{"id":16269274,"url":"https://github.com/thinkwee/abstract_summarization_rnn","last_synced_at":"2025-09-26T11:30:43.600Z","repository":{"id":79907351,"uuid":"118341904","full_name":"thinkwee/Abstract_Summarization_RNN","owner":"thinkwee","description":"RNN Seq2Seq Based Abstract Summarization(ABS) On Tensorflow","archived":false,"fork":false,"pushed_at":"2019-03-16T09:19:44.000Z","size":207823,"stargazers_count":10,"open_issues_count":0,"forks_count":4,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-01-12T21:21:49.221Z","etag":null,"topics":["lstm","nlp","python","rnn","seq2seq","summarization","tensorflow-seq2seq","tensroflow"],"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/thinkwee.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}},"created_at":"2018-01-21T14:25:58.000Z","updated_at":"2024-10-24T07:18:58.000Z","dependencies_parsed_at":"2023-05-04T14:30:57.831Z","dependency_job_id":null,"html_url":"https://github.com/thinkwee/Abstract_Summarization_RNN","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/thinkwee%2FAbstract_Summarization_RNN","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/thinkwee%2FAbstract_Summarization_RNN/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/thinkwee%2FAbstract_Summarization_RNN/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/thinkwee%2FAbstract_Summarization_RNN/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/thinkwee","download_url":"https://codeload.github.com/thinkwee/Abstract_Summarization_RNN/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":234304839,"owners_count":18811265,"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":["lstm","nlp","python","rnn","seq2seq","summarization","tensorflow-seq2seq","tensroflow"],"created_at":"2024-10-10T18:07:53.277Z","updated_at":"2025-09-26T11:30:38.273Z","avatar_url":"https://github.com/thinkwee.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"*Note: this code is no longer actively maintained.*\n\n# introduction\n- attention based summarization on tensorflow using seq2seq model\n- my graduation project code\n- do not provide data for the time\n\n# environment\n- ubuntu 16.04 lts\n- anaconda python 3.6\n- recompiled tensorflow r1.7 gpu version\n- CUDA 9.0\n- cudnn 7.1.2\n- rouge\n\n# run\n- This work use Gigaword dataset which is not for public. You need fetch the data yourself.\n- The SentiWordNet 3.0 dataset can be found here :[SentiWordNet3.0](https://drive.google.com/open?id=0B0ChLbwT19XcOVZFdm5wNXA5ODg)\n- The codes are written in an early version of tensorflow. I do not recommend run this code directly. Just for reference.\n- run ```python main.py -help``` for help.\n- run ```python main.py -w2v``` to train the wordvector from Gigaword dataset using Word2Vec，then run ```python main.py -train``` to train the model and ```python main.py -test```to test the model(just get the output of testset).\n- you need install ROUGE to test the output. All the results are collected in the original PERL version of ROUGE. Using PyRouge make cause the result a little bit higher.\n\n# progress\n- [x] finish word embedding matrix\n- [x] build seq2seq model\n- [x] test lstm and gru core\n- [x] test bidirectional core\n- [x] fix infer problem\n- [x] test multilayer with dropout core\n- [x] fix lazy loading\n- [x] fix pre-processing\n- [x] try training with non-mentor model\n- [x] secondary activation\n- [x] test attention decoder(luong attention)\n- [x] choose last batch in each epoch as the validation set\n- [x] learning rate decay:gradient descent,low init value,decay=0.995\n- [x] cut vocab size to 3000,replace unusual word to unk\n- [x] enlarge rnn hidden units size\n- [x] fix word embedding matrix and try to load model\n- [x] divide infer and train into two graphs\n- [x] use rouge to value model\n- [x] save each test result\n- [ ] ~~fix unk problems~~\n- [x] train sentiment classification svm\n- [x] add sentiment-blended word embeddings\n- [x] test sentiment classify\n- [X] use larger corpus\n- [x] collect ROUGE\n\n# current effect\n- ROUGE files collected in the './ROUGE_ANSWER'\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fthinkwee%2Fabstract_summarization_rnn","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fthinkwee%2Fabstract_summarization_rnn","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fthinkwee%2Fabstract_summarization_rnn/lists"}