{"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/label-aware-document-representation-via","title":"Label-aware Document Representation via Hybrid Attention for Extreme Multi-Label Text Classification","arxiv_id":"1905.10070","date":"2019-05-24","proceeding":null,"authors":["Xin Huang","Boli Chen","Lin Xiao","Liping Jing"],"abstract":"Extreme multi-label text classification (XMTC) aims at tagging a document with most relevant labels from an extremely large-scale label set. It is a challenging problem especially for the tail labels because there are only few training documents to build classifier. This paper is motivated to better explore the semantic relationship between each document and extreme labels by taking advantage of both document content and label correlation. Our objective is to establish an explicit label-aware representation for each document with a hybrid attention deep neural network model(LAHA). LAHA consists of three parts. The first part adopts a multi-label self-attention mechanism to detect the contribution of each word to labels. The second part exploits the label structure and document content to determine the semantic connection between words and labels in a same latent space. An adaptive fusion strategy is designed in the third part to obtain the final label-aware document representation so that the essence of previous two parts can be sufficiently integrated. Extensive experiments have been conducted on six benchmark datasets by comparing with the state-of-the-art methods. The results show the superiority of our proposed LAHA method, especially on the tail labels.","url_abs":"https://arxiv.org/abs/1905.10070v2","url_pdf":"https://arxiv.org/pdf/1905.10070v2.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":"label-aware-document-representation-via","repo_url":"https://github.com/HX-idiot/Hybrid_Attention_XML","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"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":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/multi-label-text-classification-on-aapd","task":"Multi-Label Text Classification","dataset":"AAPD","model":"LAHA","rank_in_archive_order":2,"of":5,"metrics":{"P@1":"84.48","P@3":"60.72","P@5":"41.19","nDCG@3":"80.11","nDCG@5":"83.7"},"uses_additional_data":false},{"leaderboard":"/sota/multi-label-text-classification-on-amazon-12k","task":"Multi-Label Text Classification","dataset":"Amazon-12K","model":"LAHA","rank_in_archive_order":1,"of":1,"metrics":{"P@1":"94.87","P@3":"79.16","P@5":"63.16","nDCG@3":"89.13","nDCG@5":"87.57"},"uses_additional_data":false},{"leaderboard":"/sota/multi-label-text-classification-on-eur-lex","task":"Multi-Label Text Classification","dataset":"EUR-Lex","model":"LAHA","rank_in_archive_order":3,"of":3,"metrics":{"P@1":"74.95","P@3":"61.48","P@5":"50.71","nDCG@3":"64.89","nDCG@5":"59.28"},"uses_additional_data":false},{"leaderboard":"/sota/multi-label-text-classification-on-kan-shan","task":"Multi-Label Text Classification","dataset":"Kan-Shan Cup","model":"LAHA","rank_in_archive_order":1,"of":1,"metrics":{"P@1":"54.38","P@3":"34.6","P@5":"25.88","nDCG@3":"51.7","nDCG@5":"54.65"},"uses_additional_data":false},{"leaderboard":"/sota/multi-label-text-classification-on-wiki-30k","task":"Multi-Label Text Classification","dataset":"Wiki-30K","model":"LAHA","rank_in_archive_order":1,"of":1,"metrics":{"P@1":"84.18","P@3":"73.14","P@5":"62.87","nDCG@3":"75.64","nDCG@5":"67.82"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1905.10070","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}