{"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/shoma-at-parseme-shared-task-on-automatic","title":"SHOMA at Parseme Shared Task on Automatic Identification of VMWEs: Neural Multiword Expression Tagging with High Generalisation","arxiv_id":"1809.03056","date":"2018-09-09","proceeding":null,"authors":["Shiva Taslimipoor","Omid Rohanian"],"abstract":"This paper presents a language-independent deep learning architecture adapted\nto the task of multiword expression (MWE) identification. We employ a neural\narchitecture comprising of convolutional and recurrent layers with the addition\nof an optional CRF layer at the top. This system participated in the open track\nof the Parseme shared task on automatic identification of verbal MWEs due to\nthe use of pre-trained wikipedia word embeddings. It outperformed all\nparticipating systems in both open and closed tracks with the overall\nmacro-average MWE-based F1 score of 58.09 averaged among all languages. A\nparticular strength of the system is its superior performance on unseen data\nentries.","url_abs":"http://arxiv.org/abs/1809.03056v1","url_pdf":"http://arxiv.org/pdf/1809.03056v1.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":"shoma-at-parseme-shared-task-on-automatic","repo_url":"https://github.com/shivaat/VMWE-Identification","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[{"method_slug":"crf","method_name":"CRF"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1809.03056","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}