Hi siddsax,
I wanna ask about the pooling layer because you're using a sliding max pooling. XML-CNN use dynamic max pooling with the definition "For a p document with m words, we evenly divide its m-dimensional feature map into p chunks, each chunk is pooled to a single feature by taking the largest value within that chunk".
Hi siddsax,
I wanna ask about the pooling layer because you're using a sliding max pooling. XML-CNN use dynamic max pooling with the definition "For a p document with m words, we evenly divide its m-dimensional feature map into p chunks, each chunk is pooled to a single feature by taking the largest value within that chunk".