{"id":21978604,"url":"https://github.com/vijaydwivedi75/beyond_word2vec","last_synced_at":"2025-08-22T12:39:41.861Z","repository":{"id":130626695,"uuid":"94893324","full_name":"vijaydwivedi75/Beyond_word2vec","owner":"vijaydwivedi75","description":"Deep learning architectures to embed multi-word units into a vector space maximizing similarity between units of different sizes.","archived":false,"fork":false,"pushed_at":"2019-05-14T07:26:10.000Z","size":3548,"stargazers_count":9,"open_issues_count":0,"forks_count":2,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-04-28T18:16:00.825Z","etag":null,"topics":["keras","siamese-network","tensorflow","word2vec"],"latest_commit_sha":null,"homepage":null,"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/vijaydwivedi75.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}},"created_at":"2017-06-20T13:19:00.000Z","updated_at":"2022-04-12T06:37:17.000Z","dependencies_parsed_at":"2024-03-17T12:49:09.114Z","dependency_job_id":null,"html_url":"https://github.com/vijaydwivedi75/Beyond_word2vec","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/vijaydwivedi75/Beyond_word2vec","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vijaydwivedi75%2FBeyond_word2vec","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vijaydwivedi75%2FBeyond_word2vec/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vijaydwivedi75%2FBeyond_word2vec/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vijaydwivedi75%2FBeyond_word2vec/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/vijaydwivedi75","download_url":"https://codeload.github.com/vijaydwivedi75/Beyond_word2vec/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vijaydwivedi75%2FBeyond_word2vec/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":271641277,"owners_count":24795337,"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":"2025-08-22T02:00:08.480Z","response_time":65,"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":["keras","siamese-network","tensorflow","word2vec"],"created_at":"2024-11-29T16:24:59.505Z","updated_at":"2025-08-22T12:39:41.829Z","avatar_url":"https://github.com/vijaydwivedi75.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\n## IIITH NLP Lab Summer Research Project\n\n## Beyond Word2Vec\n - Vijay Prakash Dwivedi\n - Dr Manish Shrivastava\n\n## Description\nBuilding deep learning architectures to embed multi-word units into a vector space maximizing similarity between units of different sizes.\n\n## Work\nImplemented a Siamese MLP architecture with following best results.\n![Siamese MLP Architecture](https://i.stack.imgur.com/AyWic.png)\n\n```\n* Training on 263000 samples, Testing on 113000 samples\n* Accuracy on training set: 91.06%\n* Accuracy on test set: 74.93%\n```\nAlso, implemented a Siamese LSTM architecture with following best results.\n![Siamese LSTM Architecture](http://i.imgur.com/d6YxKgP.jpg)\n```\n* Training on 263000 samples, Testing on 113000 samples\n* Accuracy on training set: 93.20%\n* Accuracy on test set: 76.65%\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvijaydwivedi75%2Fbeyond_word2vec","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fvijaydwivedi75%2Fbeyond_word2vec","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvijaydwivedi75%2Fbeyond_word2vec/lists"}