{"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/document-level-representation-learning-using","title":"SPECTER: Document-level Representation Learning using Citation-informed Transformers","arxiv_id":"2004.07180","date":"2020-04-15","proceeding":"ACL 2020 6","authors":["Arman Cohan","Sergey Feldman","Iz Beltagy","Doug Downey","Daniel S. Weld"],"abstract":"Representation learning is a critical ingredient for natural language processing systems. Recent Transformer language models like BERT learn powerful textual representations, but these models are targeted towards token- and sentence-level training objectives and do not leverage information on inter-document relatedness, which limits their document-level representation power. For applications on scientific documents, such as classification and recommendation, the embeddings power strong performance on end tasks. We propose SPECTER, a new method to generate document-level embedding of scientific documents based on pretraining a Transformer language model on a powerful signal of document-level relatedness: the citation graph. Unlike existing pretrained language models, SPECTER can be easily applied to downstream applications without task-specific fine-tuning. Additionally, to encourage further research on document-level models, we introduce SciDocs, a new evaluation benchmark consisting of seven document-level tasks ranging from citation prediction, to document classification and recommendation. We show that SPECTER outperforms a variety of competitive baselines on the benchmark.","url_abs":"https://arxiv.org/abs/2004.07180v4","url_pdf":"https://arxiv.org/pdf/2004.07180v4.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":"document-level-representation-learning-using","repo_url":"https://github.com/allenai/scidocs","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"document-level-representation-learning-using","repo_url":"https://github.com/allenai/specter","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"document-level-representation-learning-using","repo_url":"https://github.com/allenai/aspire","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"document-level-representation-learning-using","repo_url":"https://github.com/hle027/IR-Competition","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"document-level-representation-learning-using","repo_url":"https://github.com/sntcristian/and-kge","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"citation-prediction","task_name":"Citation Prediction"},{"task_slug":"document-classification","task_name":"Document Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"sentence","task_name":"Sentence"}],"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":[{"slug":"scidocs","name":"SciDocs","full_name":"SciDocs"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/document-classification-on-scidocs-mag","task":"Document Classification","dataset":"SciDocs (MAG)","model":"SPECTER","rank_in_archive_order":1,"of":2,"metrics":{"F1 (micro)":"82.0"},"uses_additional_data":false},{"leaderboard":"/sota/document-classification-on-scidocs-mesh","task":"Document Classification","dataset":"SciDocs (MeSH)","model":"SPECTER","rank_in_archive_order":2,"of":2,"metrics":{"F1 (micro)":"86.4"},"uses_additional_data":false},{"leaderboard":"/sota/representation-learning-on-scidocs","task":"Representation Learning","dataset":"SciDocs","model":"SPECTER","rank_in_archive_order":2,"of":7,"metrics":{"Avg.":"80.0"},"uses_additional_data":false},{"leaderboard":"/sota/representation-learning-on-scidocs","task":"Representation Learning","dataset":"SciDocs","model":"Citeomatic","rank_in_archive_order":3,"of":7,"metrics":{"Avg.":"76.0"},"uses_additional_data":false},{"leaderboard":"/sota/representation-learning-on-scidocs","task":"Representation Learning","dataset":"SciDocs","model":"SciBERT","rank_in_archive_order":5,"of":7,"metrics":{"Avg.":"59.6"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2004.07180","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.07180"}},"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":"deterministic:regex_extraction","url":"https://github.com/allenai/specter","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/allenai/aspire","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sntcristian/and-kge","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hle027/IR-Competition","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/allenai/scidocs","reach":null}],"summary":{"ran":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"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":1,"samples":[{"code_sha256_prefix":"58111a8f1b8f5e9e","entry":"SimClickTripletSampler","repo":"allenai/scidocs","repo_kind":"official","path":"scidocs/recommender/simclick_triplet_sampler.py","file_url":"https://github.com/allenai/scidocs/blob/HEAD/scidocs/recommender/simclick_triplet_sampler.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"58111a8f1b8f5e9e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}