{"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/codesc-a-large-code-description-parallel","title":"CoDesc: A Large Code-Description Parallel Dataset","arxiv_id":"2105.14220","date":"2021-05-29","proceeding":null,"authors":["Masum Hasan","Tanveer Muttaqueen","Abdullah Al Ishtiaq","Kazi Sajeed Mehrab","Md. Mahim Anjum Haque","Tahmid Hasan","Wasi Uddin Ahmad","Anindya Iqbal","Rifat Shahriyar"],"abstract":"Translation between natural language and source code can help software development by enabling developers to comprehend, ideate, search, and write computer programs in natural language. Despite growing interest from the industry and the research community, this task is often difficult due to the lack of large standard datasets suitable for training deep neural models, standard noise removal methods, and evaluation benchmarks. This leaves researchers to collect new small-scale datasets, resulting in inconsistencies across published works. In this study, we present CoDesc -- a large parallel dataset composed of 4.2 million Java methods and natural language descriptions. With extensive analysis, we identify and remove prevailing noise patterns from the dataset. We demonstrate the proficiency of CoDesc in two complementary tasks for code-description pairs: code summarization and code search. We show that the dataset helps improve code search by up to 22\\% and achieves the new state-of-the-art in code summarization. Furthermore, we show CoDesc's effectiveness in pre-training--fine-tuning setup, opening possibilities in building pretrained language models for Java. To facilitate future research, we release the dataset, a data processing tool, and a benchmark at \\url{https://github.com/csebuetnlp/CoDesc}.","url_abs":"https://arxiv.org/abs/2105.14220v1","url_pdf":"https://arxiv.org/pdf/2105.14220v1.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":"codesc-a-large-code-description-parallel","repo_url":"https://github.com/csebuetnlp/CoDesc","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"code-search","task_name":"Code Search"},{"task_slug":"code-summarization-1","task_name":"Code Summarization"},{"task_slug":"code-summarization","task_name":"Source Code Summarization"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[{"slug":"codesc","name":"CoDesc","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/code-search-on-codesc","task":"Code Search","dataset":"CoDesc","model":"Self-attention","rank_in_archive_order":1,"of":3,"metrics":{"Test MRR":"0.839"},"uses_additional_data":false},{"leaderboard":"/sota/code-search-on-codesc","task":"Code Search","dataset":"CoDesc","model":"NBOW","rank_in_archive_order":2,"of":3,"metrics":{"Test MRR":"0.812"},"uses_additional_data":false},{"leaderboard":"/sota/code-search-on-codesc","task":"Code Search","dataset":"CoDesc","model":"RNN","rank_in_archive_order":3,"of":3,"metrics":{"Test MRR":"0.766"},"uses_additional_data":false},{"leaderboard":"/sota/source-code-summarization-on-codesc","task":"Source Code Summarization","dataset":"CoDesc","model":"Transformer","rank_in_archive_order":1,"of":1,"metrics":{"BLEU-4":"45.89"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2105.14220","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.14220"}},"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/csebuetnlp/CoDesc","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/csebuetnlp/TransCoder","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran_violates":1,"unverified":7},"by_repo_kind":{"official":{"samples":8,"ran":1,"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":0,"samples":[{"code_sha256_prefix":"8c0dec327bfce0f2","entry":"str2bool","repo":"csebuetnlp/CoDesc","repo_kind":"official","path":"CodeSummarization/c2nl/config.py","file_url":"https://github.com/csebuetnlp/CoDesc/blob/HEAD/CodeSummarization/c2nl/config.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8c0dec327bfce0f2"}},{"code_sha256_prefix":"cb64b0975f6c0461","entry":"create_sample","repo":"csebuetnlp/CoDesc","repo_kind":"official","path":"Dataset_Preparation/Preprocess_CSN.py","file_url":"https://github.com/csebuetnlp/CoDesc/blob/HEAD/Dataset_Preparation/Preprocess_CSN.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cb64b0975f6c0461"}},{"code_sha256_prefix":"d04ac70d96d9c8bd","entry":"get_model_args","repo":"csebuetnlp/CoDesc","repo_kind":"official","path":"CodeSummarization/c2nl/config.py","file_url":"https://github.com/csebuetnlp/CoDesc/blob/HEAD/CodeSummarization/c2nl/config.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d04ac70d96d9c8bd"}},{"code_sha256_prefix":"c77d305475488a3d","entry":"override_model_args","repo":"csebuetnlp/CoDesc","repo_kind":"official","path":"CodeSummarization/c2nl/config.py","file_url":"https://github.com/csebuetnlp/CoDesc/blob/HEAD/CodeSummarization/c2nl/config.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c77d305475488a3d"}},{"code_sha256_prefix":"81cd041092327b37","entry":"str_int_str_case_tokenizer","repo":"csebuetnlp/CoDesc","repo_kind":"official","path":"Tokenizer/CodePreprocess_final.py","file_url":"https://github.com/csebuetnlp/CoDesc/blob/HEAD/Tokenizer/CodePreprocess_final.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"81cd041092327b37"}},{"code_sha256_prefix":"002866c5d9bea425","entry":"str_int_str_case_tokenizer","repo":"csebuetnlp/CoDesc","repo_kind":"official","path":"Tokenizer/NLPreprocess_final.py","file_url":"https://github.com/csebuetnlp/CoDesc/blob/HEAD/Tokenizer/NLPreprocess_final.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"002866c5d9bea425"}},{"code_sha256_prefix":"d1365e142f9912b3","entry":"tokenize_with_snake_case","repo":"csebuetnlp/CoDesc","repo_kind":"official","path":"Tokenizer/CodePreprocess_final.py","file_url":"https://github.com/csebuetnlp/CoDesc/blob/HEAD/Tokenizer/CodePreprocess_final.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d1365e142f9912b3"}},{"code_sha256_prefix":"925b4c4f3d361730","entry":"tokenize_with_str_int_str","repo":"csebuetnlp/CoDesc","repo_kind":"official","path":"Tokenizer/CodePreprocess_final.py","file_url":"https://github.com/csebuetnlp/CoDesc/blob/HEAD/Tokenizer/CodePreprocess_final.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"925b4c4f3d361730"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}