{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:BSE534ZH76DS2M2ESFI5P2ATCN","short_pith_number":"pith:BSE534ZH","schema_version":"1.0","canonical_sha256":"0c89ddf327ff872d33449151d7e8131351138d9db71a9b2c53c1111882729114","source":{"kind":"arxiv","id":"2010.01771","version":1},"attestation_state":"computed","paper":{"title":"Improving AMR Parsing with Sequence-to-Sequence Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dongqin Xu, Guodong Zhou, Junhui Li, Min Zhang, Muhua Zhu","submitted_at":"2020-10-05T04:32:47Z","abstract_excerpt":"In the literature, the research on abstract meaning representation (AMR) parsing is much restricted by the size of human-curated dataset which is critical to build an AMR parser with good performance. To alleviate such data size restriction, pre-trained models have been drawing more and more attention in AMR parsing. However, previous pre-trained models, like BERT, are implemented for general purpose which may not work as expected for the specific task of AMR parsing. In this paper, we focus on sequence-to-sequence (seq2seq) AMR parsing and propose a seq2seq pre-training approach to build pre-"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2010.01771","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-05T04:32:47Z","cross_cats_sorted":[],"title_canon_sha256":"85a3df1c840a620ba5b521b4015a8df2bb623a271ba246e210486a5f2c915c01","abstract_canon_sha256":"8f1d12ab54bca6d866fc11b4ed6bbb427d39bc09a24db7be5894fc094c9bdfd6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:40:09.296672Z","signature_b64":"ybWTfOx3HOymUqshVl/QF0PPdYi6rU7foXO0U38JcaIJh6fW8M4ZwRCMn2au8x/cJE3MZpH7RSTdizxXpTEHAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c89ddf327ff872d33449151d7e8131351138d9db71a9b2c53c1111882729114","last_reissued_at":"2026-07-05T01:40:09.296258Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:40:09.296258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving AMR Parsing with Sequence-to-Sequence Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dongqin Xu, Guodong Zhou, Junhui Li, Min Zhang, Muhua Zhu","submitted_at":"2020-10-05T04:32:47Z","abstract_excerpt":"In the literature, the research on abstract meaning representation (AMR) parsing is much restricted by the size of human-curated dataset which is critical to build an AMR parser with good performance. To alleviate such data size restriction, pre-trained models have been drawing more and more attention in AMR parsing. However, previous pre-trained models, like BERT, are implemented for general purpose which may not work as expected for the specific task of AMR parsing. In this paper, we focus on sequence-to-sequence (seq2seq) AMR parsing and propose a seq2seq pre-training approach to build pre-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.01771","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2010.01771/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2010.01771","created_at":"2026-07-05T01:40:09.296322+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.01771v1","created_at":"2026-07-05T01:40:09.296322+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.01771","created_at":"2026-07-05T01:40:09.296322+00:00"},{"alias_kind":"pith_short_12","alias_value":"BSE534ZH76DS","created_at":"2026-07-05T01:40:09.296322+00:00"},{"alias_kind":"pith_short_16","alias_value":"BSE534ZH76DS2M2E","created_at":"2026-07-05T01:40:09.296322+00:00"},{"alias_kind":"pith_short_8","alias_value":"BSE534ZH","created_at":"2026-07-05T01:40:09.296322+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.07171","citing_title":"EventRR: Event Referential Reasoning for Referring Video Object Segmentation","ref_index":60,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BSE534ZH76DS2M2ESFI5P2ATCN","json":"https://pith.science/pith/BSE534ZH76DS2M2ESFI5P2ATCN.json","graph_json":"https://pith.science/api/pith-number/BSE534ZH76DS2M2ESFI5P2ATCN/graph.json","events_json":"https://pith.science/api/pith-number/BSE534ZH76DS2M2ESFI5P2ATCN/events.json","paper":"https://pith.science/paper/BSE534ZH"},"agent_actions":{"view_html":"https://pith.science/pith/BSE534ZH76DS2M2ESFI5P2ATCN","download_json":"https://pith.science/pith/BSE534ZH76DS2M2ESFI5P2ATCN.json","view_paper":"https://pith.science/paper/BSE534ZH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.01771&json=true","fetch_graph":"https://pith.science/api/pith-number/BSE534ZH76DS2M2ESFI5P2ATCN/graph.json","fetch_events":"https://pith.science/api/pith-number/BSE534ZH76DS2M2ESFI5P2ATCN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BSE534ZH76DS2M2ESFI5P2ATCN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BSE534ZH76DS2M2ESFI5P2ATCN/action/storage_attestation","attest_author":"https://pith.science/pith/BSE534ZH76DS2M2ESFI5P2ATCN/action/author_attestation","sign_citation":"https://pith.science/pith/BSE534ZH76DS2M2ESFI5P2ATCN/action/citation_signature","submit_replication":"https://pith.science/pith/BSE534ZH76DS2M2ESFI5P2ATCN/action/replication_record"}},"created_at":"2026-07-05T01:40:09.296322+00:00","updated_at":"2026-07-05T01:40:09.296322+00:00"}