The Fact Extraction and VERification (FEVER) shared task was launched to support the development of systems able verify claims by extracting supporting or refuting facts from raw text. organizers provide a large-scale dataset for consecutive steps involved in claim verification, particular, document retrieval, fact extraction, classification. In this paper, we present our verification pipeline approach, which, according preliminary results, scored third task, out 23 competing systems. For...

Steffen Eger, Gözde Gül Şahin, Andreas Rücklé, Ji-Ung Lee, Claudia Schulz, Mohsen Mesgar, Krishnkant Swarnkar, Edwin Simpson, Iryna Gurevych. Proceedings of the 2019 Conference North American Chapter Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). 2019.

Automated fact-checking based on machine learning is a promising approach to identify false information distributed the web. In order achieve satisfactory performance, methods require large corpus with reliable annotations for different tasks in process. Having analyzed existing corpora, we found that none of them meets these criteria full. They are either too small size, do not provide detailed annotations, or limited single domain. Motivated by this gap, present new substantially sized...

Although effective treatments are available, most individuals with body dysmorphic disorder (BDD) do not receive an appropriate diagnosis or treatment. We aimed to examine treatment utilization and barriers treatment, identify associated socio-demographic clinical characteristics.German completed online self-report survey of appearance concerns. A sample N = 429 met criteria for BDD. examined the frequency barriers, analyzed comparisons between treated untreated assessed relationships...

Claudia Schulz, Steffen Eger, Johannes Daxenberger, Tobias Kahse, Iryna Gurevych. Proceedings of the 2018 Conference North American Chapter Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers). 2018.

An answer set is a plain of literals which has no further structure that would explain why certain are part it and others not. We show how argumentation theory can help to literal or not contained in given by defining two justification methods, both make use the correspondence between sets logic program stable extensions Assumption-Based Argumentation (ABA) framework constructed from same program. Attack Trees justify argumentation-theoretic terms, i.e. using arguments attacks them, whereas...

Visual modifications to text are often used obfuscate offensive comments in social media (e.g., "!d10t") or as a writing style ("1337" "leet speak"), among other scenarios. We consider this new type of adversarial attack NLP, setting which humans very robust, our experiments with both simple and more difficult visual input perturbations demonstrate. then investigate the impact attacks on current NLP systems character-, word-, sentence-level tasks, showing that neural non-neural models are,...

It has been proposed that social anxiety disorder (SAD) is associated with automatic information processing biases resulting in hypersensitivity to signals of threat such as negative facial expressions. However, the nature and extent processes SAD on behavioral neural level not entirely clear yet. The present review summarizes neuroscientific findings but also other disorder-related stimuli emotional prosody or words SAD. We initial evidence for activation amygdala, insula, sensory cortices...

The 7th Symposium on Educational Advances in Artificial Intelligence (EAAI'17, co-chaired by Sven Koenig and Eric Eaton) launched the EAAI New Future AI Educator Program to support training of early-career university faculty, secondary school future educators (PhD candidates or postdocs who intend a career academia). As part program, awardees were asked address one following "blue sky" questions: * How could/should (AI) courses incorporate ethics into curriculum? could we teach topics at an...

Abstract Artificial intelligence (AI) approaches to problem-solving and decision-making are becoming more complex, leading a decrease in the understandability of solutions. The European Union’s new General Data Protection Regulation tries tackle this problem by stipulating “right explanation” for decisions made AI systems. One paradigms that may be affected regulation is answer set programming (ASP). Thanks emergence efficient solvers, ASP has recently been used variety domains, including...

Clinical pharmacy services in German hospitals appear to be underdeveloped compared with other European countries. However, recent developments have increased the interest expanding these services. Detailed data about current state of clinical Germany are lacking. This survey establishes level and barriers implementation.An online conducted 2017 was distributed directors all 389 hospital pharmacies. The contained 26 questions addressing characteristics, provided, number pharmacists frequency...

Assumption-Based Argumentation (ABA) has been shown to subsume various other non-monotonic reasoning formalisms, among them normal logic programming (LP). We re-examine the relationship between ABA and LP show that also subsumes (flat) ABA. More precisely, we specify a procedure given framework yields an associated program with almost same syntax whose semantics coincide those of framework. That is, 3-valued stable (respectively well-founded, regular, 2-valued stable, ideal) models complete...

Previous event-related potential (ERP) studies have shown that the N170 to faces is modulated by emotion of face and its context. However, it unclear how encoding emotional target as reflected in preceding contextual facial expression when temporal onset identity are unpredictable. In addition, no study yet has investigated whether modulates later recognition faces. To address these issues, participants present were asked identify (fearful or neutral) presented after a sequence fearful...

Diagnostic reasoning is a key component of many professions. To improve students’ diagnostic skills, educational psychologists analyse and give feedback on epistemic activities used by these students while diagnosing, in particular, hypothesis generation, evidence evaluation, drawing conclusions. However, this manual analysis highly time-consuming. We aim to enable the large-scale adoption automating activity identification. create first corpus for task, comprising selfexplanations from two...

Cognitive-behavioral models of body dysmorphic disorder (BDD) conceptualize biases in visual information processing as maintaining factors the disorder. Empirical findings point to selective attentional mechanisms and a detail-oriented style facial perception, which are related perceived aesthetics. However, so far, it remains unclear whether higher discrimination abilities symmetry attractiveness ratings contribute mind filter BDD. BDD (n = 25) mentally healthy subjects rated fifty...