{"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/ml-net-multi-label-classification-of","title":"ML-Net: multi-label classification of biomedical texts with deep neural networks","arxiv_id":"1811.05475","date":"2018-11-13","proceeding":null,"authors":["Jingcheng Du","Qingyu Chen","Yifan Peng","Yang Xiang","Cui Tao","Zhiyong Lu"],"abstract":"In multi-label text classification, each textual document can be assigned\nwith one or more labels. Due to this nature, the multi-label text\nclassification task is often considered to be more challenging compared to the\nbinary or multi-class text classification problems. As an important task with\nbroad applications in biomedicine such as assigning diagnosis codes, a number\nof different computational methods (e.g. training and combining binary\nclassifiers for each label) have been proposed in recent years. However, many\nsuffered from modest accuracy and efficiency, with only limited success in\npractical use. We propose ML-Net, a novel deep learning framework, for\nmulti-label classification of biomedical texts. As an end-to-end system, ML-Net\ncombines a label prediction network with an automated label count prediction\nmechanism to output an optimal set of labels by leveraging both predicted\nconfidence score of each label and the contextual information in the target\ndocument. We evaluate ML-Net on three independent, publicly-available corpora\nin two kinds of text genres: biomedical literature and clinical notes. For\nevaluation, example-based measures such as precision, recall and f-measure are\nused. ML-Net is compared with several competitive machine learning baseline\nmodels. Our benchmarking results show that ML-Net compares favorably to the\nstate-of-the-art methods in multi-label classification of biomedical texts.\nML-NET is also shown to be robust when evaluated on different text genres in\nbiomedicine. Unlike traditional machine learning methods, ML-Net does not\nrequire human efforts in feature engineering and is highly efficient and\nscalable approach to tasks with a large set of labels (no need to build\nindividual classifiers for each separate label). Finally, ML-NET is able to\ndynamically estimate the label count based on the document context in a more\nsystematic and accurate manner.","url_abs":"http://arxiv.org/abs/1811.05475v2","url_pdf":"http://arxiv.org/pdf/1811.05475v2.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":"ml-net-multi-label-classification-of","repo_url":"https://github.com/jingcheng-du/ML_Net-1","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"ml-net-multi-label-classification-of","repo_url":"https://github.com/FelixHub/custom-LSEP-loss-function","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"ml-net-multi-label-classification-of","repo_url":"https://github.com/ncbi-nlp/BLUE_Benchmark","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"ml-net-multi-label-classification-of","repo_url":"https://github.com/ncbi-nlp/ML_Net","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"feature-engineering","task_name":"Feature Engineering"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"multi-label-classification-2","task_name":"MUlTI-LABEL-ClASSIFICATION"},{"task_slug":"multi-label-classification","task_name":"Multi-Label Classification"},{"task_slug":"multi-label-classification-of-biomedical","task_name":"Multi-Label Classification Of Biomedical Texts"},{"task_slug":"multi-label-text-classification","task_name":"Multi-Label Text Classification"},{"task_slug":"text-classification","task_name":"Text Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.05475","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}