{"id":13535223,"url":"https://github.com/santhoshkolloju/Abstractive-Summarization-With-Transfer-Learning","last_synced_at":"2025-04-02T00:32:57.836Z","repository":{"id":50669992,"uuid":"168450999","full_name":"santhoshkolloju/Abstractive-Summarization-With-Transfer-Learning","owner":"santhoshkolloju","description":"Abstractive summarisation using Bert as encoder and Transformer Decoder","archived":false,"fork":false,"pushed_at":"2023-05-30T05:41:22.000Z","size":807,"stargazers_count":404,"open_issues_count":30,"forks_count":100,"subscribers_count":21,"default_branch":"master","last_synced_at":"2024-08-02T08:10:01.794Z","etag":null,"topics":["abstractive-summarization","abstractive-text-summarization","bert","bert-model","nlg","nlp","summarization","transfer-learning","transformer"],"latest_commit_sha":null,"homepage":null,"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/santhoshkolloju.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}},"created_at":"2019-01-31T02:42:25.000Z","updated_at":"2024-07-06T04:02:06.000Z","dependencies_parsed_at":"2024-01-14T02:37:13.160Z","dependency_job_id":"6f59ecfc-8156-4ebe-b660-c0191770b9ce","html_url":"https://github.com/santhoshkolloju/Abstractive-Summarization-With-Transfer-Learning","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/santhoshkolloju%2FAbstractive-Summarization-With-Transfer-Learning","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/santhoshkolloju%2FAbstractive-Summarization-With-Transfer-Learning/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/santhoshkolloju%2FAbstractive-Summarization-With-Transfer-Learning/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/santhoshkolloju%2FAbstractive-Summarization-With-Transfer-Learning/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/santhoshkolloju","download_url":"https://codeload.github.com/santhoshkolloju/Abstractive-Summarization-With-Transfer-Learning/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":222788514,"owners_count":17037777,"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":["abstractive-summarization","abstractive-text-summarization","bert","bert-model","nlg","nlp","summarization","transfer-learning","transformer"],"created_at":"2024-08-01T08:00:51.497Z","updated_at":"2024-11-02T23:31:06.897Z","avatar_url":"https://github.com/santhoshkolloju.png","language":"Python","funding_links":[],"categories":["BERT Text Summarization Task:"],"sub_categories":[],"readme":"\u003ch3\u003eAbstractive summarization using bert as encoder and transformer decoder\u003c/h3\u003e\n\nI have used a text generation library called Texar , Its a beautiful library with a lot of abstractions, i would say it to be \nscikit learn for text generation problems.\n\nThe main idea behind this architecture is to use the transfer learning from pretrained BERT a masked language model ,\nI have replaced the Encoder part with BERT Encoder and the deocder is trained from the scratch.\n\nOne of the advantages of using Transfomer Networks is training is much faster than LSTM based models as we elimanate sequential behaviour in Transformer models.\n\nTransformer based models generate more gramatically correct  and coherent sentences.\n\n\n\u003ch3\u003eTo run the model\u003c/h3\u003e\n\u003cpre\u003e\nwget https://storage.googleapis.com/bert_models/2018_10_18/uncased_L-12_H-768_A-12.zip \nunzip uncased_L-12_H-768_A-12.zip\n\nPlace the story and summary files under data folder with the following names.\n-train_story.txt\n-train_summ.txt\n-eval_story.txt\n-eval_summ.txt\neach story and summary must be in a single line (see sample text given.)\n\n\nStep1:\nRun Preprocessing\n\u003cb\u003epython preprocess.py\u003c/b\u003e\n\nThis creates two tfrecord files under the data folder.\n\nStep 2:\n\u003cb\u003epython main.py\u003c/b\u003e\n\nConfigurations for the model can be changes from config.py file\n\nStep 3:\nInference \nRun the command \u003cb\u003epython inference.py\u003c/b\u003e\nThis code runs a flask server \nUse postman to send the POST request @http://your_ip_address:1118/results\nwith two form parameters story,summary\n\n\n\n\u003c/pre\u003e\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsanthoshkolloju%2FAbstractive-Summarization-With-Transfer-Learning","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsanthoshkolloju%2FAbstractive-Summarization-With-Transfer-Learning","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsanthoshkolloju%2FAbstractive-Summarization-With-Transfer-Learning/lists"}