{"id":16619776,"url":"https://github.com/rid17pawar/semantic-search-model-experiments","last_synced_at":"2026-07-09T21:31:11.838Z","repository":{"id":177988269,"uuid":"661208168","full_name":"rid17pawar/Semantic-Search-Model-Experiments","owner":"rid17pawar","description":"Experiments in the field of Semantic Search using BM-25 Algorithm, Mean of Word Vectors, along with state of the art Transformer based models namely USE and SBERT.","archived":false,"fork":false,"pushed_at":"2023-10-29T10:18:12.000Z","size":305,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-01-17T22:08:49.201Z","etag":null,"topics":["bm25","fasttext","fasttext-embeddings","glove","glove-embeddings","information-retrieval","sbert","semantic-search","universal-sentence-encoder","word2vec","word2vec-embeddinngs"],"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/rid17pawar.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}},"created_at":"2023-07-02T06:03:50.000Z","updated_at":"2023-11-18T01:40:31.000Z","dependencies_parsed_at":null,"dependency_job_id":"d4804765-ebc2-48ae-9828-c213a23d05a1","html_url":"https://github.com/rid17pawar/Semantic-Search-Model-Experiments","commit_stats":null,"previous_names":["rid17pawar/semantic-search-model-experiments"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rid17pawar%2FSemantic-Search-Model-Experiments","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rid17pawar%2FSemantic-Search-Model-Experiments/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rid17pawar%2FSemantic-Search-Model-Experiments/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rid17pawar%2FSemantic-Search-Model-Experiments/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/rid17pawar","download_url":"https://codeload.github.com/rid17pawar/Semantic-Search-Model-Experiments/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":242988057,"owners_count":20217540,"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":["bm25","fasttext","fasttext-embeddings","glove","glove-embeddings","information-retrieval","sbert","semantic-search","universal-sentence-encoder","word2vec","word2vec-embeddinngs"],"created_at":"2024-10-12T02:42:45.704Z","updated_at":"2025-10-17T08:17:33.649Z","avatar_url":"https://github.com/rid17pawar.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Semantic-Search-Model-Experiments\n\n## Dataset Used For Semantic Search/ Information Retrieval: \n[CISI Dataset - Kaggle](https://www.kaggle.com/datasets/dmaso01dsta/cisi-a-dataset-for-information-retrieval)\n\u003c/br\u003e\u003c/br\u003e\n\n## Experiments:\n#### Experiment-1. Using BM-25 Algorithm and Parameter Tuning For Semantic Search\n\n*BM-25 Algorithm variations used:*\n- BM25Okapi\n- BM25L\n- BM25Plus\n\u003c/br\u003e\u003c/br\u003e\n\n#### Result:\n![image](https://github.com/rid17pawar/Semantic-Search-Model-Experiments/assets/47048717/4b061f8d-8626-4f5e-8270-1aaefecb5ad7)\n\u003c/br\u003e\n*BEST MODEL: BM25Plus*\n\u003c/br\u003e\u003c/br\u003e\n\n#### Experiment-2. Using Mean of Word Vectors (MWV) with Pretrained Embeddings For Semantic Search\n\n*BM-25 Algorithm variations used:*\n- word2vec\n- GloVe\n- FastText\n\u003c/br\u003e\u003c/br\u003e\n\n#### Result:\n![image](https://github.com/rid17pawar/Semantic-Search-Model-Experiments/assets/47048717/885b4171-b6d7-4176-8226-c92c4828597a)\n\u003c/br\u003e\n*BEST MODEL: word2vec*\n\u003c/br\u003e\u003c/br\u003e\n\n#### Experiment-3. Using LDA Topic Modelling For Semantic Search\n\n#### Result:\n*Performs worst than BM-25*\n\u003c/br\u003e\u003c/br\u003e\n\n#### Experiment-4. Using Universal Sentence Encoder (USE) For Semantic Search\n\n*USE Model variations used:*\n- Transformer Encoder\n- Deep Averaging Network(DAN) Encoder\n\u003c/br\u003e\u003c/br\u003e\n\n#### Result:\n![image](https://github.com/rid17pawar/Semantic-Search-Model-Experiments/assets/47048717/30f4a784-f121-403c-8dfe-95ad4c638a01)\n\u003c/br\u003e\n*BEST MODEL: USE-Transformer*\n\u003c/br\u003e\u003c/br\u003e\n\n#### Experiment-5. Using Pretrained and Finetuned Sentence Transformers (SBERT) For Semantic Search\n\n#### Result:\n![image](https://github.com/rid17pawar/Semantic-Search-Model-Experiments/assets/47048717/0d96bc97-6620-490d-ac3d-46b41021eb46)\n\u003c/br\u003e\n*BEST MODEL: Finetuned SBERT*\n\u003c/br\u003e\u003c/br\u003e\n\n#### Final Result:\n![image](https://github.com/rid17pawar/Semantic-Search-Model-Experiments/assets/47048717/3d3094a6-0234-45ee-9ef1-b86ad68dc37e)\n\n![image](https://github.com/rid17pawar/Semantic-Search-Model-Experiments/assets/47048717/2d00cdf3-a0d5-4cd7-8945-4df601138813)\n\u003c/br\u003e\n**Overall Best Model: Finetuned SBERT**\n\u003c/br\u003e\u003c/br\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frid17pawar%2Fsemantic-search-model-experiments","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Frid17pawar%2Fsemantic-search-model-experiments","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frid17pawar%2Fsemantic-search-model-experiments/lists"}