{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/deep-residual-learning-for-weakly-supervised","title":"Deep Residual Learning for Weakly-Supervised Relation Extraction","arxiv_id":"1707.08866","date":"2017-07-27","proceeding":"EMNLP 2017 9","authors":["Yi Yao Huang","William Yang Wang"],"abstract":"Deep residual learning (ResNet) is a new method for training very deep neural\nnetworks using identity map-ping for shortcut connections. ResNet has won the\nImageNet ILSVRC 2015 classification task, and achieved state-of-the-art\nperformances in many computer vision tasks. However, the effect of residual\nlearning on noisy natural language processing tasks is still not well\nunderstood. In this paper, we design a novel convolutional neural network (CNN)\nwith residual learning, and investigate its impacts on the task of distantly\nsupervised noisy relation extraction. In contradictory to popular beliefs that\nResNet only works well for very deep networks, we found that even with 9 layers\nof CNNs, using identity mapping could significantly improve the performance for\ndistantly-supervised relation extraction.","url_abs":"http://arxiv.org/abs/1707.08866v1","url_pdf":"http://arxiv.org/pdf/1707.08866v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"deep-residual-learning-for-weakly-supervised","repo_url":"https://github.com/liuzhencheng/zcliu_code","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"relation-extraction","task_name":"Relation Extraction"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1707.08866","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}