{"id":21291584,"url":"https://github.com/smartdataanalytics/ak-de-bigru","last_synced_at":"2025-07-16T01:20:09.377Z","repository":{"id":33021594,"uuid":"145605476","full_name":"SmartDataAnalytics/AK-DE-biGRU","owner":"SmartDataAnalytics","description":"Improving Response Selection in Multi-turn Dialogue Systems by Incorporating Domain Knowledge","archived":false,"fork":false,"pushed_at":"2023-03-10T10:31:01.000Z","size":43,"stargazers_count":58,"open_issues_count":10,"forks_count":13,"subscribers_count":17,"default_branch":"master","last_synced_at":"2024-04-16T07:41:32.153Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","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/SmartDataAnalytics.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":"2018-08-21T18:45:51.000Z","updated_at":"2024-01-27T11:59:27.000Z","dependencies_parsed_at":"2023-01-14T23:05:11.839Z","dependency_job_id":null,"html_url":"https://github.com/SmartDataAnalytics/AK-DE-biGRU","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/SmartDataAnalytics%2FAK-DE-biGRU","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SmartDataAnalytics%2FAK-DE-biGRU/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SmartDataAnalytics%2FAK-DE-biGRU/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SmartDataAnalytics%2FAK-DE-biGRU/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/SmartDataAnalytics","download_url":"https://codeload.github.com/SmartDataAnalytics/AK-DE-biGRU/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":225738027,"owners_count":17516477,"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":"2024-11-21T13:36:21.034Z","updated_at":"2024-11-21T13:36:21.757Z","avatar_url":"https://github.com/SmartDataAnalytics.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Attention and external Knowledge augmented Dual Encoder with bi-directional GRU (AK-DE-biGRU)\n\nCode for implementing the paper : \"[Improving Response Selection in Multi-turn Dialogue Systems by Incorporating Domain Knowledge](https://arxiv.org/pdf/1809.03194.pdf)\" \n\n## Getting Started\n\nWe use python version 3.6.4\nInstall the requirements.txt file and install pytorch version: \"0.3.1.post2\"\n\n### Prerequisites\n\nDownload the pre-processed files from Wu et. al, from here: https://www.dropbox.com/s/2fdn26rj6h9bpvl/ubuntu%20data.zip?dl=0and save it in ubuntu_data.\nRun: python ./preprocess.py\nTo create the required preprocessed dataset\nThis will be read from data.py\nUse the train.txt file to train a fasttext model using the fasttext library:https://github.com/facebookresearch/fastText by:\n```\n./fasttext skipgram -input train.txt -dim 200 -output fast_text_200\n```\nSave this file into a numpy array whose index corresponds to the word_id from the previous dictionary and the row contains the fasttext vector for that word.\ncopy the file to ubuntu_data directory.\n\nDownload the ubuntu_description.npy file provided and copy it to ubuntu_data directory\n\n## Running the model\n\nThe AK-DKE-biGRU model should be run as:\n```\npython -u run_models.py --h_dim 300 --mb_size 32 --n_epoch 20 --gpu --lr 0.0001\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsmartdataanalytics%2Fak-de-bigru","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsmartdataanalytics%2Fak-de-bigru","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsmartdataanalytics%2Fak-de-bigru/lists"}