{"id":24064345,"url":"https://github.com/nusnlp/s2t2","last_synced_at":"2025-06-17T19:37:16.765Z","repository":{"id":79268146,"uuid":"434062824","full_name":"nusnlp/S2T2","owner":"nusnlp","description":"A Semi-supervised Learning Approach with Two Teachers to Improve Breakdown Identification in Dialogues","archived":false,"fork":false,"pushed_at":"2023-08-18T02:04:35.000Z","size":56,"stargazers_count":10,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-04-23T18:52:47.862Z","etag":null,"topics":["data-augmentation","language-model","question-answering","self-training"],"latest_commit_sha":null,"homepage":"https://arxiv.org/abs/2202.10948","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/nusnlp.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":"2021-12-02T03:00:42.000Z","updated_at":"2024-10-26T07:15:21.000Z","dependencies_parsed_at":"2025-01-09T10:24:51.415Z","dependency_job_id":"52e89df3-1144-4a1d-838a-256ab81514d9","html_url":"https://github.com/nusnlp/S2T2","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/nusnlp/S2T2","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nusnlp%2FS2T2","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nusnlp%2FS2T2/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nusnlp%2FS2T2/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nusnlp%2FS2T2/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/nusnlp","download_url":"https://codeload.github.com/nusnlp/S2T2/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nusnlp%2FS2T2/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":260427400,"owners_count":23007503,"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":["data-augmentation","language-model","question-answering","self-training"],"created_at":"2025-01-09T10:24:46.717Z","updated_at":"2025-06-17T19:37:11.749Z","avatar_url":"https://github.com/nusnlp.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"## A Semi-supervised Learning Approach with Two Teachers to Improve Breakdown Identification in Dialogues\nThis repository contains codes of the paper \"A Semi-supervised Learning Approach with Two Teachers to Improve Breakdown Identification in Dialogues\" published in AAAI 2022.\n\n[![paperlink](https://img.shields.io/badge/paper-AAAI-blue)](https://ojs.aaai.org/index.php/AAAI/article/view/21349)\n[![paperlink](https://img.shields.io/badge/paper-arXiv-b31b1b)](https://arxiv.org/abs/2202.10948)\n\n### Requirements ###\nCheck dependencies in `requirements.txt`, install required packages (with python 3.6.8):\n```\npip install -r requirements.txt\n```\n\n### Data ###\n\nRefer to `README` in each `[dataset]` sub-directory for instructions of data retrieval and preprocessing.\n\n### Training ###\n\nFollow the commands of training in `[dataset]/run.sh`.\n\nTrained models can be specified and downloaded by running `bash get_trained_models.sh`.\n\n### Evaluation ###\n\nRefer to `README` in each `[dataset]` sub-directory for evaluation steps.\n\n### Publication ###\nIf you use the source code or models from this work, please cite our paper:\n```\n@inproceedings{lin2022semi,\n  author    = \"Lin, Qian and Ng, Hwee Tou\",\n  title     = \"A Semi-supervised Learning Approach with Two Teachers to Improve Breakdown Identification in Dialogues\",\n  booktitle = \"Proceedings of the AAAI Conference on Artificial Intelligence\",\n  year      = \"2022\",\n  pages     = \"11011--11019\",\n}\n```\n### License ###\n\nThe source code and models in this repository are licensed under GNU GPL 3.0 (see [LICENSE](LICENSE)) for non-commercial use. For commercial use of this code, separate commercial licensing is also available. Please contact Prof. Hwee Tou Ng ([nght@comp.nus.edu.sg](mailto:nght@comp.nus.edu.sg)).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnusnlp%2Fs2t2","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fnusnlp%2Fs2t2","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnusnlp%2Fs2t2/lists"}