{"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/edinburgh-at-semeval-2022-task-1-jointly","title":"Edinburgh at SemEval-2022 Task 1: Jointly Fishing for Word Embeddings and Definitions","arxiv_id":null,"date":"2022-07-01","proceeding":"SemEval (NAACL) 2022 7","authors":["Pinzhen Chen","Zheng Zhao"],"abstract":"This paper presents a winning submission to the SemEval 2022 Task 1 on two sub-tasks: reverse dictionary and definition modelling. We leverage a recently proposed unified model with multi-task training. It utilizes data symmetrically and learns to tackle both tracks concurrently. Analysis shows that our system performs consistently on diverse languages, and works the best with sgns embeddings. Yet, char and electra carry intriguing properties. The two tracks’ best results are always in differing subsets grouped by linguistic annotations. In this task, the quality of definition generation lags behind, and BLEU scores might be misleading.","url_abs":"https://aclanthology.org/2022.semeval-1.8","url_pdf":"https://aclanthology.org/2022.semeval-1.8.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":"edinburgh-at-semeval-2022-task-1-jointly","repo_url":"https://github.com/pinzhenchen/unifiedrevdicdefmod","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"definition-extraction","task_name":"Definition Extraction"},{"task_slug":"definition-modelling","task_name":"Definition Modelling"},{"task_slug":"reverse-dictionary","task_name":"Reverse Dictionary"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}