{"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/primer-pyramid-based-masked-sentence-pre","title":"PRIMERA: Pyramid-based Masked Sentence Pre-training for Multi-document Summarization","arxiv_id":"2110.08499","date":"2021-10-16","proceeding":"ACL 2022 5","authors":["Wen Xiao","Iz Beltagy","Giuseppe Carenini","Arman Cohan"],"abstract":"We introduce PRIMERA, a pre-trained model for multi-document representation with a focus on summarization that reduces the need for dataset-specific architectures and large amounts of fine-tuning labeled data. PRIMERA uses our newly proposed pre-training objective designed to teach the model to connect and aggregate information across documents. It also uses efficient encoder-decoder transformers to simplify the processing of concatenated input documents. With extensive experiments on 6 multi-document summarization datasets from 3 different domains on zero-shot, few-shot and full-supervised settings, PRIMERA outperforms current state-of-the-art dataset-specific and pre-trained models on most of these settings with large margins. The code and pre-trained models can be found at \\url{https://github.com/allenai/PRIMER}.","url_abs":"https://arxiv.org/abs/2110.08499v2","url_pdf":"https://arxiv.org/pdf/2110.08499v2.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":"primer-pyramid-based-masked-sentence-pre","repo_url":"https://github.com/allenai/primer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"primer-pyramid-based-masked-sentence-pre","repo_url":"https://github.com/allenai/open-mds","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"primer-pyramid-based-masked-sentence-pre","repo_url":"https://github.com/pwc-1/Paper-9/tree/main/longformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"abstractive-text-summarization","task_name":"Abstractive Text Summarization"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"document-summarization","task_name":"Document Summarization"},{"task_slug":"multi-document-summarization","task_name":"Multi-Document Summarization"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"text-summarization","task_name":"Text Summarization"}],"methods":[{"method_slug":"adamw","method_name":"AdamW"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"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":"longformer","method_name":"Longformer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"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":[{"leaderboard":"/sota/multi-document-summarization-on-multi-news","task":"Multi-Document Summarization","dataset":"Multi-News","model":"PRIMER","rank_in_archive_order":1,"of":6,"metrics":{"ROUGE-1":"49.9","ROUGE-2":"21.1","ROUGE-L":"25.9"},"uses_additional_data":false},{"leaderboard":"/sota/multi-document-summarization-on-wcep","task":"Multi-Document Summarization","dataset":"WCEP","model":"PRIMER","rank_in_archive_order":1,"of":1,"metrics":{"ROUGE-1":"46.1","ROUGE-2":"25.2","ROUGE-L":"37.9"},"uses_additional_data":false},{"leaderboard":"/sota/text-summarization-on-arxiv-summarization","task":"Text Summarization","dataset":"arXiv Summarization Dataset","model":"PRIMER","rank_in_archive_order":1,"of":4,"metrics":{"ROUGE-1":"47.6","ROUGE-2":"20.8","ROUGE-L":"42.6"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2110.08499","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.08499"}},"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/pwc-1/Paper-9/tree/main/longformer","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/allenai/open-mds","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/allenai/primer","reach":null}],"summary":{"ran_draft_wrong":2,"ran_fixture":1,"ran_honours":1,"unverified":3},"by_repo_kind":{"official":{"samples":4,"ran":4,"repositories":1},"listed":{"samples":3,"ran":0,"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":"84f33e1d3d0467ca","entry":"get_src_tgt_with_mask","repo":"allenai/primer","repo_kind":"official","path":"utils/pretrain_preprocess.py","file_url":"https://github.com/allenai/primer/blob/HEAD/utils/pretrain_preprocess.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"84f33e1d3d0467ca"}},{"code_sha256_prefix":"5e9a5fc2ab282ff2","entry":"label_smoothed_nll_loss","repo":"allenai/primer","repo_kind":"official","path":"script/primer_main.py","file_url":"https://github.com/allenai/primer/blob/HEAD/script/primer_main.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5e9a5fc2ab282ff2"}},{"code_sha256_prefix":"6585a560bafdc923","entry":"preprocessing_entities","repo":"allenai/primer","repo_kind":"official","path":"utils/pretrain_preprocess.py","file_url":"https://github.com/allenai/primer/blob/HEAD/utils/pretrain_preprocess.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6585a560bafdc923"}},{"code_sha256_prefix":"d91287c5691fce6c","entry":"select_sent_with_entities","repo":"allenai/primer","repo_kind":"official","path":"utils/pretrain_preprocess.py","file_url":"https://github.com/allenai/primer/blob/HEAD/utils/pretrain_preprocess.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d91287c5691fce6c"}},{"code_sha256_prefix":"31e3adacd2841d84","entry":"sanitize_text","repo":"allenai/open-mds","repo_kind":"listed","path":"src/open_mds/common/util.py","file_url":"https://github.com/allenai/open-mds/blob/HEAD/src/open_mds/common/util.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":"31e3adacd2841d84"}},{"code_sha256_prefix":"94d3056000ccbb34","entry":"split_docs","repo":"allenai/open-mds","repo_kind":"listed","path":"src/open_mds/common/util.py","file_url":"https://github.com/allenai/open-mds/blob/HEAD/src/open_mds/common/util.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":"94d3056000ccbb34"}},{"code_sha256_prefix":"bd497b6193ae78a7","entry":"unflatten","repo":"allenai/open-mds","repo_kind":"listed","path":"src/open_mds/common/util.py","file_url":"https://github.com/allenai/open-mds/blob/HEAD/src/open_mds/common/util.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":"bd497b6193ae78a7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}