id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_3izv3tjjq5ga7j3fkxkvenujpy	Abe Kazemzadeh	A Socratic epistemology for verbal emotional intelligence	2016	26	.pdf	application/pdf	10213	1072	65	guess the human opponent's emotion word in the EMO20Q game, the agent's behavior of We describe and experimentally validate a question-asking framework for machine-learned linguistic knowledge about human emotions. Even when the agent fails to guess the human opponent's emotion word in the EMO20Q agent cannot directly experience emotions as a human would, question-asking can be leveraged for the40 using question-asking to interactivly acquire linguistic knowledge about emotion by a computer dialog agent The key goals of this paper are to use question-asking to observe natural language descriptions of emotion The model we use for the EMO20Q questioner agent is a sequential Bayesian belief update algorithm.205 Of the 110 matches played between the 25 human players, 94 – approximately 85% – terminated successfully with the questioner correctly identifying the emotion that the answerer picked or a word that the the human opponent's emotion word in the EMO20Q game, the agent's behavior of searching for knowledge	./cache/work_3izv3tjjq5ga7j3fkxkvenujpy.pdf	./txt/work_3izv3tjjq5ga7j3fkxkvenujpy.txt