{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:FFIHVBIAQI5IUBAGP4JOIEJO5I","short_pith_number":"pith:FFIHVBIA","schema_version":"1.0","canonical_sha256":"29507a8500823a8a04067f12e4112eea0a697d28d29f51f69842fb5f5d6933b9","source":{"kind":"arxiv","id":"1708.09403","version":1},"attestation_state":"computed","paper":{"title":"Fast(er) Exact Decoding and Global Training for Transition-Based Dependency Parsing via a Minimal Feature Set","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Liang Huang, Lillian Lee, Tianze Shi","submitted_at":"2017-08-30T18:01:08Z","abstract_excerpt":"We first present a minimal feature set for transition-based dependency parsing, continuing a recent trend started by Kiperwasser and Goldberg (2016a) and Cross and Huang (2016a) of using bi-directional LSTM features. We plug our minimal feature set into the dynamic-programming framework of Huang and Sagae (2010) and Kuhlmann et al. (2011) to produce the first implementation of worst-case O(n^3) exact decoders for arc-hybrid and arc-eager transition systems. With our minimal features, we also present O(n^3) global training methods. Finally, using ensembles including our new parsers, we achieve "},"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":"1708.09403","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-30T18:01:08Z","cross_cats_sorted":[],"title_canon_sha256":"64cdc172a5c26769bc721de6dab7e27c91145fc44f2a5e6142bcd86b3bb3ffb5","abstract_canon_sha256":"b8f91b8d7d3f0b7c92fd8731b31ac8ae4c7c73216f258d073d90230a01ece39a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:36:18.917272Z","signature_b64":"pGAuGJ7A8yBgwtVQQaYpX9Mf8GxFM4LHj4qbBXUFFKB+1Hcx2V3NTf8NAUeu5Xjx1o2Ne19691gG+5Z97rrMDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29507a8500823a8a04067f12e4112eea0a697d28d29f51f69842fb5f5d6933b9","last_reissued_at":"2026-05-18T00:36:18.916714Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:36:18.916714Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fast(er) Exact Decoding and Global Training for Transition-Based Dependency Parsing via a Minimal Feature Set","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Liang Huang, Lillian Lee, Tianze Shi","submitted_at":"2017-08-30T18:01:08Z","abstract_excerpt":"We first present a minimal feature set for transition-based dependency parsing, continuing a recent trend started by Kiperwasser and Goldberg (2016a) and Cross and Huang (2016a) of using bi-directional LSTM features. We plug our minimal feature set into the dynamic-programming framework of Huang and Sagae (2010) and Kuhlmann et al. (2011) to produce the first implementation of worst-case O(n^3) exact decoders for arc-hybrid and arc-eager transition systems. With our minimal features, we also present O(n^3) global training methods. Finally, using ensembles including our new parsers, we achieve "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.09403","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":"1708.09403","created_at":"2026-05-18T00:36:18.916802+00:00"},{"alias_kind":"arxiv_version","alias_value":"1708.09403v1","created_at":"2026-05-18T00:36:18.916802+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.09403","created_at":"2026-05-18T00:36:18.916802+00:00"},{"alias_kind":"pith_short_12","alias_value":"FFIHVBIAQI5I","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_16","alias_value":"FFIHVBIAQI5IUBAG","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_8","alias_value":"FFIHVBIA","created_at":"2026-05-18T12:31:15.632608+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/FFIHVBIAQI5IUBAGP4JOIEJO5I","json":"https://pith.science/pith/FFIHVBIAQI5IUBAGP4JOIEJO5I.json","graph_json":"https://pith.science/api/pith-number/FFIHVBIAQI5IUBAGP4JOIEJO5I/graph.json","events_json":"https://pith.science/api/pith-number/FFIHVBIAQI5IUBAGP4JOIEJO5I/events.json","paper":"https://pith.science/paper/FFIHVBIA"},"agent_actions":{"view_html":"https://pith.science/pith/FFIHVBIAQI5IUBAGP4JOIEJO5I","download_json":"https://pith.science/pith/FFIHVBIAQI5IUBAGP4JOIEJO5I.json","view_paper":"https://pith.science/paper/FFIHVBIA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1708.09403&json=true","fetch_graph":"https://pith.science/api/pith-number/FFIHVBIAQI5IUBAGP4JOIEJO5I/graph.json","fetch_events":"https://pith.science/api/pith-number/FFIHVBIAQI5IUBAGP4JOIEJO5I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FFIHVBIAQI5IUBAGP4JOIEJO5I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FFIHVBIAQI5IUBAGP4JOIEJO5I/action/storage_attestation","attest_author":"https://pith.science/pith/FFIHVBIAQI5IUBAGP4JOIEJO5I/action/author_attestation","sign_citation":"https://pith.science/pith/FFIHVBIAQI5IUBAGP4JOIEJO5I/action/citation_signature","submit_replication":"https://pith.science/pith/FFIHVBIAQI5IUBAGP4JOIEJO5I/action/replication_record"}},"created_at":"2026-05-18T00:36:18.916802+00:00","updated_at":"2026-05-18T00:36:18.916802+00:00"}