{"id":17277562,"url":"https://github.com/tata1661/shine-emnlp21","last_synced_at":"2025-04-14T08:40:55.758Z","repository":{"id":41399442,"uuid":"405068975","full_name":"tata1661/SHINE-EMNLP21","owner":"tata1661","description":"Codes for SHINE published in EMNLP 2021.","archived":false,"fork":false,"pushed_at":"2022-07-01T04:29:38.000Z","size":48260,"stargazers_count":38,"open_issues_count":5,"forks_count":5,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-03-27T22:12:31.376Z","etag":null,"topics":["graph-neural-networks","graph-structure-learning","hierarchical-graph-neural-network","semi-supervised-learning","short-text-classification","text-classification"],"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/tata1661.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":"2021-09-10T12:13:18.000Z","updated_at":"2025-03-17T11:32:42.000Z","dependencies_parsed_at":"2022-08-25T11:41:20.028Z","dependency_job_id":null,"html_url":"https://github.com/tata1661/SHINE-EMNLP21","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/tata1661%2FSHINE-EMNLP21","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tata1661%2FSHINE-EMNLP21/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tata1661%2FSHINE-EMNLP21/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tata1661%2FSHINE-EMNLP21/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/tata1661","download_url":"https://codeload.github.com/tata1661/SHINE-EMNLP21/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248848567,"owners_count":21171398,"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":["graph-neural-networks","graph-structure-learning","hierarchical-graph-neural-network","semi-supervised-learning","short-text-classification","text-classification"],"created_at":"2024-10-15T09:09:08.088Z","updated_at":"2025-04-14T08:40:55.734Z","avatar_url":"https://github.com/tata1661.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# SHINE-EMNLP21\n\n\u003cp align=\"center\"\u003e\u003cimg src=\"SHINE-thumbnail.png\" alt=\"logo\" width=\"600px\" /\u003e\n\n\nThis repository provides the source codes of [\"Hierarchical Heterogeneous Graph Representation Learning for Short Text Classification\"](https://aclanthology.org/2021.emnlp-main.247/) published in *EMNLP 2021* as a long paper. \n\nPlease cite our paper if you find it helpful. Thanks. \n```\n@inproceedings{wang-etal-2021-hierarchical,\n    title = \"Hierarchical Heterogeneous Graph Representation Learning for Short Text Classification\",\n    author = \"Wang, Yaqing  and\n      Wang, Song  and\n      Yao, Quanming  and\n      Dou, Dejing\",\n    booktitle = \"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing\",\n    month = nov,\n    year = \"2021\",\n    address = \"Online and Punta Cana, Dominican Republic\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2021.emnlp-main.247\",\n    doi = \"10.18653/v1/2021.emnlp-main.247\",\n    pages = \"3091--3101\",\n    abstract = \"Short text classification is a fundamental task in natural language processing. It is hard due to the lack of context information and labeled data in practice. In this paper, we propose a new method called SHINE, which is based on graph neural network (GNN), for short text classification. First, we model the short text dataset as a hierarchical heterogeneous graph consisting of word-level component graphs which introduce more semantic and syntactic information. Then, we dynamically learn a short document graph that facilitates effective label propagation among similar short texts. Thus, comparing with existing GNN-based methods, SHINE can better exploit interactions between nodes of the same types and capture similarities between short texts. Extensive experiments on various benchmark short text datasets show that SHINE consistently outperforms state-of-the-art methods, especially with fewer labels.\",\n}\n```\n\n## Environment  \nWe provide both the **PyTorch** and **PaddlePaddle** implementations of SHINE in this repository: \n\n### Torch Version:\n- Python 3.7\n- Pytorch 1.2\n\n### Paddle Version:\n- Python 3.7\n- Paddlepaddle 2.2\n\n## Quick Start\nIf you want to run the Torch version:\n```\ncd SHINE-Torch\n```\nOr if you want to run the PaddlePaddle version:\n```\ncd SHINE-Paddle\n```\n\nThen, You can quickly check out how SHINE operates on the Twitter dataset by:\n```\nPython train.py\n```\n\nYou can choose a specific dataset by: \n```\nPython train.py --dataset snippets\n```\nLikewise, you can choose the specific GPU by:\n```\nPython train.py --dataset snippets --gpu 2\n```\n\n## Use Your Own Datasets\n\nIf you want to try SHINE on your own datasets, you need to make your data in the same form of \"snippets_split.json\".\n\nFor the pretrained NELL entity embedding and Glove6B word embedding used in SHINE, you can download them from [here](https://drive.google.com/file/d/1gzIsN6XVqEXPJQR8MXVolbmKqlPgU_YA/view?usp=sharing). \nAfterwards, you can preprocess the data by:\n```\nPython preprocess.py\n```\n\n\n\n\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftata1661%2Fshine-emnlp21","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftata1661%2Fshine-emnlp21","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftata1661%2Fshine-emnlp21/lists"}