{"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/semantic-unit-based-dilated-convolution-for","title":"Semantic-Unit-Based Dilated Convolution for Multi-Label Text Classification","arxiv_id":"1808.08561","date":"2018-08-26","proceeding":"EMNLP 2018 10","authors":["Junyang Lin","Qi Su","Pengcheng Yang","Shuming Ma","Xu sun"],"abstract":"We propose a novel model for multi-label text classification, which is based\non sequence-to-sequence learning. The model generates higher-level semantic\nunit representations with multi-level dilated convolution as well as a\ncorresponding hybrid attention mechanism that extracts both the information at\nthe word-level and the level of the semantic unit. Our designed dilated\nconvolution effectively reduces dimension and supports an exponential expansion\nof receptive fields without loss of local information, and the\nattention-over-attention mechanism is able to capture more summary relevant\ninformation from the source context. Results of our experiments show that the\nproposed model has significant advantages over the baseline models on the\ndataset RCV1-V2 and Ren-CECps, and our analysis demonstrates that our model is\ncompetitive to the deterministic hierarchical models and it is more robust to\nclassifying low-frequency labels.","url_abs":"http://arxiv.org/abs/1808.08561v2","url_pdf":"http://arxiv.org/pdf/1808.08561v2.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":"semantic-unit-based-dilated-convolution-for","repo_url":"https://github.com/lancopku/SU4MLC","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"multi-label-text-classification-1","task_name":"Multi Label Text Classification"},{"task_slug":"multi-label-text-classification","task_name":"Multi-Label Text Classification"},{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":"text-classification-1","task_name":"text-classification"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dilated-convolution","method_name":"Dilated Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1808.08561","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}