{"id":16269272,"url":"https://github.com/thinkwee/co2sum","last_synced_at":"2026-03-18T18:43:25.428Z","repository":{"id":188422217,"uuid":"678698074","full_name":"thinkwee/co2sum","owner":"thinkwee","description":"code for paper \"Co2sum: contrastive learning for factual-consistent abstractive summarization\"","archived":false,"fork":false,"pushed_at":"2023-08-15T06:46:39.000Z","size":26,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-07-31T13:33:52.334Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":null,"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}},"created_at":"2023-08-15T06:45:52.000Z","updated_at":"2023-09-08T09:42:40.000Z","dependencies_parsed_at":"2023-08-15T08:57:16.500Z","dependency_job_id":null,"html_url":"https://github.com/thinkwee/co2sum","commit_stats":null,"previous_names":["thinkwee/co2sum"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/thinkwee/co2sum","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/thinkwee%2Fco2sum","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/thinkwee%2Fco2sum/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/thinkwee%2Fco2sum/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/thinkwee%2Fco2sum/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/thinkwee","download_url":"https://codeload.github.com/thinkwee/co2sum/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/thinkwee%2Fco2sum/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29256709,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-09T04:11:57.159Z","status":"ssl_error","status_checked_at":"2026-02-09T04:11:56.117Z","response_time":56,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":[],"created_at":"2024-10-10T18:07:53.232Z","updated_at":"2026-02-09T04:32:54.421Z","avatar_url":"https://github.com/thinkwee.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"# CO2Sum\n-   Code for the paper [CO2Sum:Contrastive Learning for Factual-Consistent Abstractive Summarization](https://arxiv.org/pdf/2112.01147.pdf)\n-   Include the negative sample constuction method LFN CO2Sum_LFN, and the training code CO2Sum_train\n\n## CO2Sum_LFN\n-   Code for the LFN algorithm introduced in the paper\n-   The process of LFN consists of three steps:\n    -   run get_next.py to get the context of summary\n    -   run ./LFN_LM/run.sh to get the fact fragments based on the article, summary and context\n    -   run LFN_construct.py to construct the negative samples based on the fact fragments\n\n## CO2Sum_train\n-   We develop our method based on the fairseq. Since there is no model architecture modified, you can just extend the criterion, data, tasks by setting --user-dir to CO2Sum_train then start training and inference by using default fairseq-train and fairseq-generate\n-   The loss function of CoEnc and CoDec are described in the ./criterions/label_smoothed_cross_entropy_with_position_triplet_contrastive.py\n-   The data loading process for ground truth summary and negative samples is described in ./data/language_position_triplet_dataset.py","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fthinkwee%2Fco2sum","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fthinkwee%2Fco2sum","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fthinkwee%2Fco2sum/lists"}