AdeDZY / K-NRM

K-NRM: End-to-End Neural Ad-hoc Ranking with Kernel Pooling

AdeDZY/K-NRM Issues

Why the paper says the kernel devolves to mean pooling when σ becomes infinity?
Updated 2 years ago2
求论文中的数据集
Closed 4 years ago2
Maybe unfair to compare simple k-nrm-max/mean-pool approach with k-nrm-kernel-pool in the paper
Closed 4 years ago9
For text match problem, what is the different between question-question match and question-answer match?
Closed 5 years ago
关于模型的小疑问
Updated 5 years ago2
Could you provide a very short sample of training and evaluation file for ease of using?
Updated 5 years ago
Dataset Preparation
Updated 5 years ago9
关于怎么处理文档
Updated 5 years ago5
Errors? when initial idf values in testing part.
Updated 6 years ago1
code error: where can I find file: deeplearning4ir.utils？
Closed 6 years ago2
missing knrm embedding
Updated 6 years ago
关于训练样本数据的疑问
Updated 6 years ago4
Is possible to add other type of kernel ?
Updated 6 years ago1
any sample dataset for quick evaluation
Updated 6 years ago1
can use the samples that their different score is 1?
Closed 7 years ago2
About embedding usage
Updated 7 years ago2
mu = tf.reshape(input_mu, shape=[1, 1, self.n_bins]) 这个操作有什么特殊意思吗?
Updated 7 years ago1
可以提供paper中使用的搜狗训练数据吗？
Updated 7 years ago1