{"id":19245941,"url":"https://github.com/moisestg/rare-lm","last_synced_at":"2025-04-21T10:33:28.219Z","repository":{"id":71929399,"uuid":"90125710","full_name":"moisestg/rare-lm","owner":"moisestg","description":"Understanding of broad discourse context for word prediction","archived":false,"fork":false,"pushed_at":"2020-10-31T18:25:34.000Z","size":21659,"stargazers_count":6,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-04-01T12:49:27.833Z","etag":null,"topics":["deep-learning","nlp","python","tensorflow"],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/moisestg.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":"2017-05-03T08:23:45.000Z","updated_at":"2024-04-28T14:49:51.000Z","dependencies_parsed_at":null,"dependency_job_id":"69536f33-06bc-4bf6-8602-7947760d119f","html_url":"https://github.com/moisestg/rare-lm","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/moisestg%2Frare-lm","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/moisestg%2Frare-lm/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/moisestg%2Frare-lm/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/moisestg%2Frare-lm/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/moisestg","download_url":"https://codeload.github.com/moisestg/rare-lm/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":250040452,"owners_count":21365109,"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":["deep-learning","nlp","python","tensorflow"],"created_at":"2024-11-09T17:29:51.983Z","updated_at":"2025-04-21T10:33:28.212Z","avatar_url":"https://github.com/moisestg.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Broad Discourse Context for language modeling\n\n## About the code: \nThis repo features a simple implementation of a [pointer sentinel mixture](https://arxiv.org/abs/1609.07843) language model (PSMM) in Tensorflow v1.4 (`psmm` folder) which may serve you as a starting point for your own projects. It also includes a vanilla RNNLM (`vanilla` folder).\n\n## About the thesis:\nThe work is focused on analyizing the nature of the [LAMBADA dataset](https://arxiv.org/abs/1606.06031) and exploring techniques that may increase the performance on this task. Some key points of our work:\n- LAMBADA focuses on probing the ability of language models to handle long-range dependencies. However, rare words (e.g. named entities) play an important role on the overall performance that is usually overlooked when all results are averaged.\n- Pointer-based models yield state-of-the-art performance on LAMBADA. PSMM produces comparable results while having a high degree of adaptability. \n\nFor more details and results, check the full thesis [here](../master/report/MasterThesis_MTorres.pdf) or [there](https://doi.org/10.3929/ethz-b-000223923).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmoisestg%2Frare-lm","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmoisestg%2Frare-lm","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmoisestg%2Frare-lm/lists"}