{"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/multilingual-hierarchical-attention-networks","title":"Multilingual Hierarchical Attention Networks for Document Classification","arxiv_id":"1707.00896","date":"2017-07-04","proceeding":"IJCNLP 2017 11","authors":["Nikolaos Pappas","Andrei Popescu-Belis"],"abstract":"Hierarchical attention networks have recently achieved remarkable performance\nfor document classification in a given language. However, when multilingual\ndocument collections are considered, training such models separately for each\nlanguage entails linear parameter growth and lack of cross-language transfer.\nLearning a single multilingual model with fewer parameters is therefore a\nchallenging but potentially beneficial objective. To this end, we propose\nmultilingual hierarchical attention networks for learning document structures,\nwith shared encoders and/or shared attention mechanisms across languages, using\nmulti-task learning and an aligned semantic space as input. We evaluate the\nproposed models on multilingual document classification with disjoint label\nsets, on a large dataset which we provide, with 600k news documents in 8\nlanguages, and 5k labels. The multilingual models outperform monolingual ones\nin low-resource as well as full-resource settings, and use fewer parameters,\nthus confirming their computational efficiency and the utility of\ncross-language transfer.","url_abs":"http://arxiv.org/abs/1707.00896v4","url_pdf":"http://arxiv.org/pdf/1707.00896v4.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":"multilingual-hierarchical-attention-networks","repo_url":"https://github.com/idiap/mhan","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"multilingual-hierarchical-attention-networks","repo_url":"https://github.com/idiap/gile","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"document-classification","task_name":"Document Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1707.00896","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}