{"id":13535266,"url":"https://github.com/bouchardi/BERT_for_GAP-coreference","last_synced_at":"2025-04-02T00:33:13.105Z","repository":{"id":73763441,"uuid":"178930028","full_name":"bouchardi/BERT_for_GAP-coreference","owner":"bouchardi","description":"BERT finetuning for GAP unbiased pronoun resolution","archived":false,"fork":false,"pushed_at":"2019-04-22T07:13:30.000Z","size":125,"stargazers_count":5,"open_issues_count":0,"forks_count":1,"subscribers_count":0,"default_branch":"master","last_synced_at":"2024-08-11T16:09:17.125Z","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":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/bouchardi.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}},"created_at":"2019-04-01T19:09:16.000Z","updated_at":"2024-08-11T16:09:17.126Z","dependencies_parsed_at":"2023-09-21T03:15:28.084Z","dependency_job_id":null,"html_url":"https://github.com/bouchardi/BERT_for_GAP-coreference","commit_stats":null,"previous_names":["bouchardi/bert_for_gap-coreference","isabellebouchard/bert_for_gap-coreference"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bouchardi%2FBERT_for_GAP-coreference","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bouchardi%2FBERT_for_GAP-coreference/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bouchardi%2FBERT_for_GAP-coreference/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bouchardi%2FBERT_for_GAP-coreference/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/bouchardi","download_url":"https://codeload.github.com/bouchardi/BERT_for_GAP-coreference/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":222788514,"owners_count":17037777,"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":"2024-08-01T08:00:52.336Z","updated_at":"2024-11-02T23:31:15.639Z","avatar_url":"https://github.com/bouchardi.png","language":"Python","funding_links":[],"categories":["BERT  Coreference Resolution"],"sub_categories":[],"readme":"# BERT_for_GAP-coreference\n\nThis project was realised in the context of the INF8225 AI course. In this project,\nwe aim to reduce gender bias in pronoun resolution by creating a coreference \nresolver that performs well on a gender-balanced pronoun dataset, the Gendered \nAmbiguous Pronouns (GAP) dataset. We leverage BERT's strong pre-training tasks on \nlarge unsupervised datasets and transfer these contextual representations to the fine-tuning stage. The fine-tuning stage was trained in a SWAG-like manner on the GAP supervised dataset.\n\nWe have submitted our best performing model to the [Gendered Pronoun Resolution](https://www.kaggle.com/c/gendered-pronoun-resolution/) Kaggle competition. \n\n\n## Setting up\n```\ngit clone --recursive git@github.com:isabellebouchard/BERT_for_GAP-coreference.git\n```\nMake sure the submodules are properly initialized. \n\n\n## First steps\n\nTo run the code, first install [Docker](https://docs.docker.com/install/) to be able\nto build and run a docker container with all the proper dependencies installed\n```\ndocker build -t IMAGE_NAME .\nnvidia-docker run --rm -it -v /path/to/your/code/:/project IMAGE_NAME\n```\n\nIf you don't have access to GPU, change `nvidia-docker` for `docker`. It is \nhighly recommended to run the training on (multiple) GPUs.\n\nOnce inside the container you should be able run the training script:\n```\npython run_GAP.py --data_dir gap-coreference \\\n                  --bert_model bert-base-cased \\\n                  --output_dir results \\\n```\nThis will run the training script and save checkpoints of the best model in the \noutput directory.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbouchardi%2FBERT_for_GAP-coreference","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbouchardi%2FBERT_for_GAP-coreference","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbouchardi%2FBERT_for_GAP-coreference/lists"}