id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_ea2y7a4x6zabxp5sgs3jl5skuy	Wenpeng Yin	ABCNN: Attention-Based Convolutional Neural Network for Modeling Sentence Pairs	2016	14	.pdf	application/pdf	8509	1061	72	ABCNN: Attention-Based Convolutional Neural Network This work presents a general Attention Based Convolutional Neural The ABCNN can be applied to a wide variety of tasks that require modeling of sentence pairs. How to model a pair of sentences is a critical issue in many NLP tasks such as answer selection ABCNN, an attention-based convolutional neural ARC-I focuses on sentence representation learning while ARC-II focuses on matching features on phrase level. For the output feature map of the last convolution layer, we do column-wise averaging over all For the output feature map of non-final convolution layers, we do column-wise averaging over windows of w consecutive columns, denoted as w-ap; ABCNN-3, that each introduces an attention mechanism for modeling sentence pairs; see Figure 3. The ABCNN-1 (Figure 3(a)) employs an attention feature matrix A to influence conAs a result, the new input of convolution has two feature maps for each sentence (shown	./cache/work_ea2y7a4x6zabxp5sgs3jl5skuy.pdf	./txt/work_ea2y7a4x6zabxp5sgs3jl5skuy.txt