{"id":22393095,"url":"https://github.com/ha-lins/maml-dst","last_synced_at":"2026-02-27T22:10:44.115Z","repository":{"id":37614211,"uuid":"228289279","full_name":"ha-lins/MAML-DST","owner":"ha-lins","description":"Model-agnostic meta-learning (MAML) for few-shot dialogue state tracking (DST) based on TRADE.","archived":false,"fork":false,"pushed_at":"2022-12-08T05:24:57.000Z","size":742,"stargazers_count":3,"open_issues_count":3,"forks_count":2,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-07-31T12:30:16.015Z","etag":null,"topics":["dialog-state-tracking","maml","meret","meta-learning","trade"],"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/ha-lins.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":"2019-12-16T02:47:50.000Z","updated_at":"2021-01-08T03:57:55.000Z","dependencies_parsed_at":"2023-01-24T12:15:18.975Z","dependency_job_id":null,"html_url":"https://github.com/ha-lins/MAML-DST","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/ha-lins/MAML-DST","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ha-lins%2FMAML-DST","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ha-lins%2FMAML-DST/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ha-lins%2FMAML-DST/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ha-lins%2FMAML-DST/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ha-lins","download_url":"https://codeload.github.com/ha-lins/MAML-DST/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ha-lins%2FMAML-DST/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29917217,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-27T19:37:42.220Z","status":"ssl_error","status_checked_at":"2026-02-27T19:37:41.463Z","response_time":57,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":["dialog-state-tracking","maml","meret","meta-learning","trade"],"created_at":"2024-12-05T04:41:51.437Z","updated_at":"2026-02-27T22:10:44.095Z","avatar_url":"https://github.com/ha-lins.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"## Model-Agnostic Meta-Learning (MAML) for Dialogue State Tracking\n\nThis repo implements the model-agnostic meta-learning (MAML) for dialogue state tracking (DST). It achieves better performance than [TRADE](https://github.com/jasonwu0731/trade-dst) in the few-shot setting. It also implements the multi-task learning (MTL-DST) as the baseline. This code has been written using PyTorch \u003e= 1.0. \n\nThis project has a similar idea to [MERET](https://www.aclweb.org/anthology/2020.acl-main.636.pdf). Our project is preliminarily named recallable meta-learning for DST (RM-DST), which can not only fast adapt to a low-resource new domain, but also employ a recallable mechanism to maintain the\nhigh performance in old tasks. If you are interested in the work, you can contact me for the draft. The overview of RM-DST is as follows: \n\n\u003cp align=\"center\"\u003e\n\u003cimg src=\"plot/Fig1.png\" width=\"50%\" height=\"50%\" /\u003e\n\u003c/p\u003e\n\nDownload the MultiWOZ dataset and the processed dst version.\n```console\n❱❱❱ python3 create_data.py\n```\n\n## Dependency\nCheck the packages needed or simply run the command\n```console\n❱❱❱ pip install -r requirements.txt\n```\nIf you run into an error related to Cython, try to upgrade it first.\n```console\n❱❱❱ pip install --upgrade cython\n```\n\n## Unseen Domain DST\n\n#### MAML-DST\nTraining\n```console\n❱❱❱ python3 myTrain_maml_DND.py -dec=TRADE -bsz=32 -dr=0.2 -lr=0.001 -le=1 -exceptd=${domain}\n```\n\n#### MTL-DST\nTraining\n```console\n❱❱❱ python3 myTrain_MTL.py -dec=TRADE -bsz=32 -dr=0.2 -lr=0.001 -le=1 -exceptd=${domain} -add_name=MTL\n```\n* -exceptd: except domain selection, choose one from {hotel, train, attraction, restaurant, taxi}.\n\n#### Fine-tune\n\nMAML-DST\n```console\n❱❱❱ python3 fine_tune_dnd.py -bsz=8 -dr=0.2 -lr=0.001 -path=${save_path_except_domain} -exceptd=${except_domain}\n```\nMTL-DST\n```console\n❱❱❱ python3 fine_tune.py -bsz=8 -dr=0.2 -lr=0.001 -path=${save_path_except_domain} -exceptd=${except_domain}\n```\n\n## Results\n\u003cp align=\"center\"\u003e\n\u003cimg src=\"plot/results.PNG\" width=\"100%\" height=\"100%\" /\u003e\n\u003c/p\u003e\n\n## Reference\n1. [DAML](https://github.com/qbetterk/DAML): Domain Adaptive Dialog Generation via Meta Learning. [ACL 2019]\n2. [TRADE](https://github.com/jasonwu0731/trade-dst): Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems. [ACL 2019]\n3. Meta-Reinforced Multi-Domain State Generator for Dialogue Systems. [ACL 2020]\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fha-lins%2Fmaml-dst","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fha-lins%2Fmaml-dst","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fha-lins%2Fmaml-dst/lists"}