{"id":22014692,"url":"https://github.com/sodalabsio/textstellar","last_synced_at":"2025-07-10T01:44:02.050Z","repository":{"id":114252864,"uuid":"571928479","full_name":"sodalabsio/textstellar","owner":"sodalabsio","description":"Mapping research capabilities using contextual text embeddings","archived":false,"fork":false,"pushed_at":"2022-12-13T02:12:59.000Z","size":2176,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-01-28T15:30:56.273Z","etag":null,"topics":["nlproc","semantic-similarity","topic-modeling","visualization"],"latest_commit_sha":null,"homepage":"https://textstellar.com","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/sodalabsio.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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":"2022-11-29T07:29:00.000Z","updated_at":"2022-12-16T09:12:13.000Z","dependencies_parsed_at":null,"dependency_job_id":"842f24c7-3fd6-4e49-b8d6-72b07b2c3b86","html_url":"https://github.com/sodalabsio/textstellar","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sodalabsio%2Ftextstellar","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sodalabsio%2Ftextstellar/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sodalabsio%2Ftextstellar/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sodalabsio%2Ftextstellar/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/sodalabsio","download_url":"https://codeload.github.com/sodalabsio/textstellar/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245078149,"owners_count":20557279,"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":["nlproc","semantic-similarity","topic-modeling","visualization"],"created_at":"2024-11-30T04:17:13.926Z","updated_at":"2025-03-23T08:42:45.188Z","avatar_url":"https://github.com/sodalabsio.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Textstellar 🌌\n\n![preview](/assets/preview.png)\n\nCapability and skill mapping using transformer-based/contextual text embeddings.\n\n## Overview\n\nOn a high level, the `Textstellar` pipeline broadly consists of three modules:\n\n1. Semantic Ranking:\n    - Given a definition for \"X\" (a list of *reference* sentences capturing X), which could be a theme, challenge, or a concept, we find the top-K related items based on their semantic similarity. The reference sentences could be either handcrafted, or GPT-3 prompted\n    - We apply this to finding relevant research outcomes (and researchers) that are most salient for a given excercise\n\n2. Topic Clustering:\n    - Perform unsupervised clustering for topic discovery\n    - Using Topic Coherence to automatically select the optimal cluster size etc.\n3. Visualization:\n    - Plot highest matching outputs and their corresponding authors\n    - Generate a 2D \"night sky\" visualization of topics\n\n## Setup \n1. Clone this repo and get started with `textstellar.ipynb` notebook to use on your own dataset\n2. Preferably run on a GPU (recommended to use Google Colab)\n3. Replace all system path(s) as needed\n\nMost importantly, explore the low-dimensional semantic space—at your leisure.\n\nClick [here](https://textstellar.com) for a live demo.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsodalabsio%2Ftextstellar","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsodalabsio%2Ftextstellar","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsodalabsio%2Ftextstellar/lists"}