{"id":13935782,"url":"https://github.com/hugochan/GraphFlow","last_synced_at":"2025-07-19T21:30:35.653Z","repository":{"id":40976267,"uuid":"202570699","full_name":"hugochan/GraphFlow","owner":"hugochan","description":"Code \u0026 data accompanying the IJCAI 2020 paper \"GraphFlow: Exploiting Conversation Flow with Graph Neural Networks for Conversational Machine Comprehension\"","archived":false,"fork":false,"pushed_at":"2022-06-21T23:24:10.000Z","size":57,"stargazers_count":36,"open_issues_count":3,"forks_count":12,"subscribers_count":2,"default_branch":"master","last_synced_at":"2024-11-27T03:34:36.085Z","etag":null,"topics":["conversational-ai","deep-learning","graph-neural-networks","machine-comprehension","pytorch"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/hugochan.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}},"created_at":"2019-08-15T15:55:58.000Z","updated_at":"2024-11-06T14:02:56.000Z","dependencies_parsed_at":"2022-08-18T21:10:31.837Z","dependency_job_id":null,"html_url":"https://github.com/hugochan/GraphFlow","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/hugochan/GraphFlow","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hugochan%2FGraphFlow","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hugochan%2FGraphFlow/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hugochan%2FGraphFlow/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hugochan%2FGraphFlow/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/hugochan","download_url":"https://codeload.github.com/hugochan/GraphFlow/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hugochan%2FGraphFlow/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":266019657,"owners_count":23864916,"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":["conversational-ai","deep-learning","graph-neural-networks","machine-comprehension","pytorch"],"created_at":"2024-08-07T23:02:05.610Z","updated_at":"2025-07-19T21:30:35.645Z","avatar_url":"https://github.com/hugochan.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# GraphFlow\n\n\nCode \u0026 data accompanying the IJCAI 2020 paper [\"GRAPHFLOW: Exploiting Conversation Flow with Graph Neural Networks for Conversational Machine Comprehension\"](https://www.ijcai.org/Proceedings/2020/171)\n\n\n## Get started\n\n\n### Prerequisites\nThis code is written in python 3. You will need to install a few python packages in order to run the code.\nWe recommend you to use `virtualenv` to manage your python packages and environments.\nPlease take the following steps to create a python virtual environment.\n\n* If you have not installed `virtualenv`, install it with ```pip install virtualenv```.\n* Create a virtual environment with ```virtualenv venv```.\n* Activate the virtual environment with `source venv/bin/activate`.\n* Install the package requirements with `pip install -r requirements.txt`.\n\n\n\n### Run the model\n\n* Download the preprocessed data from [here](https://1drv.ms/u/s!AjiSpuwVTt09gTtAGzIRsp6Py3q-?e=Yxqa7w) and put the data folder under the root directory. (Note: if you cannot access the above data, please download from [here](http://academic.hugochan.net/download/graphflow-data.zip).)\n\n* Run the model\n\n\t```\n\tpython main.py -config config/graphflow_dynamic_graph_coqa.yml\n\t```\n\n\n### Prepare your own data\n\n* Download the raw data\n\t\n\t```\n\tsh download.sh\n\t```\n\n* Run the stanford-core-nlp script\n\n\tcheck out https://stanfordnlp.github.io/CoreNLP/corenlp-server.html\n\n* Run the preprocessing script\n\t\n\t```\n\tpython coqa_scripts/preprocess.py -d path_to_input_data -o path_to_output_data\n\t```\n\n* Annotate the data if you want to have the input passage represented as graph-structured data\n\t\n\t```\n\tpython annotate_graphs.py -i path_to_input_data -o path_to_output_data\n\t```\n\n\n## Reference\n\nIf you found this code useful, please consider citing the following paper:\n\nYu Chen, Lingfei Wu, Mohammed J. Zaki. **\"Graphflow: Exploiting Conversation Flow with Graph Neural Networks for Conversational Machine Comprehension.\"** In *Proceedings of the 29th International Joint Conference on Artificial Intelligence (IJCAI 2020)*, Yokohama, Japan, Jul 11-17, 2020.\n\n\n    @article{chen2019graphflow,\n      title={Graphflow: Exploiting conversation flow with graph neural networks for conversational machine comprehension},\n      author={Chen, Yu and Wu, Lingfei and Zaki, Mohammed J},\n      journal={arXiv preprint arXiv:1908.00059},\n      year={2019}\n    }\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhugochan%2FGraphFlow","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhugochan%2FGraphFlow","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhugochan%2FGraphFlow/lists"}