{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:RSEFWYEVK5WJS4MTTOCP6VM3SJ","short_pith_number":"pith:RSEFWYEV","schema_version":"1.0","canonical_sha256":"8c885b6095576c9971939b84ff559b924293c689bac49766f05cd54f7f72e2fe","source":{"kind":"arxiv","id":"1905.13370","version":1},"attestation_state":"computed","paper":{"title":"Rewarding Smatch: Transition-Based AMR Parsing with Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abhishek Shah, Hui Wan, Miguel Ballesteros, Radu Florian, Salim Roukos, Tahira Naseem","submitted_at":"2019-05-31T01:15:36Z","abstract_excerpt":"Our work involves enriching the Stack-LSTM transition-based AMR parser (Ballesteros and Al-Onaizan, 2017) by augmenting training with Policy Learning and rewarding the Smatch score of sampled graphs. In addition, we also combined several AMR-to-text alignments with an attention mechanism and we supplemented the parser with pre-processed concept identification, named entities and contextualized embeddings. We achieve a highly competitive performance that is comparable to the best published results. We show an in-depth study ablating each of the new components of the parser"},"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":"1905.13370","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-31T01:15:36Z","cross_cats_sorted":[],"title_canon_sha256":"4a918fa1e9ed0972e3896f73b22d1ab528318969892437d779941c23be14a9ec","abstract_canon_sha256":"a366124a4cdc409b9eecd2f519e4b38ab45e67fe852174e89b844abd1a330443"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:35.153676Z","signature_b64":"TiPphP5NnAw5GZ0onLmWbpbZ8C1fLCsosRqnoYe0Jl8O2uIH+gfURf3iXxlruYsOWzxeLAXbDqg0tsVjDQ8SCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c885b6095576c9971939b84ff559b924293c689bac49766f05cd54f7f72e2fe","last_reissued_at":"2026-05-17T23:44:35.153085Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:35.153085Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rewarding Smatch: Transition-Based AMR Parsing with Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abhishek Shah, Hui Wan, Miguel Ballesteros, Radu Florian, Salim Roukos, Tahira Naseem","submitted_at":"2019-05-31T01:15:36Z","abstract_excerpt":"Our work involves enriching the Stack-LSTM transition-based AMR parser (Ballesteros and Al-Onaizan, 2017) by augmenting training with Policy Learning and rewarding the Smatch score of sampled graphs. In addition, we also combined several AMR-to-text alignments with an attention mechanism and we supplemented the parser with pre-processed concept identification, named entities and contextualized embeddings. We achieve a highly competitive performance that is comparable to the best published results. We show an in-depth study ablating each of the new components of the parser"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.13370","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":""},"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":"1905.13370","created_at":"2026-05-17T23:44:35.153183+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.13370v1","created_at":"2026-05-17T23:44:35.153183+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.13370","created_at":"2026-05-17T23:44:35.153183+00:00"},{"alias_kind":"pith_short_12","alias_value":"RSEFWYEVK5WJ","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"RSEFWYEVK5WJS4MT","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"RSEFWYEV","created_at":"2026-05-18T12:33:27.125529+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RSEFWYEVK5WJS4MTTOCP6VM3SJ","json":"https://pith.science/pith/RSEFWYEVK5WJS4MTTOCP6VM3SJ.json","graph_json":"https://pith.science/api/pith-number/RSEFWYEVK5WJS4MTTOCP6VM3SJ/graph.json","events_json":"https://pith.science/api/pith-number/RSEFWYEVK5WJS4MTTOCP6VM3SJ/events.json","paper":"https://pith.science/paper/RSEFWYEV"},"agent_actions":{"view_html":"https://pith.science/pith/RSEFWYEVK5WJS4MTTOCP6VM3SJ","download_json":"https://pith.science/pith/RSEFWYEVK5WJS4MTTOCP6VM3SJ.json","view_paper":"https://pith.science/paper/RSEFWYEV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.13370&json=true","fetch_graph":"https://pith.science/api/pith-number/RSEFWYEVK5WJS4MTTOCP6VM3SJ/graph.json","fetch_events":"https://pith.science/api/pith-number/RSEFWYEVK5WJS4MTTOCP6VM3SJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RSEFWYEVK5WJS4MTTOCP6VM3SJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RSEFWYEVK5WJS4MTTOCP6VM3SJ/action/storage_attestation","attest_author":"https://pith.science/pith/RSEFWYEVK5WJS4MTTOCP6VM3SJ/action/author_attestation","sign_citation":"https://pith.science/pith/RSEFWYEVK5WJS4MTTOCP6VM3SJ/action/citation_signature","submit_replication":"https://pith.science/pith/RSEFWYEVK5WJS4MTTOCP6VM3SJ/action/replication_record"}},"created_at":"2026-05-17T23:44:35.153183+00:00","updated_at":"2026-05-17T23:44:35.153183+00:00"}