{"id":19530852,"url":"https://github.com/alexeyev/abae-pytorch","last_synced_at":"2025-04-26T13:31:08.197Z","repository":{"id":50735951,"uuid":"193004804","full_name":"alexeyev/abae-pytorch","owner":"alexeyev","description":"PyTorch implementation of 'An Unsupervised Neural Attention Model for Aspect Extraction' by He et al. ACL2017'","archived":false,"fork":false,"pushed_at":"2021-12-09T13:31:40.000Z","size":36,"stargazers_count":64,"open_issues_count":1,"forks_count":13,"subscribers_count":3,"default_branch":"master","last_synced_at":"2023-08-04T21:04:40.309Z","etag":null,"topics":["aspect-extraction","autoencoder","nlp","pytorch","pytorch-implementation","topic-modeling","unsupervised-machine-learning"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/alexeyev.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":"2019-06-21T00:40:22.000Z","updated_at":"2023-07-28T02:53:05.000Z","dependencies_parsed_at":"2022-08-25T10:00:11.824Z","dependency_job_id":null,"html_url":"https://github.com/alexeyev/abae-pytorch","commit_stats":null,"previous_names":[],"tags_count":0,"template":null,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alexeyev%2Fabae-pytorch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alexeyev%2Fabae-pytorch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alexeyev%2Fabae-pytorch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alexeyev%2Fabae-pytorch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/alexeyev","download_url":"https://codeload.github.com/alexeyev/abae-pytorch/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":224036293,"owners_count":17245032,"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":["aspect-extraction","autoencoder","nlp","pytorch","pytorch-implementation","topic-modeling","unsupervised-machine-learning"],"created_at":"2024-11-11T01:36:39.336Z","updated_at":"2024-11-11T01:36:40.563Z","avatar_url":"https://github.com/alexeyev.png","language":"Python","readme":"# ABAE-PyTorch\n\nYet another PyTorch implementation of the model described in the paper \n[**An Unsupervised Neural Attention Model for Aspect Extraction**](https://aclweb.org/anthology/papers/P/P17/P17-1036/) \nby He, Ruidan and  Lee, Wee Sun  and  Ng, Hwee Tou  and  Dahlmeier, Daniel, **ACL2017**.\n\n**NOTA BENE**: as of December 2021, `gensim\u003e=4.1.0` and `hydra-core\u003e=1.1.0` are required.\n\n## Example\n\n**For a working example of a whole pipeline please refer to `example_run.sh`**\n\nLet's get some data:\n\n```\nwget http://snap.stanford.edu/data/amazon/productGraph/categoryFiles/reviews_Cell_Phones_and_Accessories_5.json.gz\ngunzip reviews_Cell_Phones_and_Accessories_5.json.gz    \npython3 custom_format_converter.py reviews_Cell_Phones_and_Accessories_5.json\n```\n\nThen we need to train the word vectors:\n    \n```\npython3 word2vec.py reviews_Cell_Phones_and_Accessories_5.json.txt\n```\nAnd run \n\n```\npython main.py model.aspects_number=35 data.path=$DATA_NAME.json.txt model.log_progress_steps=1000\n```\n\nPlease see all passable params in the `configs/` directory. For a working example of a whole pipeline \nplease refer to `example_run.sh` \n\nI acknowledge the implementation is raw, code modification requests and issues are welcome.\n\n## Thanks for contributions\n[@alexdevmotion](https://github.com/alexdevmotion)\n\n## TODOs\n\n* Evaluation: PMI, NPMI, LCP, L1/L2/coord/cosine (Nikolenko SIGIR'16), ...\n* Aspects prediction on text + visualization\n* Saving the model, aspects, etc.\n\n## How to cite\n\nGreatly appreciated, if you use this work.\n\n```latex\n@misc{abaepytorch2019alekseev,\n  title     = {{alexeyev/abae-pytorch: ABAE, PyTorch implementation}},\n  year      = {2019},\n  url       = {https://github.com/alexeyev/abae-pytorch},\n  language  = {english}\n}\n```\n\n## Please also see\n\n* Reference [Keras implementation](https://github.com/ruidan/Unsupervised-Aspect-Extraction)\n* Updated [Keras version](https://github.com/madrugado/Attention-Based-Aspect-Extraction), compliant with Keras 2.x and Python 3.x.\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falexeyev%2Fabae-pytorch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Falexeyev%2Fabae-pytorch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falexeyev%2Fabae-pytorch/lists"}