{"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/cosqa-20000-web-queries-for-code-search-and","title":"CoSQA: 20,000+ Web Queries for Code Search and Question Answering","arxiv_id":"2105.13239","date":"2021-05-27","proceeding":"ACL 2021 5","authors":["JunJie Huang","Duyu Tang","Linjun Shou","Ming Gong","Ke Xu","Daxin Jiang","Ming Zhou","Nan Duan"],"abstract":"Finding codes given natural language query isb eneficial to the productivity of software developers. Future progress towards better semantic matching between query and code requires richer supervised training resources. To remedy this, we introduce the CoSQA dataset.It includes 20,604 labels for pairs of natural language queries and codes, each annotated by at least 3 human annotators. We further introduce a contrastive learning method dubbed CoCLR to enhance query-code matching, which works as a data augmenter to bring more artificially generated training instances. We show that evaluated on CodeXGLUE with the same CodeBERT model, training on CoSQA improves the accuracy of code question answering by 5.1%, and incorporating CoCLR brings a further improvement of 10.5%.","url_abs":"https://arxiv.org/abs/2105.13239v1","url_pdf":"https://arxiv.org/pdf/2105.13239v1.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":"cosqa-20000-web-queries-for-code-search-and","repo_url":"https://github.com/Jun-jie-Huang/CoCLR","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"code-search","task_name":"Code Search"},{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"natural-language-queries","task_name":"Natural Language Queries"},{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[{"method_slug":"codebert","method_name":"CodeBERT"},{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[{"slug":"cosqa","name":"CoSQA","full_name":"Code Search and Question Answering"}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2105.13239","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.13239"}},"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/Jun-jie-Huang/CoCLR","reach":null}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":0,"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":"db67ebb003be85b6","entry":"ModelContra","repo":"Jun-jie-Huang/CoCLR","repo_kind":"official","path":"code_search/models.py","file_url":"https://github.com/Jun-jie-Huang/CoCLR/blob/HEAD/code_search/models.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":"db67ebb003be85b6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}