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.