{"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/a-new-dataset-and-empirical-study-for","title":"A New Dataset and Empirical Study for Sentence Simplification in Chinese","arxiv_id":"2306.04188","date":"2023-06-07","proceeding":null,"authors":["Shiping Yang","Renliang Sun","Xiaojun Wan"],"abstract":"Sentence Simplification is a valuable technique that can benefit language learners and children a lot. However, current research focuses more on English sentence simplification. The development of Chinese sentence simplification is relatively slow due to the lack of data. To alleviate this limitation, this paper introduces CSS, a new dataset for assessing sentence simplification in Chinese. We collect manual simplifications from human annotators and perform data analysis to show the difference between English and Chinese sentence simplifications. Furthermore, we test several unsupervised and zero/few-shot learning methods on CSS and analyze the automatic evaluation and human evaluation results. In the end, we explore whether Large Language Models can serve as high-quality Chinese sentence simplification systems by evaluating them on CSS.","url_abs":"https://arxiv.org/abs/2306.04188v1","url_pdf":"https://arxiv.org/pdf/2306.04188v1.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":"a-new-dataset-and-empirical-study-for","repo_url":"https://github.com/maybenotime/css","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2306.04188","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.04188"}},"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/lm-sys/FastChat","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/maybenotime/css","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/THUDM/ChatGLM-6B","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":3,"ran_draft_wrong":5,"unverified":1},"by_repo_kind":{"official":{"samples":4,"ran":4,"repositories":1},"found_in_text":{"samples":5,"ran":4,"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":4,"samples":[{"code_sha256_prefix":"bda4be9967b8d807","entry":"auto_configure_device_map","repo":"THUDM/ChatGLM-6B","repo_kind":"found_in_text","path":"utils.py","file_url":"https://github.com/THUDM/ChatGLM-6B/blob/HEAD/utils.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bda4be9967b8d807"}},{"code_sha256_prefix":"20f3c3d6999848e9","entry":"build_prompt","repo":"THUDM/ChatGLM-6B","repo_kind":"found_in_text","path":"cli_demo.py","file_url":"https://github.com/THUDM/ChatGLM-6B/blob/HEAD/cli_demo.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"20f3c3d6999848e9"}},{"code_sha256_prefix":"7ce6ba0a6898058f","entry":"build_prompt","repo":"THUDM/ChatGLM-6B","repo_kind":"found_in_text","path":"cli_demo_vision.py","file_url":"https://github.com/THUDM/ChatGLM-6B/blob/HEAD/cli_demo_vision.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7ce6ba0a6898058f"}},{"code_sha256_prefix":"83f4dfab09dd0247","entry":"load_data","repo":"maybenotime/css","repo_kind":"official","path":"dataset_statistics/feature_extraction.py","file_url":"https://github.com/maybenotime/css/blob/HEAD/dataset_statistics/feature_extraction.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"83f4dfab09dd0247"}},{"code_sha256_prefix":"0eacefae3afb6810","entry":"load_dev_data","repo":"maybenotime/css","repo_kind":"official","path":"baseline_code/finetune.py","file_url":"https://github.com/maybenotime/css/blob/HEAD/baseline_code/finetune.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0eacefae3afb6810"}},{"code_sha256_prefix":"a4c0b20fe17f4aab","entry":"load_train_data","repo":"maybenotime/css","repo_kind":"official","path":"baseline_code/finetune.py","file_url":"https://github.com/maybenotime/css/blob/HEAD/baseline_code/finetune.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a4c0b20fe17f4aab"}},{"code_sha256_prefix":"826ceb601fb31250","entry":"parse_text","repo":"THUDM/ChatGLM-6B","repo_kind":"found_in_text","path":"web_demo.py","file_url":"https://github.com/THUDM/ChatGLM-6B/blob/HEAD/web_demo.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"826ceb601fb31250"}},{"code_sha256_prefix":"2d434911a703e126","entry":"read_data","repo":"maybenotime/css","repo_kind":"official","path":"LLMs_result/Use_ChatGPT_simplification.py","file_url":"https://github.com/maybenotime/css/blob/HEAD/LLMs_result/Use_ChatGPT_simplification.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2d434911a703e126"}},{"code_sha256_prefix":"b461f4040f1eec9d","entry":"load_model_on_gpus","repo":"THUDM/ChatGLM-6B","repo_kind":"found_in_text","path":"utils.py","file_url":"https://github.com/THUDM/ChatGLM-6B/blob/HEAD/utils.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b461f4040f1eec9d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}