{"id":17153393,"url":"https://github.com/generall/oneshotnlp","last_synced_at":"2025-07-23T15:39:58.620Z","repository":{"id":147943353,"uuid":"132382543","full_name":"generall/OneShotNLP","owner":"generall","description":"PyTorch text matching models implementation for One-Shot Named Entity Linking","archived":false,"fork":false,"pushed_at":"2018-09-16T21:37:28.000Z","size":5308,"stargazers_count":23,"open_issues_count":0,"forks_count":4,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-07-19T23:30:34.280Z","etag":null,"topics":["neural-network","nlp"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/generall.png","metadata":{"files":{"readme":"readme.md","changelog":null,"contributing":null,"funding":null,"license":null,"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,"zenodo":null}},"created_at":"2018-05-06T23:00:32.000Z","updated_at":"2023-08-24T23:57:00.000Z","dependencies_parsed_at":"2023-05-05T15:30:59.530Z","dependency_job_id":null,"html_url":"https://github.com/generall/OneShotNLP","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/generall/OneShotNLP","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/generall%2FOneShotNLP","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/generall%2FOneShotNLP/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/generall%2FOneShotNLP/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/generall%2FOneShotNLP/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/generall","download_url":"https://codeload.github.com/generall/OneShotNLP/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/generall%2FOneShotNLP/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":266706625,"owners_count":23971904,"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","status":"online","status_checked_at":"2025-07-23T02:00:09.312Z","response_time":66,"last_error":null,"robots_txt_status":null,"robots_txt_updated_at":null,"robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["neural-network","nlp"],"created_at":"2024-10-14T21:46:06.593Z","updated_at":"2025-07-23T15:39:58.608Z","avatar_url":"https://github.com/generall.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# PyTorch implementation of One-Shot Named Entity Linking\n\nDesigned for [OneShot-wikilinks](https://www.kaggle.com/generall/oneshotwikilinks) dataset.\n\nTraining with [fastText](https://fasttext.cc/docs/en/pretrained-vectors.html) embeddings\n\n```bash\ncd src\npython train_arcii.py --cuda=1 --epoch 10 --dropout 0.5\\\n                      --netsize 120 --parallel 10\\\n                      --run fasttext_arc2\\\n                      --train-data ../data/full_data_train.tsv\\\n                      --valid-data ../data/full_data_valid.tsv\\\n                      --save-every 1 --read-size 1000 --batch-size 50\\\n                      --lr 0.0005 --patience 4 --emb-size 300\\\n                      --cycles 1 --preconv 1 --emb-path '../data/wiki.en.bin' |\u0026 tee run.sh.log\n```\n\nValidation accuracy: `0.88`\n\nEval\n\n```bash\npython predict.py --emb-path ../data/wiki.en.bin --model ../data/models/ARC2_best.pth --input \u003cinput_file\u003e\n```\n\n\n## Run on [paperspace](https://paperspace.com)\n\nDownload data to storage\n\n```\npaperspace jobs create --container Test-Container --machineType C2 --command \"cd data; bash -x download_kaggle.sh\"\n```\n\nRun learning\n\n```\npaperspace jobs create --container \"ufoym/deepo:pytorch-py36\" --machineType P4000 --command \"bash -x run.sh\"\n```\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgenerall%2Foneshotnlp","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgenerall%2Foneshotnlp","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgenerall%2Foneshotnlp/lists"}