the SUMO traffic simulation tool to evaluate our proposal.

Hybrid quantum computing is considered the present and the future within the field of quantum computing. Far from being a passing fad, this trend cannot be considered just a stopgap to address the limitations of NISQ-era devices. The foundations linking both computing paradigms will remain robust over time. The contribution of this work is twofold: first, we describe and categorize some of the most frequently used hybrid solvers, resorting to two different taxonomies recently published in the literature. Secondly, we put a special focus on two solvers that are currently deployed in real production and that have demonstrated to be near the real industry. These solvers are the LeapHybridBQMSampler contained in D-Wave's Hybrid Solver Service and Quantagonia's Hybrid Solver. We analyze the performance of both methods using as benchmarks four combinatorial optimization problems., Comment: Paper presented at the 25th International Conference on Intelligent Data Engineering and Automated Learning (IDEAL 2024)

Pulse shaping is a common technique for optimizing signal-to-noise ratio (SNR) in particle detectors. Although analog or digital linear shapers are typically used for this purpose, there are nonlinear approaches, such as neural networks (NN), which have demonstrated their potential to outperform linear ones. Their nonlinear nature makes it possible to optimize the SNR of incoming pulses and extract diverse information, such as particle type and energy, with extremely short shaping time to avoid crowding. This paper shows three different NNs for shaping pulses: (a) convolutional NN (CNN); (b) recurrent NN (RNN); (c) self-attenuating NN. These NNs shape the pulses and return them unfolded avoiding stacking, and even estimate the height of the pulses when there has been saturation in the preamplifier. In this work we show the architectures of the NNs and their results using CR--RC pulses with Brownian and white noise, but they could be extrapolated to any shape and type of noise. The results obtained show that when the noise level is low and the frequency is low, all the topologies presented are a valid solution, but with white noise and high pulse arrival frequency, CNN is a better solution than the others. In the case of Brownian noise, the three topologies presented give similar results.

In this short paper, we examine the main metrics used to evaluate textual coreference and we detail some of their limitations. We show that a unique score cannot represent the full complexity of the problem at stake, and is thus uninformative, or even misleading. We propose a new way of evaluating coreference, taking into account the context (in our case, the analysis of fictions, esp. novels). More specifically, we propose to distinguish long coreference chains (corresponding to main characters), from short ones (corresponding to secondary characters), and singletons (isolated elements). This way, we hope to get more interpretable and thus more informative results through evaluation., Comment: Presented as a poster at the conference CHR2023 (non archival)

NectarCAM is a Cherenkov camera that will be installed on Medium-Sized Telescopes of the northern array of the Cherenkov Telescope Array Observatory (CTAO). It is composed of 265 modules, each of which includes 7 photo-multiplier tubes, a Front-End Board and a camera trigger system for data collection. The first NectarCAM unit is currently being integrated at CEA Paris-Saclay in France. Once installed at the CTAO's northern site, the NectarCAM's timing abilities will be crucial for reducing noise in images, improving image cleaning, and distinguishing between gamma-ray photons and cosmic-ray background. Additionally, it will enable coincidence identification with neighboring telescopes for stereoscopic observations. The timing system of NectarCAM has been tested in a dark room with various light sources. The results of the tests, including timing precision and accuracy of the trigger arrival relative to a laser source, and the timing of individual and multiple pixel signals, will be presented., Comment: Presented at the 38th International Cosmic Ray Conference (ICRC 2023), 2023 (arXiv:2309.08219)

With recent advances in Generative AI, it is becoming easier to automatically manipulate 3D models. However, current methods tend to apply edits to models globally, which risks compromising the intended functionality of the 3D model when fabricated in the physical world. For example, modifying functional segments in 3D models, such as the base of a vase, could break the original functionality of the model, thus causing the vase to fall over. We introduce a method for automatically segmenting 3D models into functional and aesthetic elements. This method allows users to selectively modify aesthetic segments of 3D models, without affecting the functional segments. To develop this method we first create a taxonomy of functionality in 3D models by qualitatively analyzing 1000 models sourced from a popular 3D printing repository, Thingiverse. With this taxonomy, we develop a semi-automatic classification method to decompose 3D models into functional and aesthetic elements. We propose a system called Style2Fab that allows users to selectively stylize 3D models without compromising their functionality. We evaluate the effectiveness of our classification method compared to human-annotated data, and demonstrate the utility of Style2Fab with a user study to show that functionality-aware segmentation helps preserve model functionality.

Galaxy clusters are expected to be dark matter (DM) reservoirs and storage rooms for the cosmic-ray protons (CRp) that accumulate along the cluster's formation history. Accordingly, they are excellent targets to search for signals of DM annihilation and decay at gamma-ray energies and are predicted to be sources of large-scale gamma-ray emission due to hadronic interactions in the intracluster medium. We estimate the sensitivity of the Cherenkov Telescope Array (CTA) to detect diffuse gamma-ray emission from the Perseus galaxy cluster. We perform a detailed spatial and spectral modelling of the expected signal for the DM and the CRp components. For each, we compute the expected CTA sensitivity. The observing strategy of Perseus is also discussed. In the absence of a diffuse signal (non-detection), CTA should constrain the CRp to thermal energy ratio within the radius $R_{500}$ down to about $X_{500}<3\times 10^{-3}$, for a spatial CRp distribution that follows the thermal gas and a CRp spectral index $\alpha_{\rm CRp}=2.3$. Under the optimistic assumption of a pure hadronic origin of the Perseus radio mini-halo and depending on the assumed magnetic field profile, CTA should measure $\alpha_{\rm CRp}$ down to about $\Delta\alpha_{\rm CRp}\simeq 0.1$ and the CRp spatial distribution with 10% precision. Regarding DM, CTA should improve the current ground-based gamma-ray DM limits from clusters observations on the velocity-averaged annihilation cross-section by a factor of up to $\sim 5$, depending on the modelling of DM halo substructure. In the case of decay of DM particles, CTA will explore a new region of the parameter space, reaching models with $\tau_{\chi}>10^{27}$s for DM masses above 1 TeV. These constraints will provide unprecedented sensitivity to the physics of both CRp acceleration and transport at cluster scale and to TeV DM particle models, especially in the decay scenario., Comment: 93 pages (including author list, appendix and references), 143 figures. Submitted to JCAP

The expectations arising from the latest achievements in the quantum computing field are causing that researchers coming from classical artificial intelligence to be fascinated by this new paradigm. In turn, quantum computing, on the road towards usability, needs classical procedures. Hybridization is, in these circumstances, an indispensable step but can also be seen as a promising new avenue to get the most from both computational worlds. Nonetheless, hybrid approaches have now and will have in the future many challenges to face, which, if ignored, will threaten the viability or attractiveness of quantum computing for real-world applications. To identify them and pose pertinent questions, a proper characterization of the hybrid quantum computing field, and especially hybrid solvers, is compulsory. With this motivation in mind, the main purpose of this work is to propose a preliminary taxonomy for classifying hybrid schemes, and bring to the fore some questions to stir up researchers minds about the real challenges regarding the application of quantum computing., Comment: 2 pages, 1 figure, paper accepted for being presented in the upcoming IEEE International Conference on Quantum Computing and Engineering - IEEE QCE 2023

The challenges expected for the next era of the Large Hadron Collider (LHC), both in terms of storage and computing resources, provide LHC experiments with a strong motivation for evaluating ways of rethinking their computing models at many levels. Great efforts have been put into optimizing the computing resource utilization for the data analysis, which leads both to lower hardware requirements and faster turnaround for physics analyses. In this scenario, the Compact Muon Solenoid (CMS) collaboration is involved in several activities aimed at benchmarking different solutions for running High Energy Physics (HEP) analysis workflows. A promising solution is evolving software towards more user-friendly approaches featuring a declarative programming model and interactive workflows. The computing infrastructure should keep up with this trend by offering on the one side modern interfaces, and on the other side hiding the complexity of the underlying environment, while efficiently leveraging the already deployed grid infrastructure and scaling toward opportunistic resources like public cloud or HPC centers. This article presents the first example of using the ROOT RDataFrame technology to exploit such next-generation approaches for a production-grade CMS physics analysis. A new analysis facility is created to offer users a modern interactive web interface based on JupyterLab that can leverage HTCondor-based grid resources on different geographical sites. The physics analysis is converted from a legacy iterative approach to the modern declarative approach offered by RDataFrame and distributed over multiple computing nodes. The new scenario offers not only an overall improved programming experience, but also an order of magnitude speedup increase with respect to the previous approach.

Altimetry data of two and a half years (June 2016-November 2018) of Sentinel 3A SRAL were validated at the sampling frequency of 80 Hz. The study areas are three coastal sites in Spain: Huelva (HU) (Gulf of Cadiz), Barcelona (BA), and Bilbao (BI). Two tracks were selected in each site: one ascending and one descending. Data were validated using in situ tide gauge (TG) data provided by the Spanish Puertos del Estado. In the 5 to 20 km segment, the results were 6-8 cm (rmse) and 0.7-0.8 (r) for all the tracks. The 0 to 5 km segment was also analyzed in detail to study the land effect on the altimetry data quality. The results showed that the track orientation, the angle of intersection with the coast, and the land topography concur to determine the nearest distance to the coast at which the data retain a similar level of accuracy than in the 5 to 20 km segment. This distance of good quality to shore reaches a minimum of 3 km for the tracks at HU and the descending track at BA.

This paper analyzes the availability and accuracy of coastal altimetry sea level products in the Strait of Gibraltar. All possible repeats of two sections of the Envisat and AltiKa ground-tracks were used in the eastern and western portions of the strait. For Envisat, along-track sea level anomalies (SLAs) at 18-Hz posting rate were computed using ranges from two sources, namely, the official SGDRs and the outputs of a coastal waveform retracker, the ALES retracker; in addition, SLAs at 1 Hz were obtained from CTOH, France. For AltiKa, along-track SLA at 40 Hz was also computed both from SGDR and ALES ranges. The quality of these altimeter products was validated using two tide gauges located on the southern coast of Spain. We observed an improvement of about 20% in the accuracy of the Envisat SLAs from ALES compared to the standard (SGDR) and the reprocessed CTOH data sets. AltiKa shows higher accuracy, with no significant differences between SGDR and ALES.

Voicebots have provided a new avenue for supporting the development of language skills, particularly within the context of second language learning. Voicebots, though, have largely been geared towards native adult speakers. We sought to assess the performance of two state-of-the-art ASR systems, Wav2Vec2.0 and Whisper AI, with a view to developing a voicebot that can support children acquiring a foreign language. We evaluated their performance on read and extemporaneous speech of native and non-native Dutch children. We also investigated the utility of using ASR technology to provide insight into the children's pronunciation and fluency. The results show that recent, pre-trained ASR transformer-based models achieve acceptable performance from which detailed feedback on phoneme pronunciation quality can be extracted, despite the challenging nature of child and non-native speech., Comment: Published on SLATE 2023, Esmad, Politecnico Do Porto, Portugal, 26-28 June, 2023, pp: 11:1-11:8

CTA (Cherenkov Telescope Array) is the next generation ground-based observatory for gamma-ray astronomy at very-high energies. The Large-Sized Telescope prototype (LST-1) is located at the Northern site of CTA, on the Canary Island of La Palma. LSTs are designed to provide optimal performance in the lowest part of the energy range covered by CTA, down to $\simeq 20$ GeV. LST-1 started performing astronomical observations in November 2019, during its commissioning phase, and it has been taking data since then. We present the first LST-1 observations of the Crab Nebula, the standard candle of very-high energy gamma-ray astronomy, and use them, together with simulations, to assess the basic performance parameters of the telescope. The data sample consists of around 36 hours of observations at low zenith angles collected between November 2020 and March 2022. LST-1 has reached the expected performance during its commissioning period - only a minor adjustment of the preexisting simulations was needed to match the telescope behavior. The energy threshold at trigger level is estimated to be around 20 GeV, rising to $\simeq 30$ GeV after data analysis. Performance parameters depend strongly on energy, and on the strength of the gamma-ray selection cuts in the analysis: angular resolution ranges from 0.12 to 0.40 degrees, and energy resolution from 15 to 50%. Flux sensitivity is around 1.1% of the Crab Nebula flux above 250 GeV for a 50-h observation (12% for 30 minutes). The spectral energy distribution (in the 0.03 - 30 TeV range) and the light curve obtained for the Crab Nebula agree with previous measurements, considering statistical and systematic uncertainties. A clear periodic signal is also detected from the pulsar at the center of the Nebula., Comment: Accepted in ApJ. v3: updated author list and acknowledgements, fixed typos and other minor issues

Providing high quality explanations for AI predictions based on machine learning is a challenging and complex task. To work well it requires, among other factors: selecting a proper level of generality/specificity of the explanation; considering assumptions about the familiarity of the explanation beneficiary with the AI task under consideration; referring to specific elements that have contributed to the decision; making use of additional knowledge (e.g. expert evidence) which might not be part of the prediction process; and providing evidence supporting negative hypothesis. Finally, the system needs to formulate the explanation in a clearly interpretable, and possibly convincing, way. Given these considerations, ANTIDOTE fosters an integrated vision of explainable AI, where low-level characteristics of the deep learning process are combined with higher level schemes proper of the human argumentation capacity. ANTIDOTE will exploit cross-disciplinary competences in deep learning and argumentation to support a broader and innovative view of explainable AI, where the need for high-quality explanations for clinical cases deliberation is critical. As a first result of the project, we publish the Antidote CasiMedicos dataset to facilitate research on explainable AI in general, and argumentation in the medical domain in particular., Comment: To appear: In SEPLN 2023: 39th International Conference of the Spanish Society for Natural Language Processing

The interest in employing automatic speech recognition (ASR) in applications for reading practice has been growing in recent years. In a previous study, we presented an ASR-based Dutch reading tutor application that was developed to provide instantaneous feedback to first-graders learning to read. We saw that ASR has potential at this stage of the reading process, as the results suggested that pupils made progress in reading accuracy and fluency by using the software. In the current study, we used children's speech from an existing corpus (JASMIN) to develop two new ASR systems, and compared the results to those of the previous study. We analyze correct/incorrect classification of the ASR systems using human transcripts at word level, by means of evaluation measures such as Cohen's Kappa, Matthews Correlation Coefficient (MCC), precision, recall and F-measures. We observe improvements for the newly developed ASR systems regarding the agreement with human-based judgment and correct rejection (CR). The accuracy of the ASR systems varies for different reading tasks and word types. Our results suggest that, in the current configuration, it is difficult to classify isolated words. We discuss these results, possible ways to improve our systems and avenues for future research., Comment: Published (double-blind peer-reviewed) on SPECOM 2021