No abstract

To combat COVID-19, both clinicians and scientists need to digest vast amounts of relevant biomedical knowledge in scientific literature to understand the disease mechanism and related biological functions. We have developed a novel and comprehensive knowledge discovery framework, COVID-KG to extract finegrained multimedia knowledge elements (entities and their visual chemical structures, relations and events) from scientific literature. We then exploit the constructed multimedia knowledge graphs (KGs) for question answering and report generation, using drug repurposing as a case study. Our framework also provides detailed contextual sentences, subfigures, and knowledge subgraphs as evidence. All of the data, KGs, reports 1 , resources, and shared services are publicly available 2 .

Variational Auto-Encoders (VAEs) are deep latent space generative models which have been immensely successful in many applications such as image generation, image captioning, protein design, mutation prediction, and language models among others. The fundamental idea in VAEs is to learn the distribution of data in such a way that new meaningful data can be generated from the encoded distribution. This concept has led to tremendous research and variations in the design of VAEs in the last few years creating a field of its own, referred to as unsupervised representation learning. This paper provides a muchneeded comprehensive evaluation of the variations of the VAEs based on their end goals and resulting architectures. It further provides intuition as well as mathematical formulation and quantitative results of each popular variation, presents a concise comparison of these variations, and concludes with challenges and future opportunities for research in VAEs.

Background Worldwide, five billion people lack access to safe, affordable surgical, obstetric, and anaesthesia (SOA) care when needed. In many countries, a growing commitment to SOA care is culminating in the development of national surgical, obstetric, and anaesthesia plans (NSOAPs) that are fully embedded in the National Health Strategic Plan. This manuscript highlights the content and outputs from a World Health Organization (WHO) lead workshop that supported country‐led plans for improving SOA care as a component of health system strengthening. Methods In March 2018, a group of 79 high‐level global SOA stakeholders from 25 countries in the WHO AFRO and EMRO regions gathered in Dubai to provide technical and strategic guidance for the creation and expansion of NSOAPs. Results Drawing on the experience and expertise of represented countries that are at different stages of the NSOAP process, topics covered included (1) the global burden of surgical, obstetric, and anaesthetic conditions; (2) the key principles and components of NSOAP development; (3) the critical evaluation and feasibility of different models of NSOAP implementation; and (4) innovative financing mechanisms to fund NSOAPs. Conclusions Lessons learned include: (1) there is unmet need for the establishment of an NSOAP community in order to provide technical support, expertise, and mentorship at a regional level; (2) data should be used to inform future priorities, for monitoring and evaluation and to showcase advances in care following NSOAP implementation; and (3) SOA health system strengthening must be uniquely prioritized and not hidden within other health strategies.

This paper presents the outcomes of the Parsing Time Normalization shared task held within SemEval-2018. The aim of the task is to parse time expressions into the compositional semantic graphs of the Semantically Compositional Annotation of Time Expressions (SCATE) schema, which allows the representation of a wider variety of time expressions than previous approaches. Two tracks were included, one to evaluate the parsing of individual components of the produced graphs, in a classic information extraction way, and another one to evaluate the quality of the time intervals resulting from the interpretation of those graphs. Though 40 participants registered for the task, only one team submitted output, achieving 0.55 F1 in Track 1 (parsing) and 0.70 F1 in Track 2 (intervals).