{"id":13848322,"url":"https://github.com/voidful/mctest","last_synced_at":"2025-07-12T12:30:37.415Z","repository":{"id":109432053,"uuid":"229026256","full_name":"voidful/mctest","owner":"voidful","description":"MCTest dataset and models.","archived":false,"fork":true,"pushed_at":"2014-11-16T15:46:21.000Z","size":1384,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2024-08-05T19:35:32.015Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":null,"has_issues":false,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":"mcobzarenco/mctest","license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/voidful.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}},"created_at":"2019-12-19T10:01:02.000Z","updated_at":"2019-12-19T10:01:04.000Z","dependencies_parsed_at":"2023-03-05T01:25:59.508Z","dependency_job_id":null,"html_url":"https://github.com/voidful/mctest","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/voidful%2Fmctest","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/voidful%2Fmctest/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/voidful%2Fmctest/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/voidful%2Fmctest/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/voidful","download_url":"https://codeload.github.com/voidful/mctest/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":225820302,"owners_count":17529138,"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":[],"created_at":"2024-08-04T19:00:46.953Z","updated_at":"2024-11-21T23:31:13.777Z","avatar_url":"https://github.com/voidful.png","language":null,"readme":"MCTest Dataset\n========\n\nBaseline models as well as more complex ones for doing question answering on the MCTest dataset.\n\nDependencies:\n```\nprotobuf\nnumpy\npandas\nnltk\n```\n\nWord embeddings can be used from a model file created by [word2vec](https://github.com/danielfrg/word2vec).\n\n## Running baseline models\n\n\nFirst, clone the repo and compile the protobuf:\n```\ngit clone https://github.com/mcobzarenco/mctest.git \ncd mctest\nprotoc --python_out=. mctest.proto\n```\n\nTo parse the raw data (dev + train combined), remove stopwords and save it as a length delimted protobuf flat file:\n```\ncat data/MCTest/mc160.dev.tsv data/MCTest/mc160.train.tsv | \\\n  ./parse.py --rm-stop data/stopwords.txt -o proto \u003e train160-stop.words\n```\n\nAlso create a file with the ground truth for dev + train:\n```\ncat data/MCTest/mc160.dev.ans data/MCTest/mc160.train.ans \u003e train160.ans \n```\n\nTo run the sliding window with distance baseline:\n```\n./baseline.py --train train160-stop.words --truth train160.ans --distance\n\n[model]\nwindow_size = None\ndistance = True\n\n[results]\nAll accuracy [400]: 0.5600\nSingle accuracy [185]: 0.5946\nMultiple accuracy [215]: 0.5302\n```\n\n#### Word embeddings\nFirst, [word2vec](https://github.com/danielfrg/word2vec) should be installed and a model file with embeddings created.\nSay the model file is `mctest.vec.bin`, the following command will parse the raw data (dev + train combined), replace the words with their corresponding embedding and save that to disk:\n```\ncat data/MCTest/mc160.dev.tsv data/MCTest/mc160.train.tsv | \\\n  ./parse.py --model-file mctest.vec.bin --rm-punct -o proto \u003e train160-punct-mctest.embed\n```\nTo run the sliding window model over the embeddings:\n```\n./baseline-embed.py --train train160-punct-mctest.embed --truth train160.ans \n\n[model]\nwindow_size = None\n\nAll accuracy [400]: 0.5775\nSingle accuracy [185]: 0.6108\nMultiple accuracy [215]: 0.5488\n```\n","funding_links":[],"categories":["Type of Dataset"],"sub_categories":["Multiple choice"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvoidful%2Fmctest","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fvoidful%2Fmctest","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvoidful%2Fmctest/lists"}