As the sources of information that we consume everyday rapidly diversify, it is becoming increasingly important to develop NLP tools that help to evaluate the credibility of the information we receive. A critical step towards this goal is to determine the factuality of events in text. In this paper, we frame factuality assessment as a modal dependency parsing task that identifies the events and their sources, formally known as conceivers, and then determine the level of certainty that the sources are asserting with respect to the events. We crowdsource the first large-scale data set annotated with modal dependency structures that consists of 353 Covid-19 related news articles, 24,016 events, and 2,938 conceivers. 1 We also develop the first modal dependency parser that jointly extracts events, conceivers and constructs the modal dependency structure of a text. We evaluate the joint model against a pipeline model and demonstrate the advantage of the joint model in conceiver extraction and modal dependency structure construction when events and conceivers are automatically extracted. We believe the dataset and the models will be a valuable resource for a whole host of NLP applications such as fact checking and rumor detection.
Correlation dimension analysis of EEG signals is widely used to access sleep stages. However, the standard Grassberger-Procaccia (GP) algorithm used to calculate the correlation dimension is very time consuming. To overcome this problem, an algorithm that combines the grey model and GP algorithm (GM-GP) is proposed. The results show that the correlation dimensions computed from GP and GM-GP are highly correlated, and the significance between the CDs in different stages of GM-GP is similar to GP. Furthermore, the computation time of the proposed method is at most 5% of that of the GP. The proposed algorithm is suitable for the real-time monitoring of sleep stages, which can provide a deeper understanding of brain function.
We present UMR-Writer, a web-based application for annotating Uniform Meaning Representations (UMR), a graph-based, crosslinguistically applicable semantic representation developed recently to support the development of interpretable natural language applications that require deep semantic analysis of texts. We present the functionalities of UMR-Writer and discuss the challenges in developing such a tool and how they are addressed.
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.