{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:QDRATSV6HFAOCD5DLL3BUDGRCT","short_pith_number":"pith:QDRATSV6","schema_version":"1.0","canonical_sha256":"80e209cabe3940e10fa35af61a0cd114f4223fc460af77af03d21cf3c3980d64","source":{"kind":"arxiv","id":"1711.04951","version":1},"attestation_state":"computed","paper":{"title":"From Word Segmentation to POS Tagging for Vietnamese","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dai Quoc Nguyen, Dat Quoc Nguyen, Mark Dras, Mark Johnson, Thanh Vu","submitted_at":"2017-11-14T05:19:45Z","abstract_excerpt":"This paper presents an empirical comparison of two strategies for Vietnamese Part-of-Speech (POS) tagging from unsegmented text: (i) a pipeline strategy where we consider the output of a word segmenter as the input of a POS tagger, and (ii) a joint strategy where we predict a combined segmentation and POS tag for each syllable. We also make a comparison between state-of-the-art (SOTA) feature-based and neural network-based models. On the benchmark Vietnamese treebank (Nguyen et al., 2009), experimental results show that the pipeline strategy produces better scores of POS tagging from unsegment"},"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":"1711.04951","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-11-14T05:19:45Z","cross_cats_sorted":[],"title_canon_sha256":"52818ce5c9e3cce5bffbd2a343371d9ea28cfd038d6added4f135293b3e1e652","abstract_canon_sha256":"6bdb08c93ea16c50d661ee95eb2ff39f37da219f33423eaecb47595131963268"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:30:35.345133Z","signature_b64":"IXPYTdq1Aao6oNiQ8A2JMqN/juwncIydHrDhcPFtkQDl6aMbfG3gDTOXJJncQnpNNEhqvGG0DXv/MIYBr9lYAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80e209cabe3940e10fa35af61a0cd114f4223fc460af77af03d21cf3c3980d64","last_reissued_at":"2026-05-18T00:30:35.344240Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:30:35.344240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Word Segmentation to POS Tagging for Vietnamese","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dai Quoc Nguyen, Dat Quoc Nguyen, Mark Dras, Mark Johnson, Thanh Vu","submitted_at":"2017-11-14T05:19:45Z","abstract_excerpt":"This paper presents an empirical comparison of two strategies for Vietnamese Part-of-Speech (POS) tagging from unsegmented text: (i) a pipeline strategy where we consider the output of a word segmenter as the input of a POS tagger, and (ii) a joint strategy where we predict a combined segmentation and POS tag for each syllable. We also make a comparison between state-of-the-art (SOTA) feature-based and neural network-based models. On the benchmark Vietnamese treebank (Nguyen et al., 2009), experimental results show that the pipeline strategy produces better scores of POS tagging from unsegment"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.04951","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":"1711.04951","created_at":"2026-05-18T00:30:35.344403+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.04951v1","created_at":"2026-05-18T00:30:35.344403+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.04951","created_at":"2026-05-18T00:30:35.344403+00:00"},{"alias_kind":"pith_short_12","alias_value":"QDRATSV6HFAO","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_16","alias_value":"QDRATSV6HFAOCD5D","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_8","alias_value":"QDRATSV6","created_at":"2026-05-18T12:31:37.085036+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/QDRATSV6HFAOCD5DLL3BUDGRCT","json":"https://pith.science/pith/QDRATSV6HFAOCD5DLL3BUDGRCT.json","graph_json":"https://pith.science/api/pith-number/QDRATSV6HFAOCD5DLL3BUDGRCT/graph.json","events_json":"https://pith.science/api/pith-number/QDRATSV6HFAOCD5DLL3BUDGRCT/events.json","paper":"https://pith.science/paper/QDRATSV6"},"agent_actions":{"view_html":"https://pith.science/pith/QDRATSV6HFAOCD5DLL3BUDGRCT","download_json":"https://pith.science/pith/QDRATSV6HFAOCD5DLL3BUDGRCT.json","view_paper":"https://pith.science/paper/QDRATSV6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.04951&json=true","fetch_graph":"https://pith.science/api/pith-number/QDRATSV6HFAOCD5DLL3BUDGRCT/graph.json","fetch_events":"https://pith.science/api/pith-number/QDRATSV6HFAOCD5DLL3BUDGRCT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QDRATSV6HFAOCD5DLL3BUDGRCT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QDRATSV6HFAOCD5DLL3BUDGRCT/action/storage_attestation","attest_author":"https://pith.science/pith/QDRATSV6HFAOCD5DLL3BUDGRCT/action/author_attestation","sign_citation":"https://pith.science/pith/QDRATSV6HFAOCD5DLL3BUDGRCT/action/citation_signature","submit_replication":"https://pith.science/pith/QDRATSV6HFAOCD5DLL3BUDGRCT/action/replication_record"}},"created_at":"2026-05-18T00:30:35.344403+00:00","updated_at":"2026-05-18T00:30:35.344403+00:00"}