{"url":"/sota/amr-parsing-on-ldc2014t12-1","task":{"name":"AMR Parsing","url":"/task/amr-parsing","note":null},"dataset":{"name":"LDC2014T12","url":null},"category":"Natural Language Processing","categories":["Natural Language Processing"],"category_note":null,"description":"Each AMR is a single rooted, directed graph. AMRs include PropBank semantic roles, within-sentence coreference, named entities and types, modality, negation, questions, quantities, and so on. [See](https://amr.isi.edu/index.html).","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["F1 Full","F1 Newswire"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"F1 Full":"higher","F1 Newswire":"higher"}},"counts":{"rows":12,"rows_with_code":5,"rows_with_paper_page":12,"rows_dated":12,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"APT (IBM)","metrics":{"F1 Full":"78.5"},"uses_additional_data":false,"paper_date":"2021-04-29","paper":"/paper/amr-parsing-with-action-pointer-transformer","paper_url":"https://arxiv.org/abs/2104.14674v3","paper_title":"AMR Parsing with Action-Pointer Transformer","code":"https://github.com/ibm/graph_ensemble_learning","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"stack-Transformer + self-learning (IBM)","metrics":{"F1 Full":"78.2"},"uses_additional_data":false,"paper_date":"2020-10-20","paper":"/paper/pushing-the-limits-of-amr-parsing-with-self","paper_url":"https://arxiv.org/abs/2010.10673v1","paper_title":"Pushing the Limits of AMR Parsing with Self-Learning","code":"https://github.com/IBM/transition-amr-parser","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"AMR Parsing via Graph-Sequence Iterative Inference","metrics":{"F1 Full":"75.4"},"uses_additional_data":false,"paper_date":"2020-04-12","paper":"/paper/amr-parsing-via-graph-sequence-iterative","paper_url":"https://arxiv.org/abs/2004.05572v2","paper_title":"AMR Parsing via Graph-Sequence Iterative Inference","code":"https://github.com/bjascob/amrlib","n_code_links":3,"syntology":{"n_ran":19,"n_unverified":12,"n_samples":31,"n_pointer_only_licence":1}},{"rank_in_archive_order":4,"model":"Broad-Coverage Semantic Parsing as Transduction","metrics":{"F1 Full":"71.3"},"uses_additional_data":false,"paper_date":"2019-09-05","paper":"/paper/broad-coverage-semantic-parsing-as","paper_url":"https://arxiv.org/abs/1909.02607v2","paper_title":"Broad-Coverage Semantic Parsing as Transduction","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":5,"model":"Two-stage Sequence-to-Graph Transducer","metrics":{"F1 Full":"70.2"},"uses_additional_data":false,"paper_date":"2019-05-21","paper":"/paper/amr-parsing-as-sequence-to-graph-transduction","paper_url":"https://arxiv.org/abs/1905.08704v2","paper_title":"AMR Parsing as Sequence-to-Graph Transduction","code":"https://github.com/sheng-z/stog","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"Transition-based+improved aligner+ensemble","metrics":{"F1 Full":"68.4","F1 Newswire":"73.3"},"uses_additional_data":false,"paper_date":"2018-10-08","paper":"/paper/an-amr-aligner-tuned-by-transition-based","paper_url":"http://arxiv.org/abs/1810.03541v1","paper_title":"An AMR Aligner Tuned by Transition-based Parser","code":"https://github.com/Oneplus/tamr","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"Improved CAMR","metrics":{"F1 Full":"68.1"},"uses_additional_data":false,"paper_date":"2017-09-01","paper":"/paper/getting-the-most-out-of-amr-parsing","paper_url":"https://aclanthology.org/D17-1129","paper_title":"Getting the Most out of AMR Parsing","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":8,"model":"Incremental joint model","metrics":{"F1 Full":"66","F1 Newswire":"71"},"uses_additional_data":false,"paper_date":"2016-11-01","paper":"/paper/amr-parsing-with-an-incremental-joint-model","paper_url":"https://aclanthology.org/D16-1065","paper_title":"AMR Parsing with an Incremental Joint Model","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":9,"model":"Transition-based transducer","metrics":{"F1 Full":"66","F1 Newswire":"70"},"uses_additional_data":false,"paper_date":"2015-07-01","paper":"/paper/boosting-transition-based-amr-parsing-with","paper_url":"https://aclanthology.org/P15-2141","paper_title":"Boosting Transition-based AMR Parsing with Refined Actions and Auxiliary Analyzers","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":10,"model":"MT-Based","metrics":{"F1 Full":"66"},"uses_additional_data":false,"paper_date":"2015-09-01","paper":"/paper/parsing-english-into-abstract-meaning","paper_url":"https://aclanthology.org/D15-1136","paper_title":"Parsing English into Abstract Meaning Representation Using Syntax-Based Machine Translation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":11,"model":"Transition-based parser-Stack-LSTM","metrics":{"F1 Full":"63","F1 Newswire":"68"},"uses_additional_data":false,"paper_date":"2017-07-24","paper":"/paper/amr-parsing-using-stack-lstms","paper_url":"http://arxiv.org/abs/1707.07755v2","paper_title":"AMR Parsing using Stack-LSTMs","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":12,"model":"Imitation learning","metrics":{"F1 Newswire":"70"},"uses_additional_data":false,"paper_date":"2016-08-01","paper":"/paper/noise-reduction-and-targeted-exploration-in","paper_url":"https://aclanthology.org/P16-1001","paper_title":"Noise reduction and targeted exploration in imitation learning for Abstract Meaning Representation parsing","code":null,"n_code_links":0,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,885 of the 9,623 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9623,"papers_checked":6885,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2737},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":2,"rows_with_any_sample_ran":2,"distinct_papers_with_graph_line":2,"distinct_papers_with_any_sample_ran":2,"samples_over_distinct_papers":{"n_ran":20,"n_unverified":13,"n_samples":33,"n_pointer_only_licence":1,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":20,"n_unverified":13,"n_samples":33,"n_pointer_only_licence":1,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}