{"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/graph-pre-training-for-amr-parsing-and-1","title":"Graph Pre-training for AMR Parsing and Generation","arxiv_id":"2203.07836","date":"2022-03-15","proceeding":"ACL 2022 5","authors":["Xuefeng Bai","Yulong Chen","Yue Zhang"],"abstract":"Abstract meaning representation (AMR) highlights the core semantic information of text in a graph structure. Recently, pre-trained language models (PLMs) have advanced tasks of AMR parsing and AMR-to-text generation, respectively. However, PLMs are typically pre-trained on textual data, thus are sub-optimal for modeling structural knowledge. To this end, we investigate graph self-supervised training to improve the structure awareness of PLMs over AMR graphs. In particular, we introduce two graph auto-encoding strategies for graph-to-graph pre-training and four tasks to integrate text and graph information during pre-training. We further design a unified framework to bridge the gap between pre-training and fine-tuning tasks. Experiments on both AMR parsing and AMR-to-text generation show the superiority of our model. To our knowledge, we are the first to consider pre-training on semantic graphs.","url_abs":"https://arxiv.org/abs/2203.07836v4","url_pdf":"https://arxiv.org/pdf/2203.07836v4.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":"graph-pre-training-for-amr-parsing-and-1","repo_url":"https://github.com/muyeby/amrbart","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"graph-pre-training-for-amr-parsing-and-1","repo_url":"https://github.com/goodbai-nlp/amrbart","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"amr-parsing","task_name":"AMR Parsing"},{"task_slug":"amr-to-text-generation","task_name":"AMR-to-Text Generation"},{"task_slug":"abstract-meaning-representation","task_name":"Abstract Meaning Representation"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/amr-parsing-on-bio","task":"AMR Parsing","dataset":"Bio","model":"AMRBART large","rank_in_archive_order":2,"of":5,"metrics":{"Smatch":"63.2"},"uses_additional_data":true},{"leaderboard":"/sota/amr-parsing-on-ldc2017t10","task":"AMR Parsing","dataset":"LDC2017T10","model":"AMRBART large","rank_in_archive_order":6,"of":27,"metrics":{"Smatch":"85.4"},"uses_additional_data":true},{"leaderboard":"/sota/amr-parsing-on-ldc2020t02","task":"AMR Parsing","dataset":"LDC2020T02","model":"AMRBART large","rank_in_archive_order":6,"of":13,"metrics":{"Smatch":"84.2"},"uses_additional_data":true},{"leaderboard":"/sota/amr-parsing-on-new3","task":"AMR Parsing","dataset":"New3","model":"AMRBART large","rank_in_archive_order":1,"of":4,"metrics":{"Smatch":"76.9"},"uses_additional_data":true},{"leaderboard":"/sota/amr-parsing-on-the-little-prince","task":"AMR Parsing","dataset":"The Little Prince","model":"AMRBART large","rank_in_archive_order":1,"of":4,"metrics":{"Smatch":"79.8"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2203.07836","atlas_url":"https://app.syntology.ai/?focus=2203.07836","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.07836"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/goodbai-nlp/amrbart","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/muyeby/amrbart","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/muyeby/AMRBART","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":3,"ran":1,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":3,"repositories":1},"listed":{"samples":2,"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":0,"samples":[{"code_sha256_prefix":"3f7786bc696c91ec","entry":"joint_infilling_full","repo":"goodbai-nlp/amrbart","repo_kind":"listed","path":"pre-train/common/utils.py","file_url":"https://github.com/goodbai-nlp/amrbart/blob/HEAD/pre-train/common/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3f7786bc696c91ec"}},{"code_sha256_prefix":"fadc10fc2c451c92","entry":"label_smoothed_nll_loss","repo":"muyeby/AMRBART","repo_kind":"official","path":"fine-tune/seq2seq_trainer.py","file_url":"https://github.com/muyeby/AMRBART/blob/HEAD/fine-tune/seq2seq_trainer.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fadc10fc2c451c92"}},{"code_sha256_prefix":"cfb09657fff12fcf","entry":"shift_tokens_right","repo":"muyeby/AMRBART","repo_kind":"official","path":"fine-tune/model_interface/modeling_bart.py","file_url":"https://github.com/muyeby/AMRBART/blob/HEAD/fine-tune/model_interface/modeling_bart.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cfb09657fff12fcf"}},{"code_sha256_prefix":"59b0b785b926c986","entry":"shift_tokens_right","repo":"muyeby/AMRBART","repo_kind":"official","path":"pre-train/run_multitask_unified_pretraining.py","file_url":"https://github.com/muyeby/AMRBART/blob/HEAD/pre-train/run_multitask_unified_pretraining.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"59b0b785b926c986"}},{"code_sha256_prefix":"d0b58628f19131d6","entry":"sentence_infilling","repo":"goodbai-nlp/amrbart","repo_kind":"listed","path":"pre-train/common/utils.py","file_url":"https://github.com/goodbai-nlp/amrbart/blob/HEAD/pre-train/common/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d0b58628f19131d6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}