{"id":28355308,"url":"https://github.com/dsksd/sden-pytorch","last_synced_at":"2025-10-03T23:56:39.646Z","repository":{"id":295902448,"uuid":"130204705","full_name":"DSKSD/SDEN-Pytorch","owner":"DSKSD","description":"Pytorch Implementation of \"Sequential Dialogue Context Modeling for Spoken Language Understanding( https://arxiv.org/abs/1705.03455 )\"","archived":false,"fork":false,"pushed_at":"2018-07-10T09:18:39.000Z","size":44751,"stargazers_count":34,"open_issues_count":1,"forks_count":9,"subscribers_count":4,"default_branch":"master","last_synced_at":"2025-06-20T10:40:01.328Z","etag":null,"topics":["chatbot","multi-domain","multi-turn","nlp","nlu","task-oriented"],"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/DSKSD.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,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2018-04-19T11:20:31.000Z","updated_at":"2023-03-27T04:52:22.000Z","dependencies_parsed_at":"2025-06-02T22:47:09.659Z","dependency_job_id":null,"html_url":"https://github.com/DSKSD/SDEN-Pytorch","commit_stats":null,"previous_names":["dsksd/sden-pytorch"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/DSKSD/SDEN-Pytorch","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DSKSD%2FSDEN-Pytorch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DSKSD%2FSDEN-Pytorch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DSKSD%2FSDEN-Pytorch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DSKSD%2FSDEN-Pytorch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/DSKSD","download_url":"https://codeload.github.com/DSKSD/SDEN-Pytorch/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DSKSD%2FSDEN-Pytorch/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":278245386,"owners_count":25955016,"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","status":"online","status_checked_at":"2025-10-03T02:00:06.070Z","response_time":53,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":["chatbot","multi-domain","multi-turn","nlp","nlu","task-oriented"],"created_at":"2025-05-28T04:09:14.503Z","updated_at":"2025-10-03T23:56:39.635Z","avatar_url":"https://github.com/DSKSD.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# SDEN-Pytorch\n\nPytorch implementation of [Sequential Dialogue Context Modeling for Spoken Language\nUnderstanding](https://arxiv.org/pdf/1705.03455.pdf)\n\n![Model](images/model.png \"SDEN\")\n\n\n## Requirements\n\n```\npytorch==0.4\nnltk==3.5.1\nsklearn_crfsuite\n```\n\n## Run\n\n```\npython3 main.py\n```\n\n## Data\n\nI have modified [Stanford Multi-turn dataset](https://nlp.stanford.edu/blog/a-new-multi-turn-multi-domain-task-oriented-dialogue-dataset/) to fit this model. *So it has some noise especially slot tags.*\nIt consists of three domain, `Weather`, `Schedule`, `Navigate`. I did dialogue recombination for multi-domain dialogue and modified its format to BIO.\n\n### sample\n\n#### Single domain dialogue\n\n```\nUser :  Will it be hot in Inglewood over the next few days?\nBOT  :  It will be warm both Monday and Tuesday in Inglewood.\nUser :  Thank you very much.\nBOT  :  You're welcome. Hope you have a great day.\n```\n\n#### Multi domain dialogue\n\n```\nUser :  is it going to be raining this weekend\nBOT  :  What city are you inquiring about?\nUser :  Alhambra please.\nBOT  :  It will be raining on Saturday and hailing on Sunday in Alhambra.\nUser :  Thanks.\nBOT  :  happy to help\nUser :  I need a gas station\nBOT  :  I have one gas station listed. Want more info?\nUser :  What is the address?\nBOT  :  76 is at 91 El Camino Real.\nUser :  Thank you!\nBOT  :  You're welcome, stay safe.\n```\n\n\n## Devset Result\n\n`Intent Detection : 0.9503091367071216 (Accuracy)`\n\n\n`Slot Extraction`\n\n|                     | precision| recall | f1-score | support |\n|---------------------|----------|--------|----------|---------|\n| B-agenda            |0.256     |0.278   |0.267     |36       | \n| I-agenda            |0.733     |0.407   |0.524     |54       |\n| B-date              |0.826     |0.836   |0.831     |911      |\n| I-date              |0.533     |0.885   |0.665     |549      |\n| B-distance          |0.624     |0.674   |0.648     |487      |\n| I-distance          |0.424     |0.353   |0.386     |167      |\n| B-event             |0.813     |0.793   |0.803     |517      |\n| I-event             |0.637     |0.847   |0.727     |367      |\n| B-location          |0.718     |0.928   |0.809     |572      |\n| I-location          |0.384     |0.950   |0.547     |280      |\n| B-party             |0.298     |0.807   |0.435     |187      |\n| I-party             |0.471     |0.471   |0.471     |17       |\n| B-poi_type          |0.790     |0.738   |0.763     |534      |\n| I-poi_type          |0.528     |0.718   |0.608     |301      |\n| B-room              |1.000     |0.400   |0.571     |35       |\n| I-room              |0.683     |0.848   |0.757     |33       |\n| B-time              |0.496     |0.595   |0.541     |220      |\n| I-time              |0.129     |0.286   |0.178     |14       |\n| B-traffic_info      |0.661     |0.527   |0.587     |237      |\n| I-traffic_info      |0.749     |0.636   |0.688     |272      |\n| B-weather_attribute |0.904     |0.877   |0.890     |546      |\n| I-weather_attribute |0.954     |0.775   |0.855     |80       |\n| avg / total         |0.683     |0.775   |0.712     |6416     |\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdsksd%2Fsden-pytorch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdsksd%2Fsden-pytorch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdsksd%2Fsden-pytorch/lists"}