We propose a language-agnostic way of automatically generating sets of semantically similar clusters of entities along with sets of "outlier" elements, which may then be used to perform an intrinsic evaluation of word embeddings in the outlier detection task. We used our methodology to create a gold-standard dataset, which we call WikiSem500, and evaluated multiple state-of-the-art embeddings. The results show a correlation between performance on this dataset and performance on sentiment analysis.
Background Since medical access to medicinal cannabis (MC) was legalised in Australia in 2016, numbers of people prescribed MC have increased exponentially. There is a need for safety and effectiveness data on the longer-term use of MC in real-world settings. This paper describes the methodology of Project Twenty21 Australia, an observational study that commenced early in 2022 and its preliminary findings. Method This study tests whether medicinal cannabis is effective in four primary conditions: chronic pain, anxiety, posttraumatic stress disorder and multiple sclerosis (MS). Participants are prescribed MC from within a Project Formulary, completing questionnaires at baseline then 3 monthly for up to 12 months. Results Between the start of the study in February and 30 August 2022, 278 participants had been recruited into the study: 50.7% female, 48.2% male and 1.1% non-binary with average age 39.2 years (18–77). Patients reported a low quality of life and high levels of co-morbidity. Three-month data, available for 71 participants, indicate that MC was associated with substantial improvements in self-reported quality of life, general health, mood/depression and sleep with standardised effect size estimates ranging from 0.57 to 0.93. Three adverse reactions were reported. Conclusions This paper describes the protocol used for an observational study conducted in Australia assessing the effectiveness of MC in four main conditions. We have established the feasibility of collecting real-world data on symptoms and quality of life in people receiving treatment with MC. Preliminary evidence suggests that MC may be effective in improving quality of life, general health, mood and sleep.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.