Search

In recent years, machine learning (ML) models have been successfully applied in a variety of real-world applications. However, they are often complex and incomprehensible to human users. This can decrease trust in their outputs and render their usage in critical settings ethically problematic. As a result, several methods for explaining such ML models have been proposed recently, in particular for black-box models such as deep neural networks (NNs). Nevertheless, these methods predominantly explain outputs in terms of inputs, disregarding the inner workings of the ML model computing those outputs. We present Argflow, a toolkit enabling the generation of a variety of ‘deep’ argumentative explanations (DAXs) for outputs of NNs on classification tasks.

In cancer, the lymphatic system is hijacked by tumor cells to escape from primary tumor and to metastasize to the sentinel lymph nodes. Tumor lymphangiogenesis is stimulated by the vascular endothelial growth factors-C (VEGFC) after binding to its receptor VEGFR-3. However, how VEGFC cooperates with other molecules to promote lymphatic neovessels growth is not fully determined. Here, we found that tumor lymphangiogenesis developed in tumoral lesions and in their surrounding adipose tissue (AT). Interestingly, lymphatic vessel density correlated with an increase of circulating free fatty acids (FFA) in the lymph from tumor-bearing mice. We found that adipocyte-released FFA are uploaded by lymphatic endothelial cells (LEC) to stimulate their sprouting. Lipidomic analysis identified the monounsaturated oleic acid (OA) as the major circulating FFA in the lymph in tumoral context. OA transporters FATP-3, -6 and CD36 were only upregulated on LEC in the presence of VEGFC showing a collaborative effect of these molecules. OA released from adipocytes is taken up by LECs to stimulate the fatty acid β-oxidation, leading to increase adipose tissue lymphangiogenesis. Our results provide new insights on the dialogue between tumors and adipocytes via the lymphatic system and identify a key role for adipocyte-derived FFA in the promotion of lymphangiogenesis, revealing novel therapeutic opportunities for inhibitors of lymphangiogenesis in cancer.

Despite the rapid growth in attention on eXplainable AI (XAI) of late, explanations in the literature provide little insight into the actual functioning of Neural Networks (NNs), significantly limiting their transparency. We propose a methodology for explaining NNs, providing transparency about their inner workings, by utilising computational argumentation (a form of symbolic AI offering reasoning abstractions for a variety of settings where opinions matter) as the scaffolding underpinning Deep Argumentative eXplanations (DAXs). We define three DAX instantiations (for various neural architectures and tasks) and evaluate them empirically in terms of stability, computational cost, and importance of depth. We also conduct human experiments with DAXs for text classification models, indicating that they are comprehensible to humans and align with their judgement, while also being competitive, in terms of user acceptance, with existing approaches to XAI that also have an argumentative spirit.

Argument Mining is the research area which aims at extracting argument components and predicting argumentative relations (i.e.,support and attack) from text. In particular, numerous approaches have been proposed in the literature to predict the relations holding between the arguments, and application-specific annotated resources were built for this purpose. Despite the fact that these resources have been created to experiment on the same task, the definition of a single relation prediction method to be successfully applied to a significant portion of these datasets is an open research problem in Argument Mining. This means that none of the methods proposed in the literature can be easily ported from one resource to another. In this paper, we address this problem by proposing a set of dataset independent strong neural baselines which obtain homogeneous results on all the datasets proposed in the literature for the argumentative relation prediction task. Thus, our baselines can be employed by the Argument Mining community to compare more effectively how well a method performs on the argumentative relation prediction task.

Background - PRES (posterior reversible encephalopathy syndrome) is a clinical-radiological entity characterised by a combination of neurological signs and symptoms and neuroradiological alterations like subcortical and cortical vasogenic oedema that is bilateral and symmetric and mainly involves the posteriors regions of cerebral hemispheres. Currently, two theories exist about the pathophysiology of PRES; these theories identify arterial hypertension and endothelial injury induced by an inflammatory process or immune disorders as trigger factors of PRES. The signs and symptoms associated with PRES are also common to other diseases of CNS, like ischemic or haemorrhagic events, infections, neoplasia, metabolic diseases and epilepsy. These diseases have to be considered in the differential diagnosis process. PRES is associated with a wide range of clinical conditions, namely transplantations, immunosuppressive therapy, chemotherapy, autoimmune diseases, infections and hypertension. As these groups of patients are more predisposed to the onset of PRES, the encephalopathy should be taken into consideration and the right exams should be prescribed in order to diagnose it. In this case brain MRI represents the gold standard for the diagnosis. PRES is generally a reversible and benign condition, nevertheless severe complications with poor clinical outcomes can occur. Methods - The paper describes PRES peculiar aspects including a curios clinical case of PRES associated to a massive consumption of glycyrrhizic acid coming from liquorice sweets that Paolo (a 10-year-old boy) had been eating in high quantity every day since 4 months, unaware that his blood pressure would have increased until the onset of an encephalopathy that luckily had been solved without permanent outcomes. Conclusion - It is essential to know patients' categories that are at high risk of encephalopathy and suspect PRES at an early stage to start an appropriate treatment and avoid severe complications.

Today’s AI landscape is permeated by plentiful data anddominated by powerful data-centric methods with the potential toimpact a wide range of human sectors. Yet, in some settings this po-tential is hindered by these data-centric AI methods being mostlyopaque. Considerable efforts are currently being devoted to defin-ing methods for explaining black-box techniques in some settings,while the use of transparent methods is being advocated in others,especially when high-stake decisions are involved, as in healthcareand the practice of law. In this paper we advocate a novel transpar-ent paradigm of Data-Empowered Argumentation (DEAr in short)for dialectically explainable predictions. DEAr relies upon the ex-traction of argumentation debates from data, so that the dialecticaloutcomes of these debates amount to predictions (e.g. classifications)that can be explained dialectically. The argumentation debates con-sist of (data) arguments which may not be linguistic in general butmay nonetheless be deemed to be ‘arguments’ in that they are dialec-tically related, for instance by disagreeing on data labels. We illus-trate and experiment with the DEAr paradigm in three settings, mak-ing use, respectively, of categorical data, (annotated) images and text.We show empirically that DEAr is competitive with another transpar-ent model, namely decision trees (DTs), while also providing natu-rally dialectical explanations.

Objectives To assess the role of fetal magnetic resonance imaging (MRI) in detecting associated anomalies in fetuses presenting with mild or moderate isolated ventriculomegaly (VM) undergoing multiplanar ultrasound evaluation of the fetal brain. Methods This was a multicenter, retrospective, cohort study involving 15 referral fetal medicine centers in Italy, the UK and Spain. Inclusion criteria were fetuses affected by isolated mild (ventricular atrial diameter, 10.0-11.9 mm) or moderate (ventricular atrial diameter, 12.0-14.9 mm) VM on ultrasound, defined as VM with normal karyotype and no other additional central nervous system (CNS) or extra-CNS anomalies on ultrasound, undergoing detailed assessment of the fetal brain using a multiplanar approach as suggested by the International Society of Ultrasound in Obstetrics and Gynecology guidelines for the fetal neurosonogram, followed by fetal MRI. The primary outcome of the study was to report the incidence of additional CNS anomalies detected exclusively on prenatal MRI and missed on ultrasound, while the secondary aim was to estimate the incidence of additional anomalies detected exclusively after birth and missed on prenatal imaging (ultrasound and MRI). Subgroup analysis according to gestational age at MRI (< 24 vs >= 24 weeks), laterality of VM (unilateral vs bilateral) and severity of dilatation (mild vs moderate VM) were also performed. Results Five hundred and fifty-six fetuses with a prenatal diagnosis of isolated mild or moderate VM on ultrasound were included in the analysis. Additional structural anomalies were detected on prenatal MRI and missed on ultrasound in 5.4% (95% CI, 3.8-7.6%) of cases. When considering the type of anomaly, supratentorial intracranial hemorrhage was detected on MRI in 26.7% of fetuses, while polymicrogyria and lissencephaly were detected in 20.0% and 13.3% of cases, respectively. Hypoplasia of the corpus callosum was detected on MRI in 6.7% of cases, while dysgenesis was detected in 3.3%. Fetuses with an associated anomaly detected only on MRI were more likely to have moderate than mild VM (60.0% vs 17.7%; P

Arguing is amenable to humans and argumentation serves as anatural form of interaction in many settings. Several formal mod-els of argumentation have been proposed in the AI literature asabstractions of various forms of debates. We show how these mod-els can serve as the backbone of conversational systems that canexplain machine-computed outputs. These systems can engage inconversations with humans following templates instantiated onargumentation models that are automatically obtained from thedata analysis underpinning the machine-computed outputs. Asan illustration, we consider one such argumentation-empoweredconversational system and exemplify its use and benefits in twodifferent domains, for recommending movies and hotels based onthe aggregation of information drawn from reviews.

Bipolar Argumentation Frameworks (BAFs) admit several interpretations of the support relation and diverging definitions of semantics. Recently, several classes of BAFs have been captured as instances of bipolar Assumption-Based Argumentation, a class of Assumption-Based Argumentation (ABA). In this paper, we establish the complexity of bipolar ABA, and consequently of several classes of BAFs. In addition to the standard five complexity problems, we analyse the rarely-addressed extension enumeration problem too. We also advance backtracking-driven algorithms for enumerating extensions of bipolar ABA frameworks, and consequently of BAFs under several interpretations. We prove soundness and completeness of our algorithms, describe their implementation and provide a scalability evaluation. We thus contribute to the study of the as yet uninvestigated complexity problems of (variously interpreted) BAFs as well as of bipolar ABA, and provide the lacking implementations thereof., Paper accepted for publication at AAMAS 2019

Bipolar Argumentation Frameworks (BAFs) are an important class of argumentation frameworks useful for capturing, reasoning with, and deriving conclusions from debates. They have the potential to make solid contributions to real-world multi-agent systems and human-agent interaction in domains such as legal reasoning, healthcare and politics. Despite this fact, practical systems implementing BAFs are largely lacking. In this demonstration, we provide a software system implementing novel algorithms for calculating extensions (winning sets of arguments) of BAFs. Participants in the demonstration will be able to input their own debates into our system, and watch a graphical representation of the algorithms as they process information and decide which sets of arguments are winners of the debate.

The aggregation of online reviews is fast becoming the chosen method of quality control for users in various domains, from retail to entertainment. Consequently, fair, thorough and explainable aggregation of reviews is increasingly sought-after. We consider the movie review domain, and in particular Rotten Tomatoes' ubiquitous (and arguably over-simplified) aggregation method, the Tomatometer Score (TS). For a movie, this amounts to the percentage of critics giving the movie a positive review. We define a novel form of argumentative dialogical agent (ADA) for explaining the reasoning within the reviews. ADA integrates: 1.) NLP with reviews to extract a Quantitative Bipolar Argumentation Framework (QBAF) for any chosen movie to provide the underlying structure of explanations, and 2.) gradual semantics for QBAFs for deriving a dialectical strength measure for movies, as an alternative to the TS, satisfying desirable properties for obtaining explanations. We evaluate ADA using some prominent NLP methods and gradual semantics for QBAFs. We show that they provide a dialectical strength which is comparable with the TS, while at the same time being able to provide dialogical explanations of why a movie obtained its strength via interactions between the user and ADA.

BACKGROUND: In recent years, respiratory support in severe bronchiolitis has changed in several aspects: increased use of noninvasive ventilation, new equipment, and implementation of high-flow nasal cannula therapy. OBJECTIVE: To analyze the effectiveness of the changes progressively introduced in the respiratory support of patients with bronchiolitis to reduce the intubation rate. METHODS: This was a retrospective, observational, descriptive study. Patients admitted to the pediatric ICU of Hospital Sant Joan de Déu (Barcelona, Spain) with respiratory failure due to bronchiolitis in the 2010-2011 and 2016-2017 periods were included. Exclusion criteria were the following: patients who were previously intubated and tracheostomized and patients > 1 y. Data collected were demographic, clinical, and ventilatory variables, including the type, equipment used, and length of the respiratory support received. RESULTS: A total of 161 subjects were included: 53 in the 2010-2011 period and 108 in the 2016-2017 period. No clinical differences were observed except the incidence of previous apnea, a diagnosis of sepsis, and procalcitonin values on admission that were higher in the first period. High-flow nasal cannula use before pediatric ICU admission was significantly higher in 2016-2017. A significant increase in the use of the total face mask was observed. The need for invasive ventilation decreased from 37.7% to 17.5%. In the multivariate study, use of interfaces other than the total face mask was identified as the only independent predictive factor for noninvasive ventilation failure, with an odds ratio of 2.5, 95% CI 1.04-6.2 (P = .040). CONCLUSIONS: An important reduction in invasive ventilation was observed. An independent predictive factor for noninvasive ventilation failure was in using an interface other than the total face mask. Implementation of high-flow nasal cannula has not been identified as an independent protective factor for intubation.

One problem that Argument Mining (AM) is facing is the difficultyof obtaining suitable annotated corpora. We propose a web-basedplatform, BookSafari, that allows crowdsourcing of annotated cor-pora forrelation-based AMfrom users providing reviews for booksand exchanging opinions about these reviews to facilitate argumen-tative dialogue. The annotations amount to pairwise argumentativerelations ofattackandsupportbetween opinions and between opin-ions and reviews. As a result of the annotations, reviews and opinionsform structured debates which can be understood as bipolar argu-mentation frameworks. The platform also empowers annotationsof the same pairs by multiple annotators and can support differentmeasures of inter-annotator agreement and corpora selection.

Several gradual semantics for abstract and bipolar argumentation have been proposed in the literature, ascribing to each argument a value taken from a scale, i.e. an ordered set. These values somewhat match the arguments’ dialectical status and provide an indication of their dialectical strength, in the context of the given argumentation framework. These research efforts have been complemented by formulations of several properties that these gradual semantics may satisfy. More recently a synthesis of many literature properties into more general groupings based on parametric definitions has been proposed. In this paper we show how this generalised parametric formulation enables the identification of new properties not previously considered in the literature and discuss their usefulness to capture alternative requirements coming from different application contexts.

Data-centric AI has proven successful in several domains, but its outputs are often hard to explain. We present an architecture combining Artificial Neural Networks (ANNs) for feature selection and an instance of Abstract Argumentation (AA) for reasoning to provide effective predictions, explain- able both dialectically and logically. In particular, we train an autoencoder to rank features in input ex- amples, and select highest-ranked features to gen- erate an AA framework that can be used for mak- ing and explaining predictions as well as mapped onto logical rules, which can equivalently be used for making predictions and for explaining. We show empirically that our method significantly out- performs ANNs and a decision-tree-based method from which logical rules can also be extracted.