{"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/incorporating-external-knowledge-through-pre","title":"Incorporating External Knowledge through Pre-training for Natural Language to Code Generation","arxiv_id":"2004.09015","date":"2020-04-20","proceeding":"ACL 2020 6","authors":["Frank F. Xu","Zhengbao Jiang","Pengcheng Yin","Bogdan Vasilescu","Graham Neubig"],"abstract":"Open-domain code generation aims to generate code in a general-purpose programming language (such as Python) from natural language (NL) intents. Motivated by the intuition that developers usually retrieve resources on the web when writing code, we explore the effectiveness of incorporating two varieties of external knowledge into NL-to-code generation: automatically mined NL-code pairs from the online programming QA forum StackOverflow and programming language API documentation. Our evaluations show that combining the two sources with data augmentation and retrieval-based data re-sampling improves the current state-of-the-art by up to 2.2% absolute BLEU score on the code generation testbed CoNaLa. The code and resources are available at https://github.com/neulab/external-knowledge-codegen.","url_abs":"https://arxiv.org/abs/2004.09015v1","url_pdf":"https://arxiv.org/pdf/2004.09015v1.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":"incorporating-external-knowledge-through-pre","repo_url":"https://github.com/neulab/external-knowledge-codegen","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"incorporating-external-knowledge-through-pre","repo_url":"https://github.com/zorazrw/multilingual-conala","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"CC-BY-SA-4.0"}}],"tasks":[{"task_slug":"code-generation","task_name":"Code Generation"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/code-generation-on-conala","task":"Code Generation","dataset":"CoNaLa","model":"External Knowledge With API + Reranking","rank_in_archive_order":7,"of":14,"metrics":{"BLEU":"32.26"},"uses_additional_data":true},{"leaderboard":"/sota/code-generation-on-conala","task":"Code Generation","dataset":"CoNaLa","model":"External Knowledge With API","rank_in_archive_order":8,"of":14,"metrics":{"BLEU":"30.69"},"uses_additional_data":true},{"leaderboard":"/sota/code-generation-on-conala-ext","task":"Code Generation","dataset":"CoNaLa-Ext","model":"External Knowledge With API + Reranking","rank_in_archive_order":3,"of":6,"metrics":{"BLEU":"20.54"},"uses_additional_data":false},{"leaderboard":"/sota/code-generation-on-conala-ext","task":"Code Generation","dataset":"CoNaLa-Ext","model":"External Knowledge With API","rank_in_archive_order":4,"of":6,"metrics":{"BLEU":"20.37"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2004.09015","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.09015"}},"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/zorazrw/multilingual-conala","reach":{"status":"ok","spdx":"CC-BY-SA-4.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/neulab/external-knowledge-codegen","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":5,"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":"0bf34988625f82d1","entry":"decode","repo":"neulab/external-knowledge-codegen","repo_kind":"official","path":"evaluation.py","file_url":"https://github.com/neulab/external-knowledge-codegen/blob/HEAD/evaluation.py","link_basis":"first_harvest_node","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":"0bf34988625f82d1"}},{"code_sha256_prefix":"8a2b39c05ccc8ca0","entry":"dot_prod_attention","repo":"neulab/external-knowledge-codegen","repo_kind":"official","path":"model/nn_utils.py","file_url":"https://github.com/neulab/external-knowledge-codegen/blob/HEAD/model/nn_utils.py","link_basis":"first_harvest_node","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":"8a2b39c05ccc8ca0"}},{"code_sha256_prefix":"3115c02671dad0f4","entry":"evaluate","repo":"neulab/external-knowledge-codegen","repo_kind":"official","path":"evaluation.py","file_url":"https://github.com/neulab/external-knowledge-codegen/blob/HEAD/evaluation.py","link_basis":"first_harvest_node","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":"3115c02671dad0f4"}},{"code_sha256_prefix":"4d634e9ce2a4f738","entry":"input_transpose","repo":"neulab/external-knowledge-codegen","repo_kind":"official","path":"model/nn_utils.py","file_url":"https://github.com/neulab/external-knowledge-codegen/blob/HEAD/model/nn_utils.py","link_basis":"harvester_set","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":"4d634e9ce2a4f738"}},{"code_sha256_prefix":"4f498904d7930e35","entry":"length_array_to_mask_tensor","repo":"neulab/external-knowledge-codegen","repo_kind":"official","path":"model/nn_utils.py","file_url":"https://github.com/neulab/external-knowledge-codegen/blob/HEAD/model/nn_utils.py","link_basis":"harvester_set","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":"4f498904d7930e35"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}