{"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-amr-parsing-with-noisy-knowledge","title":"Multilingual AMR Parsing with Noisy Knowledge Distillation","arxiv_id":"2109.15196","date":"2021-09-30","proceeding":"Findings (EMNLP) 2021 11","authors":["Deng Cai","Xin Li","Jackie Chun-Sing Ho","Lidong Bing","Wai Lam"],"abstract":"We study multilingual AMR parsing from the perspective of knowledge distillation, where the aim is to learn and improve a multilingual AMR parser by using an existing English parser as its teacher. We constrain our exploration in a strict multilingual setting: there is but one model to parse all different languages including English. We identify that noisy input and precise output are the key to successful distillation. Together with extensive pre-training, we obtain an AMR parser whose performances surpass all previously published results on four different foreign languages, including German, Spanish, Italian, and Chinese, by large margins (up to 18.8 \\textsc{Smatch} points on Chinese and on average 11.3 \\textsc{Smatch} points). Our parser also achieves comparable performance on English to the latest state-of-the-art English-only parser.","url_abs":"https://arxiv.org/abs/2109.15196v2","url_pdf":"https://arxiv.org/pdf/2109.15196v2.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-amr-parsing-with-noisy-knowledge","repo_url":"https://github.com/jcyk/xamr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"amr-parsing","task_name":"AMR Parsing"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2109.15196","atlas_url":"https://app.syntology.ai/?focus=2109.15196","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}