{"id":29638247,"url":"https://github.com/celestialtaha/infersent","last_synced_at":"2026-05-16T13:08:30.388Z","repository":{"id":115624874,"uuid":"356143572","full_name":"celestialtaha/InferSent","owner":"celestialtaha","description":"Implementation of Facebook's InferSent in Keras as well as a slightly improved version.","archived":false,"fork":false,"pushed_at":"2021-04-09T05:26:08.000Z","size":2458,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-07-21T19:27:01.383Z","etag":null,"topics":["facebook","infersent","keras","nlp","sentence-representations","supervised-embeddings","supervised-learning"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/celestialtaha.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":"2021-04-09T05:12:40.000Z","updated_at":"2021-12-09T15:26:56.000Z","dependencies_parsed_at":null,"dependency_job_id":"62431259-c6b5-4c29-bdb4-2c23f86ba76c","html_url":"https://github.com/celestialtaha/InferSent","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/celestialtaha/InferSent","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/celestialtaha%2FInferSent","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/celestialtaha%2FInferSent/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/celestialtaha%2FInferSent/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/celestialtaha%2FInferSent/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/celestialtaha","download_url":"https://codeload.github.com/celestialtaha/InferSent/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/celestialtaha%2FInferSent/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33104009,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-16T04:41:52.686Z","status":"ssl_error","status_checked_at":"2026-05-16T04:41:52.009Z","response_time":115,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["facebook","infersent","keras","nlp","sentence-representations","supervised-embeddings","supervised-learning"],"created_at":"2025-07-21T19:07:13.710Z","updated_at":"2026-05-16T13:08:30.382Z","avatar_url":"https://github.com/celestialtaha.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# InferSent\n\nFacebook's InferSent Implemetation and Improvement using Keras framework\n\nThis is a Supervised algorithm of learning sentence representations, which has a hugely faster training time and comparable performance compared to unsupervised methods such as Skip-Thoughts and also capability of transferring to other non-sentiment based NLP tasks.\n\n\n![image](https://github.com/tahasamavati/InferSent/blob/main/results.png)\n\n\nBest Performing model is ESIM-FastText\nThere is no significant difference between using Glove or FastText Embeddings\nThe Proposed ESIM-FastText outperforms original model by 2.24%\n---------------------------------------------------------------------------------\nTaha Samavati - Analysis of final results\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcelestialtaha%2Finfersent","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcelestialtaha%2Finfersent","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcelestialtaha%2Finfersent/lists"}