{"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/hengam-an-adversarially-trained-transformer","title":"Hengam: An Adversarially Trained Transformer for Persian Temporal Tagging","arxiv_id":null,"date":"2022-11-20","proceeding":"Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing 2022 11","authors":["Sajad Mirzababaei","Amir Hossein Kargaran","Hinrich Schütze","Ehsaneddin Asgari"],"abstract":"Many NLP main tasks benefit from an accurate understanding of temporal expressions, e.g., text summarization, question answering, and information retrieval. This paper introduces Hengam, an adversarially trained transformer for Persian temporal tagging outperforming state-of-the-art approaches on a diverse and manually created dataset. We create Hengam in the following concrete steps: (1) we develop HengamTagger, an extensible rule-based tool that can extract temporal expressions from a set of diverse language-specific patterns for any language of interest. (2) We apply HengamTagger to annotate temporal tags in a large and diverse Persian text collection (covering both formal and informal contexts) to be used as weakly labeled data. (3) We introduce an adversarially trained transformer model on HengamCorpus that can generalize over the HengamTagger’s rules. We create HengamGold, the first high-quality gold standard for Persian temporal tagging. Our trained adversarial HengamTransformer not only achieves the best performance in terms of the F1-score (a type F1-Score of 95.42 and a partial F1-Score of 91.60) but also successfully deals with language ambiguities and incorrect spellings. Our code, data, and models are publicly available at https://github.com/kargaranamir/Hengam.","url_abs":"https://aclanthology.org/2022.aacl-main.74/","url_pdf":"https://aclanthology.org/2022.aacl-main.74.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":"hengam-an-adversarially-trained-transformer","repo_url":"https://github.com/kargaranamir/hengam","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"hengam-an-adversarially-trained-transformer","repo_url":"https://github.com/kargaranamir/parstdex","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"information-retrieval","task_name":"Information Retrieval"},{"task_slug":"named-entity-recognition-ner","task_name":"Named Entity Recognition (NER)"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"temporal-tagging","task_name":"Temporal Tagging"},{"task_slug":"text-anonymization","task_name":"Text Anonymization"},{"task_slug":"text-summarization","task_name":"Text Summarization"}],"methods":[],"datasets_introduced":[{"slug":"hengamcorpus","name":"HengamCorpus","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/temporal-tagging-on-hengamcorpus","task":"Temporal Tagging","dataset":"HengamCorpus","model":"Hengam","rank_in_archive_order":1,"of":1,"metrics":{"Entity F1 (partial)":"91.6"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}