Extracting and modeling typical durations of events and habits from Twitter
Williams, Jennifer Alexandra
This thesis presents recent work on a new method to automatically extract fine-grained duration information for common verbs using a large corpus of Twitter tweets. I present the results of distinguishing between habitual and episodic uses of verbs using semi-supervised machine learning methods. This work has resulted in a lexicon that contains verb lemmas and their associated episodic and habitual durations.
Showing items related by title, author, creator and subject.
Williams, Kamille D. (Georgetown University, 2016)The N-O functionality is ubiquitous endogenously. The wide range of oxidation states of the nitrogen atom, (+5 to -3), is attributed to the various biologically relevant congeners containing the NO functionality. The ...