{"id":18401717,"url":"https://github.com/borealisai/code-gen-tae","last_synced_at":"2025-07-09T01:39:38.935Z","repository":{"id":79742590,"uuid":"372545609","full_name":"BorealisAI/code-gen-TAE","owner":"BorealisAI","description":"Code generation from natural language with less prior and more monolingual data","archived":false,"fork":false,"pushed_at":"2021-08-24T14:18:36.000Z","size":42,"stargazers_count":13,"open_issues_count":1,"forks_count":1,"subscribers_count":5,"default_branch":"main","last_synced_at":"2025-04-07T07:36:28.021Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/BorealisAI.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2021-05-31T15:05:23.000Z","updated_at":"2025-03-24T03:07:22.000Z","dependencies_parsed_at":"2023-02-28T22:01:06.936Z","dependency_job_id":null,"html_url":"https://github.com/BorealisAI/code-gen-TAE","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/BorealisAI/code-gen-TAE","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BorealisAI%2Fcode-gen-TAE","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BorealisAI%2Fcode-gen-TAE/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BorealisAI%2Fcode-gen-TAE/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BorealisAI%2Fcode-gen-TAE/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/BorealisAI","download_url":"https://codeload.github.com/BorealisAI/code-gen-TAE/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BorealisAI%2Fcode-gen-TAE/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":264376623,"owners_count":23598573,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-11-06T02:39:44.217Z","updated_at":"2025-07-09T01:39:38.925Z","avatar_url":"https://github.com/BorealisAI.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Code generation from natural language with less prior and more monolingual data (TAE)\n\nPaper published in [ACL 2021](https://aclanthology.org/2021.acl-short.98/)\n\n\ninstall the requirments:\n```\npip install -r requirements.txt\n```\n\nTo train model on Django\n```\npython3 train.py --dataset_name django --save_dir CHECKPOINT_DIR --copy_bt --no_encoder_update --monolingual_ratio 1.0 --early_stopping\n``` \nTo evaluate the provided Django checkpoint:\n```\npython3 train.py --dataset_name django --save_dir pretrained_weights/django --copy_bt --no_encoder_update --monolingual_ratio 1.0 --early_stopping --just_evaluate --seed 2\n``` \nTo train model on CoNaLa\n```\npython3 train.py --dataset_name conala --save_dir CHECKPOINT_DIR --copy_bt --no_encoder_update --monolingual_ratio 0.5 --epochs 80\n``` \nTo evaluate the provided CoNaLa chceckpoint:\n```\npython3 train.py --dataset_name conala --save_dir pretrained_weights/conala --copy_bt --no_encoder_update --monolingual_ratio 0.5 --epochs 80 --just_evaluate --seed 4\n```\n\n### Evaluation Results\nHere are the evaluation numbers for the provided checkpoints:\n\n| Dataset | Results      | Metric             |\n| ------- | ------------ | ------------------ |\n| Django  | 81.77        | Exact Match Acc.   |\n| CoNaLa  | 33.41        | Corpus BLEU        |\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fborealisai%2Fcode-gen-tae","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fborealisai%2Fcode-gen-tae","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fborealisai%2Fcode-gen-tae/lists"}