{"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/cefr-based-sentence-difficulty-annotation-and","title":"CEFR-Based Sentence Difficulty Annotation and Assessment","arxiv_id":"2210.11766","date":"2022-10-21","proceeding":null,"authors":["Yuki Arase","Satoru Uchida","Tomoyuki Kajiwara"],"abstract":"Controllable text simplification is a crucial assistive technique for language learning and teaching. One of the primary factors hindering its advancement is the lack of a corpus annotated with sentence difficulty levels based on language ability descriptions. To address this problem, we created the CEFR-based Sentence Profile (CEFR-SP) corpus, containing 17k English sentences annotated with the levels based on the Common European Framework of Reference for Languages assigned by English-education professionals. In addition, we propose a sentence-level assessment model to handle unbalanced level distribution because the most basic and highly proficient sentences are naturally scarce. In the experiments in this study, our method achieved a macro-F1 score of 84.5% in the level assessment, thus outperforming strong baselines employed in readability assessment.","url_abs":"https://arxiv.org/abs/2210.11766v1","url_pdf":"https://arxiv.org/pdf/2210.11766v1.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":"cefr-based-sentence-difficulty-annotation-and","repo_url":"https://github.com/yukiar/cefr-sp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"text-simplification","task_name":"Text Simplification"}],"methods":[],"datasets_introduced":[{"slug":"cefr-sp","name":"CEFR-SP","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2210.11766","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.11766"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yukiar/cefr-sp","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/yukiar/CEFR-SP","reach":{"status":"ok"}}],"summary":{"ran":1,"ran_draft_wrong":2,"unverified":5},"by_repo_kind":{"official":{"samples":8,"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":8,"samples":[{"code_sha256_prefix":"572642549be8d87d","entry":"CEFRDataset","repo":"yukiar/CEFR-SP","repo_kind":"official","path":"src/model.py","file_url":"https://github.com/yukiar/CEFR-SP/blob/HEAD/src/model.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":"572642549be8d87d"}},{"code_sha256_prefix":"7b7b061724169807","entry":"mean_pooling","repo":"yukiar/CEFR-SP","repo_kind":"official","path":"src/model.py","file_url":"https://github.com/yukiar/CEFR-SP/blob/HEAD/src/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7b7b061724169807"}},{"code_sha256_prefix":"52aa6a438836ec5d","entry":"read_corpus","repo":"yukiar/CEFR-SP","repo_kind":"official","path":"src/model.py","file_url":"https://github.com/yukiar/CEFR-SP/blob/HEAD/src/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"52aa6a438836ec5d"}},{"code_sha256_prefix":"6a90445d562ca033","entry":"LevelEstimaterBase","repo":"yukiar/CEFR-SP","repo_kind":"official","path":"src/model.py","file_url":"https://github.com/yukiar/CEFR-SP/blob/HEAD/src/model.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":"6a90445d562ca033"}},{"code_sha256_prefix":"b2b5714c44ee589a","entry":"LevelEstimaterClassification","repo":"yukiar/CEFR-SP","repo_kind":"official","path":"src/model.py","file_url":"https://github.com/yukiar/CEFR-SP/blob/HEAD/src/model.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":"b2b5714c44ee589a"}},{"code_sha256_prefix":"d0224c5c22b5838e","entry":"_conversion","repo":"yukiar/CEFR-SP","repo_kind":"official","path":"src/model.py","file_url":"https://github.com/yukiar/CEFR-SP/blob/HEAD/src/model.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":"d0224c5c22b5838e"}},{"code_sha256_prefix":"c18f938523ca6b23","entry":"convert_numeral_to_six_levels","repo":"yukiar/CEFR-SP","repo_kind":"official","path":"src/model.py","file_url":"https://github.com/yukiar/CEFR-SP/blob/HEAD/src/model.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":"c18f938523ca6b23"}},{"code_sha256_prefix":"0ba7bf6243ff28e8","entry":"eval_multiclass","repo":"yukiar/CEFR-SP","repo_kind":"official","path":"src/model.py","file_url":"https://github.com/yukiar/CEFR-SP/blob/HEAD/src/model.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":"0ba7bf6243ff28e8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}