{"id":21714109,"url":"https://github.com/gibbsbravo/paraphrasee","last_synced_at":"2025-07-26T14:38:18.303Z","repository":{"id":55989974,"uuid":"271318080","full_name":"gibbsbravo/ParaPhrasee","owner":"gibbsbravo","description":"Paraphrase Generation Using Deep Reinforcement Learning - MSc Thesis","archived":false,"fork":false,"pushed_at":"2020-06-10T17:03:58.000Z","size":1971,"stargazers_count":18,"open_issues_count":0,"forks_count":5,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-07-14T23:41:05.017Z","etag":null,"topics":["deep-learning","deep-reinforcement-learning","natural-language-generation","natural-language-processing","paraphrase-detection","paraphrase-generation","paraphrase-identification","reinforcement-learning","reinforcement-learning-agent","reinforcement-learning-algorithms","reinforcement-learning-environments"],"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/gibbsbravo.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}},"created_at":"2020-06-10T15:44:04.000Z","updated_at":"2025-01-12T04:20:18.000Z","dependencies_parsed_at":"2022-08-15T11:00:17.578Z","dependency_job_id":null,"html_url":"https://github.com/gibbsbravo/ParaPhrasee","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/gibbsbravo/ParaPhrasee","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gibbsbravo%2FParaPhrasee","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gibbsbravo%2FParaPhrasee/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gibbsbravo%2FParaPhrasee/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gibbsbravo%2FParaPhrasee/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/gibbsbravo","download_url":"https://codeload.github.com/gibbsbravo/ParaPhrasee/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gibbsbravo%2FParaPhrasee/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":267179489,"owners_count":24048353,"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":"2025-07-26T02:00:08.937Z","response_time":62,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","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":["deep-learning","deep-reinforcement-learning","natural-language-generation","natural-language-processing","paraphrase-detection","paraphrase-generation","paraphrase-identification","reinforcement-learning","reinforcement-learning-agent","reinforcement-learning-algorithms","reinforcement-learning-environments"],"created_at":"2024-11-26T00:31:44.847Z","updated_at":"2025-07-26T14:38:18.256Z","avatar_url":"https://github.com/gibbsbravo.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# ParaPhrasee - Paraphrase Generation Using Deep Reinforcement Learning\n\nThe thesis and repo associated with the article Paraphrase Generation Using Deep Reinforcement Learning.\n\nThe code is not intended to run end-to-end for new applications and is instead meant to be used as starter code or for taking code snippets. \n\nOn page 29 of the thesis there is a full list of the different modules and a brief description. Please send me an email at andrewgbravo@gmail.com if you would like one of the specific modules not contained in the repo.\n\nThe key modules included are:\n- data: Imports raw data from various sources, preprocesses, creates train/validation/test sets and vocab index. Also contains functions for saving and loading\n- encoder_models: Defines classes for each encoder: GloVe, BERT, InferSent, Vanilla and GPT along with related code for retrieving embeddings\n- MCTS: Monte Carlo Tree Search implementation for both FrozenLake and ParaPhrasee environments\n- model_evaluation: Contains wrappers for different evaluation functions to be used primarily as reward functions for RL model\n- paraphrasee_env: Defines environment dynamics for paraphrase generation task as RL problem\n- RL_model: Defines and trains RL models for ParaPhrasee environment\n- supervised_model: Defines, trains, and evaluates the defined supervised model with MLE and beam search. Includes modifications for teacher-forcing and attention\n- toy_RL_pipeline: Defines and trains RL models for either CartPole or FrozenLake environments\n- train_ESIM: Defines and trains an ESIM model for use as the discriminator / adversary\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgibbsbravo%2Fparaphrasee","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgibbsbravo%2Fparaphrasee","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgibbsbravo%2Fparaphrasee/lists"}