{"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/europa-a-legal-multilingual-keyphrase","title":"EUROPA: A Legal Multilingual Keyphrase Generation Dataset","arxiv_id":"2403.00252","date":"2024-03-01","proceeding":null,"authors":["Olivier Salaün","Frédéric Piedboeuf","Guillaume Le Berre","David Alfonso Hermelo","Philippe Langlais"],"abstract":"Keyphrase generation has primarily been explored within the context of academic research articles, with a particular focus on scientific domains and the English language. In this work, we present EUROPA, a dataset for multilingual keyphrase generation in the legal domain. It is derived from legal judgments from the Court of Justice of the European Union (EU), and contains instances in all 24 EU official languages. We run multilingual models on our corpus and analyze the results, showing room for improvement on a domain-specific multilingual corpus such as the one we present.","url_abs":"https://arxiv.org/abs/2403.00252v2","url_pdf":"https://arxiv.org/pdf/2403.00252v2.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":"europa-a-legal-multilingual-keyphrase","repo_url":"https://github.com/rali-udem/europa","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"articles","task_name":"Articles"},{"task_slug":"keyphrase-generation","task_name":"Keyphrase Generation"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[{"slug":"europa","name":"EUROPA","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.00252","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.00252"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/rali-udem/europa","reach":{"status":"ok"}}],"summary":{"ran":3,"unverified":3},"by_repo_kind":{"official":{"samples":6,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":6,"samples":[{"code_sha256_prefix":"cd9741704cdd15cd","entry":"estonian_shell_stemmer","repo":"rali-udem/europa","repo_kind":"official","path":"eval/stemmers/estonian_stemmer.py","file_url":"https://github.com/rali-udem/europa/blob/HEAD/eval/stemmers/estonian_stemmer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cd9741704cdd15cd"}},{"code_sha256_prefix":"4198126406ebacee","entry":"stem_word_list","repo":"rali-udem/europa","repo_kind":"official","path":"eval/eval_OpenNMT_KPG.py","file_url":"https://github.com/rali-udem/europa/blob/HEAD/eval/eval_OpenNMT_KPG.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4198126406ebacee"}},{"code_sha256_prefix":"3369405fbddbef8b","entry":"validate_phrases","repo":"rali-udem/europa","repo_kind":"official","path":"eval/eval_OpenNMT_KPG.py","file_url":"https://github.com/rali-udem/europa/blob/HEAD/eval/eval_OpenNMT_KPG.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3369405fbddbef8b"}},{"code_sha256_prefix":"08fc5c7a4e21a6c6","entry":"cz_stem","repo":"rali-udem/europa","repo_kind":"official","path":"eval/stemmers/czech_stemmer.py","file_url":"https://github.com/rali-udem/europa/blob/HEAD/eval/stemmers/czech_stemmer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"08fc5c7a4e21a6c6"}},{"code_sha256_prefix":"ebf6b35a7eb511cb","entry":"evaluate","repo":"rali-udem/europa","repo_kind":"official","path":"eval/eval_OpenNMT_KPG.py","file_url":"https://github.com/rali-udem/europa/blob/HEAD/eval/eval_OpenNMT_KPG.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ebf6b35a7eb511cb"}},{"code_sha256_prefix":"e4eabc88f44d21af","entry":"sk_stem","repo":"rali-udem/europa","repo_kind":"official","path":"eval/stemmers/stemm_sk.py","file_url":"https://github.com/rali-udem/europa/blob/HEAD/eval/stemmers/stemm_sk.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e4eabc88f44d21af"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}