id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_75gdtwc2zvf7ta3kal27fs4suu	Tong Niu	Polite Dialogue Generation Without Parallel Data	2018	18	.pdf	application/pdf	10930	916	60	two retrieval-based models, where we output the response which has the highest match with the input context from a set of classifier-picked polite Therefore, our novel polite dialogue models are based on an accurate neural classifier, which Moreover, our approaches allow simply replacing the politeness classifier with any other emotion or personality based language classifier to generate stylistic dialogue for that new style dimension. for effective use in stylistic dialogue response generation, we extend and improve upon the state-of-theart CNN model of Aubakirova and Bansal (2016), model to generate a polite response, we scale the label's embedding by a score between 0.5 and 1.0, produce polite, neutral and rude responses depending on the prepended label, similar to recent multilabel, multi-space, and zero-shot machine translation work using language identity or style labels (Sennrich et al., 2016a; Johnson et al., 2017; Human To evaluate our models' ability to generate polite responses without sacrificing dialogue	./cache/work_75gdtwc2zvf7ta3kal27fs4suu.pdf	./txt/work_75gdtwc2zvf7ta3kal27fs4suu.txt