{"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/structured-prediction-as-translation-between-1","title":"Structured Prediction as Translation between Augmented Natural Languages","arxiv_id":"2101.05779","date":"2021-01-14","proceeding":"ICLR 2021 1","authors":["Giovanni Paolini","Ben Athiwaratkun","Jason Krone","Jie Ma","Alessandro Achille","Rishita Anubhai","Cicero Nogueira dos santos","Bing Xiang","Stefano Soatto"],"abstract":"We propose a new framework, Translation between Augmented Natural Languages (TANL), to solve many structured prediction language tasks including joint entity and relation extraction, nested named entity recognition, relation classification, semantic role labeling, event extraction, coreference resolution, and dialogue state tracking. Instead of tackling the problem by training task-specific discriminative classifiers, we frame it as a translation task between augmented natural languages, from which the task-relevant information can be easily extracted. Our approach can match or outperform task-specific models on all tasks, and in particular, achieves new state-of-the-art results on joint entity and relation extraction (CoNLL04, ADE, NYT, and ACE2005 datasets), relation classification (FewRel and TACRED), and semantic role labeling (CoNLL-2005 and CoNLL-2012). We accomplish this while using the same architecture and hyperparameters for all tasks and even when training a single model to solve all tasks at the same time (multi-task learning). Finally, we show that our framework can also significantly improve the performance in a low-resource regime, thanks to better use of label semantics.","url_abs":"https://arxiv.org/abs/2101.05779v3","url_pdf":"https://arxiv.org/pdf/2101.05779v3.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":"structured-prediction-as-translation-between-1","repo_url":"https://github.com/amazon-research/tanl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"structured-prediction-as-translation-between-1","repo_url":"https://github.com/amazon-science/tanl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"coreference-resolution","task_name":"Coreference Resolution"},{"task_slug":"dialogue-state-tracking","task_name":"Dialogue State Tracking"},{"task_slug":"event-extraction","task_name":"Event Extraction"},{"task_slug":"joint-entity-and-relation-extraction","task_name":"Joint Entity and Relation Extraction"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"named-entity-recognition-1","task_name":"Named Entity Recognition"},{"task_slug":"named-entity-recognition-ner","task_name":"Named Entity Recognition (NER)"},{"task_slug":"nested-named-entity-recognition","task_name":"Nested Named Entity Recognition"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"relation-classification","task_name":"Relation Classification"},{"task_slug":"relation-extraction","task_name":"Relation Extraction"},{"task_slug":"semantic-role-labeling","task_name":"Semantic Role Labeling"},{"task_slug":"structured-prediction","task_name":"Structured Prediction"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"coreference-resolution-1","task_name":"coreference-resolution"},{"task_slug":"named-entity-recognition","task_name":"named-entity-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/relation-classification-on-tacred-1","task":"Relation Classification","dataset":"TACRED","model":"TANL (multi-task)","rank_in_archive_order":3,"of":17,"metrics":{"F1":"61.9"},"uses_additional_data":false},{"leaderboard":"/sota/relation-classification-on-tacred-1","task":"Relation Classification","dataset":"TACRED","model":"TANL","rank_in_archive_order":12,"of":17,"metrics":{"F1":"71.9"},"uses_additional_data":false},{"leaderboard":"/sota/relation-extraction-on-conll04","task":"Relation Extraction","dataset":"CoNLL04","model":"TANL","rank_in_archive_order":12,"of":16,"metrics":{"RE+ Micro F1":"72.6"},"uses_additional_data":false},{"leaderboard":"/sota/relation-extraction-on-tacred","task":"Relation Extraction","dataset":"TACRED","model":"TANL","rank_in_archive_order":15,"of":40,"metrics":{"F1":"71.9"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2101.05779","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}