{"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/leveraging-pre-trained-checkpoints-for","title":"Leveraging Pre-trained Checkpoints for Sequence Generation Tasks","arxiv_id":"1907.12461","date":"2019-07-29","proceeding":"TACL 2020 1","authors":["Sascha Rothe","Shashi Narayan","Aliaksei Severyn"],"abstract":"Unsupervised pre-training of large neural models has recently revolutionized Natural Language Processing. By warm-starting from the publicly released checkpoints, NLP practitioners have pushed the state-of-the-art on multiple benchmarks while saving significant amounts of compute time. So far the focus has been mainly on the Natural Language Understanding tasks. In this paper, we demonstrate the efficacy of pre-trained checkpoints for Sequence Generation. We developed a Transformer-based sequence-to-sequence model that is compatible with publicly available pre-trained BERT, GPT-2 and RoBERTa checkpoints and conducted an extensive empirical study on the utility of initializing our model, both encoder and decoder, with these checkpoints. Our models result in new state-of-the-art results on Machine Translation, Text Summarization, Sentence Splitting, and Sentence Fusion.","url_abs":"https://arxiv.org/abs/1907.12461v2","url_pdf":"https://arxiv.org/pdf/1907.12461v2.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":"leveraging-pre-trained-checkpoints-for","repo_url":"https://github.com/google-research/bigbird","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"leveraging-pre-trained-checkpoints-for","repo_url":"https://github.com/huggingface/transformers","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"leveraging-pre-trained-checkpoints-for","repo_url":"https://github.com/kiyoungkim1/LMkor","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"leveraging-pre-trained-checkpoints-for","repo_url":"https://github.com/m3hrdadfi/news-headline-generation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"leveraging-pre-trained-checkpoints-for","repo_url":"https://github.com/m3hrdadfi/wiki-summary","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"leveraging-pre-trained-checkpoints-for","repo_url":"https://github.com/MindSpore-scientific/code-11/tree/main/Least_Generative","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"leveraging-pre-trained-checkpoints-for","repo_url":"https://huggingface.co/google/roberta2roberta_L-24_wikisplit","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"natural-language-understanding","task_name":"Natural Language Understanding"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentence-fusion","task_name":"Sentence Fusion"},{"task_slug":"split-and-rephrase","task_name":"Split and Rephrase"},{"task_slug":"text-summarization","task_name":"Text Summarization"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"unsupervised-pre-training","task_name":"Unsupervised Pre-training"}],"methods":[{"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":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"discriminative-fine-tuning","method_name":"Discriminative Fine-Tuning"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-2","method_name":"GPT-2"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"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":"residual-connection","method_name":"Residual Connection"},{"method_slug":"roberta","method_name":"RoBERTa"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1907.12461","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.12461"}},"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/huggingface/transformers","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/m3hrdadfi/news-headline-generation","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/google-research/bigbird","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://huggingface.co/google/roberta2roberta_L-24_wikisplit","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindSpore-scientific/code-11/tree/main/Least_Generative","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kiyoungkim1/LMkor","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/m3hrdadfi/wiki-summary","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":6},"by_repo_kind":{"listed":{"samples":6,"ran":0,"repositories":2}},"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":"11e5b4508003b7b6","entry":"clean_html","repo":"m3hrdadfi/news-headline-generation","repo_kind":"listed","path":"app/utils/preprocessing.py","file_url":"https://github.com/m3hrdadfi/news-headline-generation/blob/HEAD/app/utils/preprocessing.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":"11e5b4508003b7b6"}},{"code_sha256_prefix":"bd26b4ede364bd2b","entry":"install_library_in_colab","repo":"kiyoungkim1/LMkor","repo_kind":"listed","path":"src/utils/utils_colab.py","file_url":"https://github.com/kiyoungkim1/LMkor/blob/HEAD/src/utils/utils_colab.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":"bd26b4ede364bd2b"}},{"code_sha256_prefix":"d97765a6c8a014f3","entry":"load_json","repo":"m3hrdadfi/news-headline-generation","repo_kind":"listed","path":"app/utils/utils.py","file_url":"https://github.com/m3hrdadfi/news-headline-generation/blob/HEAD/app/utils/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":"d97765a6c8a014f3"}},{"code_sha256_prefix":"b983514302b138d2","entry":"load_local_image","repo":"m3hrdadfi/news-headline-generation","repo_kind":"listed","path":"app/utils/utils.py","file_url":"https://github.com/m3hrdadfi/news-headline-generation/blob/HEAD/app/utils/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":"b983514302b138d2"}},{"code_sha256_prefix":"9545b4999c218edb","entry":"load_local_text","repo":"m3hrdadfi/news-headline-generation","repo_kind":"listed","path":"app/utils/utils.py","file_url":"https://github.com/m3hrdadfi/news-headline-generation/blob/HEAD/app/utils/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":"9545b4999c218edb"}},{"code_sha256_prefix":"edafe76274ef30f1","entry":"upper_repl","repo":"m3hrdadfi/news-headline-generation","repo_kind":"listed","path":"app/utils/preprocessing.py","file_url":"https://github.com/m3hrdadfi/news-headline-generation/blob/HEAD/app/utils/preprocessing.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":"edafe76274ef30f1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}