{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/fine-tune-bert-for-extractive-summarization","title":"Fine-tune BERT for Extractive Summarization","arxiv_id":"1903.10318","date":"2019-03-25","proceeding":"arXiv 2019 3","authors":["Yang Liu"],"abstract":"BERT, a pre-trained Transformer model, has achieved ground-breaking performance on multiple NLP tasks. In this paper, we describe BERTSUM, a simple variant of BERT, for extractive summarization. Our system is the state of the art on the CNN/Dailymail dataset, outperforming the previous best-performed system by 1.65 on ROUGE-L. The codes to reproduce our results are available at https://github.com/nlpyang/BertSum","url_abs":"https://arxiv.org/abs/1903.10318v2","url_pdf":"https://arxiv.org/pdf/1903.10318v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"fine-tune-bert-for-extractive-summarization","repo_url":"https://github.com/nlpyang/BertSum","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"fine-tune-bert-for-extractive-summarization","repo_url":"https://github.com/HHousen/TransformerSum","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"fine-tune-bert-for-extractive-summarization","repo_url":"https://github.com/TidalPaladin/neural-summarizer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"fine-tune-bert-for-extractive-summarization","repo_url":"https://github.com/aikawasho/BertSum","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"fine-tune-bert-for-extractive-summarization","repo_url":"https://github.com/johnnyb1509/2020_VBDI_DL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"fine-tune-bert-for-extractive-summarization","repo_url":"https://github.com/lingyu001/nlp_text_summarization_implementation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"fine-tune-bert-for-extractive-summarization","repo_url":"https://github.com/nakhunchumpolsathien/TR-TPBS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"fine-tune-bert-for-extractive-summarization","repo_url":"https://github.com/nguyenphamvan/BertSum-master","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"fine-tune-bert-for-extractive-summarization","repo_url":"https://github.com/raqoon886/KoBertSum","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"fine-tune-bert-for-extractive-summarization","repo_url":"https://github.com/raqoon886/KorBertSum","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"fine-tune-bert-for-extractive-summarization","repo_url":"https://github.com/thangarani/bertsum","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"fine-tune-bert-for-extractive-summarization","repo_url":"https://github.com/vsubramaniam851/typ_embed","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"extractive-document-summarization-1","task_name":"Extractive Document Summarization"},{"task_slug":"extractive-summarization","task_name":"Extractive Summarization"},{"task_slug":"extractive-document-summarization","task_name":"Extractive Text Summarization"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/document-summarization-on-cnn-daily-mail","task":"Document Summarization","dataset":"CNN / Daily Mail","model":"BERTSUM+Transformer","rank_in_archive_order":12,"of":26,"metrics":{"ROUGE-1":"43.25","ROUGE-2":"20.24","ROUGE-L":"39.63"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1903.10318","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.10318"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lingyu001/nlp_text_summarization_implementation","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/johnnyb1509/2020_VBDI_DL","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nguyenphamvan/BertSum-master","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/vsubramaniam851/typ_embed","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nakhunchumpolsathien/TR-TPBS","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/aikawasho/BertSum","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/thangarani/bertsum","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/raqoon886/KoBertSum","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/raqoon886/KorBertSum","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nlpyang/BertSum","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/HHousen/TransformerSum","reach":{"status":"ok","spdx":"GPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/TidalPaladin/neural-summarizer","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":1,"ran_violates":1,"unverified":3},"by_repo_kind":{"listed":{"samples":5,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"2498cbc3aebe7442","entry":"cal_rouge","repo":"TidalPaladin/neural-summarizer","repo_kind":"listed","path":"src/prepro/data_builder.py","file_url":"https://github.com/TidalPaladin/neural-summarizer/blob/HEAD/src/prepro/data_builder.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2498cbc3aebe7442"}},{"code_sha256_prefix":"f017532fc389cbfe","entry":"str2bool","repo":"TidalPaladin/neural-summarizer","repo_kind":"listed","path":"src/preprocess.py","file_url":"https://github.com/TidalPaladin/neural-summarizer/blob/HEAD/src/preprocess.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f017532fc389cbfe"}},{"code_sha256_prefix":"bedeff473c33061f","entry":"clean","repo":"TidalPaladin/neural-summarizer","repo_kind":"listed","path":"src/others/utils.py","file_url":"https://github.com/TidalPaladin/neural-summarizer/blob/HEAD/src/others/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bedeff473c33061f"}},{"code_sha256_prefix":"7e979303d1cfbf18","entry":"rouge_results_to_str","repo":"TidalPaladin/neural-summarizer","repo_kind":"listed","path":"src/others/utils.py","file_url":"https://github.com/TidalPaladin/neural-summarizer/blob/HEAD/src/others/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7e979303d1cfbf18"}},{"code_sha256_prefix":"f5673beb535c7cce","entry":"str2bool","repo":"TidalPaladin/neural-summarizer","repo_kind":"listed","path":"src/flags.py","file_url":"https://github.com/TidalPaladin/neural-summarizer/blob/HEAD/src/flags.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f5673beb535c7cce"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}