Domain dependence of NLP systems is one of the major obstacles to their application in large-scale text analysis, also restricting the applicability of FrameNet semantic role labeling (SRL) systems. Yet, current FrameNet SRL systems are still only evaluated on a single in-domain test set. For the first time, we study the domain dependence of FrameNet SRL on a wide range of benchmark sets. We cr...

The highly persistent and often lethal human pathogen, Mycobacterium tuberculosis contains at least 88 toxin-antitoxin genes. More than half of these encode VapC PIN domain endoribonucleases that inhibit cell growth by unknown mechanisms. Here we show that VapC20 of M. tuberculosis inhibits translation by cleavage of the Sarcin-Ricin loop (SRL) of 23S ribosomal RNA at the same position where Sa...

Semantic Role Labeling (SRL) is a leading task of identifying arguments for a predicate and assigning semantically meaningful labels to them. SRL is crucial to information extraction, question answering, and machine translation. When applied to patent text, existing tools for SRL have unsatisfying performance because of long sentences. To improve performance in patent SRL systems, this study se...

Several routing protocols for mobile ad hoc networks work efficiently only in bidirectional networks. Unidirectional links may exist in a real network due to variation in transmission power of different nodes, noise or other signal propagation phenomena, and heterogeneity in transmission hardware of nodes in the network. We introduce a sub-layer called Sub Routing Layer, SRL, between the networ...

Active learning is a useful technique for tasks for which unlabeled data is abundant but manual labeling is expensive. One example of such a task is semantic role labeling (SRL), which relies heavily on labels from trained linguistic experts. One challenge in applying active learning algorithms for SRL is that the complete knowledge of the SRL model is often unavailable, against the common assu...

This study investigated the role of self-directed learning (SDL) in problem-based learning (PBL) and examined how SDL relates to self-regulated learning (SRL). First, it is explained how SDL is implemented in PBL environments. Similarities between SDL and SRL are highlighted. However, both concepts differ on important aspects. SDL includes an additional premise of giving students a broader role...

Self-regulated learning (SRL) competences are crucial for lifelong learning. Their cultivation requires the right balance between freedom and guidance during the learning processes. Current learning systems and approaches, such as personal learning environments, give overwhelming freedom, but also let weak learners alone. Other systems, such as learning management systems or adaptive systems, t...

Self-regulated learning (SRL) includes the cognitive, metacognitive, behavioral, motivational, and emotional/affective aspects of learning. It is, therefore, an extraordinary umbrella under which a considerable number of variables that influence learning (e.g., self-efficacy, volition, cognitive strategies) are studied within a comprehensive and holistic approach. For that reason, SRL has becom...

Electronic health records (EHRs) are an emerging relational domain with large potential to improve clinical outcomes. We apply two statistical relational learning (SRL) algorithms to the task of predicting primary myocardial infarction. We show that one SRL algorithm, relational functional gradient boosting, outperforms propositional learners particularly in the medically-relevant high recall r...

Glioma, as a primary tumor of central nervous system, is the main cause of death in patients with brain cancer. Therefore, development of an efficient strategy for treatment of glioma is worthy. The aim of the current study was to develop a SRL peptide-coated dendrimer as a novel dual gene delivery system for targeting the LRP receptor, an up-regulated gene in both BBB and glioma cells. To perf...