{"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/adversarial-alignment-of-multilingual-models","title":"Adversarial Alignment of Multilingual Models for Extracting Temporal Expressions from Text","arxiv_id":"2005.09392","date":"2020-05-19","proceeding":"WS 2020 7","authors":["Lukas Lange","Anastasiia Iurshina","Heike Adel","Jannik Strötgen"],"abstract":"Although temporal tagging is still dominated by rule-based systems, there have been recent attempts at neural temporal taggers. However, all of them focus on monolingual settings. In this paper, we explore multilingual methods for the extraction of temporal expressions from text and investigate adversarial training for aligning embedding spaces to one common space. With this, we create a single multilingual model that can also be transferred to unseen languages and set the new state of the art in those cross-lingual transfer experiments.","url_abs":"https://arxiv.org/abs/2005.09392v1","url_pdf":"https://arxiv.org/pdf/2005.09392v1.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":[],"tasks":[{"task_slug":"cross-lingual-transfer","task_name":"Cross-Lingual Transfer"},{"task_slug":"temporal-tagging","task_name":"Temporal Tagging"}],"methods":[{"method_slug":"bert","method_name":"BERT"},{"method_slug":"fasttext","method_name":"fastText"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/temporal-tagging-on-basque-timebank","task":"Temporal Tagging","dataset":"Basque TimeBank","model":"Lange et al.","rank_in_archive_order":1,"of":1,"metrics":{"F1":"47.87"},"uses_additional_data":false},{"leaderboard":"/sota/temporal-tagging-on-catalan-timebank-1-0","task":"Temporal Tagging","dataset":"Catalan TimeBank 1.0","model":"Lange et al.","rank_in_archive_order":1,"of":1,"metrics":{"F1":"64.21"},"uses_additional_data":false},{"leaderboard":"/sota/temporal-tagging-on-french-timebank","task":"Temporal Tagging","dataset":"French Timebank","model":"Lange et al.","rank_in_archive_order":1,"of":1,"metrics":{"F1":"62.58"},"uses_additional_data":false},{"leaderboard":"/sota/temporal-tagging-on-krauts","task":"Temporal Tagging","dataset":"KRAUTS","model":"Lange et al.","rank_in_archive_order":1,"of":1,"metrics":{"F1":"66.53"},"uses_additional_data":false},{"leaderboard":"/sota/temporal-tagging-on-spanish-timebank-1-0","task":"Temporal Tagging","dataset":"Spanish TimeBank 1.0","model":"Lange et al.","rank_in_archive_order":1,"of":1,"metrics":{"F1":"79.55"},"uses_additional_data":false},{"leaderboard":"/sota/temporal-tagging-on-tempeval-3","task":"Temporal Tagging","dataset":"TempEval-3","model":"Lange et al.","rank_in_archive_order":5,"of":5,"metrics":{"F1":"74.8"},"uses_additional_data":false},{"leaderboard":"/sota/temporal-tagging-on-timebankpt","task":"Temporal Tagging","dataset":"TimeBankPT","model":"Lange et al.","rank_in_archive_order":1,"of":1,"metrics":{"F1":"75.47"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2005.09392","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}