Max-pooling Convolutional Neural Networks Research Articles

Improving Distant Supervised Relation Extraction with Noise Detection Strategy

Distant supervised relation extraction (DSRE) is widely used to extract novel relational facts from plain text, so as to improve the knowledge graph. However, distant supervision inevitably suffers from the noisy labeling problem that will severely damage the performance of relation extraction. Currently, most DSRE methods are mainly focused on reducing the weights of noisy sentences, ignoring the bag-level noise where all sentences in a bag are wrongly labeled. In this paper, we present a novel noise detection-based relation extraction approach (NDRE) to automatically detect noisy labels with entity information and dynamically correct them, which can alleviate both instance-level and bag-level noisy problems. By this means, we can extend the dataset from the Web tables without introducing more noise. In this approach, to embed the semantics of sentences from corpus and web tables, we firstly propose a powerful sentence coder that employs an internal multi-head self-attention mechanism between the piecewise max-pooling convolutional neural network. Second, we adopt a noise detection strategy, which is expected to dynamically detect and correct the original noisy label according to the similarity between sentence representation and entity-aware embeddings. Then, we aggregate the information from corpus and web tables to make the final relation prediction. Experimental results on a public benchmark dataset demonstrate that our proposed approach achieves significant improvements over the state-of-the-art baselines and can effectively reduce the noisy labeling problem.

Automatic Identification of the Activity Area in Brain with Deep Neural Networks

We use deep max-pooling convolutional neural networks to address a problem of neuroanatomy, namely, the automatic segmentation of cerebral cortex structures of laboratory rat depicted in stacks of Two-photon microscopy images and detect the change areas when stimulation occurs. We classify each pixel in the image by training a CNN network, using a square window to predict the probability of the central pixel for each class. After classification, we perform the post-processing on the output produced by CNN. At last, we depict the areas that we interested through a threshold value.