{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:QBFTZJV3LWGCYJ7RGGOA3YOIPQ","short_pith_number":"pith:QBFTZJV3","schema_version":"1.0","canonical_sha256":"804b3ca6bb5d8c2c27f1319c0de1c87c015ab91ba4381658dacf7fafd31a64f2","source":{"kind":"arxiv","id":"2010.09623","version":2},"attestation_state":"computed","paper":{"title":"An Empirical Study for Vietnamese Constituency Parsing with Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Duc-Vu Nguyen, Kiet Van Nguyen, Ngan Luu-Thuy Nguyen, Tuan-Vi Tran, Xuan-Thien Pham","submitted_at":"2020-10-19T16:02:00Z","abstract_excerpt":"In this work, we use a span-based approach for Vietnamese constituency parsing. Our method follows the self-attention encoder architecture and a chart decoder using a CKY-style inference algorithm. We present analyses of the experiment results of the comparison of our empirical method using pre-training models XLM-Roberta and PhoBERT on both Vietnamese datasets VietTreebank and NIIVTB1. The results show that our model with XLM-Roberta archived the significantly F1-score better than other pre-training models, VietTreebank at 81.19% and NIIVTB1 at 85.70%."},"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":"2010.09623","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-19T16:02:00Z","cross_cats_sorted":[],"title_canon_sha256":"14125ae3e801dad1f560414ec5ce78b44b06cd8ceac570e8643f836c8c94e17f","abstract_canon_sha256":"3e3b2e5cc75576efcda4d1bd559fde6c80f85b3bc49a012546ee95c340f5a6ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:44:23.835023Z","signature_b64":"vTNT1/PpsUUuGXpzSemtZeXbR9Ifut7TOiqRPenBrs7jebFYYbiZIcZALGofMkgDdOuZ/fg7N19lR3TIoQf7BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"804b3ca6bb5d8c2c27f1319c0de1c87c015ab91ba4381658dacf7fafd31a64f2","last_reissued_at":"2026-07-05T01:44:23.834588Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:44:23.834588Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Empirical Study for Vietnamese Constituency Parsing with Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Duc-Vu Nguyen, Kiet Van Nguyen, Ngan Luu-Thuy Nguyen, Tuan-Vi Tran, Xuan-Thien Pham","submitted_at":"2020-10-19T16:02:00Z","abstract_excerpt":"In this work, we use a span-based approach for Vietnamese constituency parsing. Our method follows the self-attention encoder architecture and a chart decoder using a CKY-style inference algorithm. We present analyses of the experiment results of the comparison of our empirical method using pre-training models XLM-Roberta and PhoBERT on both Vietnamese datasets VietTreebank and NIIVTB1. The results show that our model with XLM-Roberta archived the significantly F1-score better than other pre-training models, VietTreebank at 81.19% and NIIVTB1 at 85.70%."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.09623","kind":"arxiv","version":2},"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/2010.09623/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":"2010.09623","created_at":"2026-07-05T01:44:23.834644+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.09623v2","created_at":"2026-07-05T01:44:23.834644+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.09623","created_at":"2026-07-05T01:44:23.834644+00:00"},{"alias_kind":"pith_short_12","alias_value":"QBFTZJV3LWGC","created_at":"2026-07-05T01:44:23.834644+00:00"},{"alias_kind":"pith_short_16","alias_value":"QBFTZJV3LWGCYJ7R","created_at":"2026-07-05T01:44:23.834644+00:00"},{"alias_kind":"pith_short_8","alias_value":"QBFTZJV3","created_at":"2026-07-05T01:44:23.834644+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/QBFTZJV3LWGCYJ7RGGOA3YOIPQ","json":"https://pith.science/pith/QBFTZJV3LWGCYJ7RGGOA3YOIPQ.json","graph_json":"https://pith.science/api/pith-number/QBFTZJV3LWGCYJ7RGGOA3YOIPQ/graph.json","events_json":"https://pith.science/api/pith-number/QBFTZJV3LWGCYJ7RGGOA3YOIPQ/events.json","paper":"https://pith.science/paper/QBFTZJV3"},"agent_actions":{"view_html":"https://pith.science/pith/QBFTZJV3LWGCYJ7RGGOA3YOIPQ","download_json":"https://pith.science/pith/QBFTZJV3LWGCYJ7RGGOA3YOIPQ.json","view_paper":"https://pith.science/paper/QBFTZJV3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.09623&json=true","fetch_graph":"https://pith.science/api/pith-number/QBFTZJV3LWGCYJ7RGGOA3YOIPQ/graph.json","fetch_events":"https://pith.science/api/pith-number/QBFTZJV3LWGCYJ7RGGOA3YOIPQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QBFTZJV3LWGCYJ7RGGOA3YOIPQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QBFTZJV3LWGCYJ7RGGOA3YOIPQ/action/storage_attestation","attest_author":"https://pith.science/pith/QBFTZJV3LWGCYJ7RGGOA3YOIPQ/action/author_attestation","sign_citation":"https://pith.science/pith/QBFTZJV3LWGCYJ7RGGOA3YOIPQ/action/citation_signature","submit_replication":"https://pith.science/pith/QBFTZJV3LWGCYJ7RGGOA3YOIPQ/action/replication_record"}},"created_at":"2026-07-05T01:44:23.834644+00:00","updated_at":"2026-07-05T01:44:23.834644+00:00"}