Papers by Zong-Ying Slaton

Copied to clipboard

Challenge:	Detecting imperatives in oral and written communication is difficult when the user doesn't use the expected forms.
Approach:	They created an imperative corpus with dialogues from The Big Bang Theory and Wikipedia comments from Wikipedia . they manually annotated imperatives and used a syntax-based classifier to extract 10,624 statements that may be imperative.
Outcome:	The proposed model performs better in the written data compared to speech data, but has a low precision and recall for speech data.