{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:FOOPPDTPH7MXWFELFWHR4DTMOG","short_pith_number":"pith:FOOPPDTP","schema_version":"1.0","canonical_sha256":"2b9cf78e6f3fd97b148b2d8f1e0e6c718cffac0e22f81a8be23d211124c2282c","source":{"kind":"arxiv","id":"2007.04686","version":1},"attestation_state":"computed","paper":{"title":"Greedy Transition-Based Dependency Parsing with Discrete and Continuous Supertag Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ali Basirat, Joakim Nivre","submitted_at":"2020-07-09T10:29:19Z","abstract_excerpt":"We study the effect of rich supertag features in greedy transition-based dependency parsing. While previous studies have shown that sparse boolean features representing the 1-best supertag of a word can improve parsing accuracy, we show that we can get further improvements by adding a continuous vector representation of the entire supertag distribution for a word. In this way, we achieve the best results for greedy transition-based parsing with supertag features with $88.6\\%$ LAS and $90.9\\%$ UASon the English Penn Treebank converted to Stanford Dependencies."},"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":"2007.04686","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-07-09T10:29:19Z","cross_cats_sorted":[],"title_canon_sha256":"d423a88f08950a3e3b1ba5f4d278258208efdfd169e8c79be1816129de8efc4a","abstract_canon_sha256":"07e1bdd7a0a7a8107964116d0f71ee0a547785496d34cd5f801f1f686ff89c2f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:17:32.934280Z","signature_b64":"nU5wRRB0hXmCymM0s8txhejBN+obYVaGvpctSy35HIObNE7XAXG8yEDveJioExLdvjVnX9TubtRUVRPgRYmPBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b9cf78e6f3fd97b148b2d8f1e0e6c718cffac0e22f81a8be23d211124c2282c","last_reissued_at":"2026-07-05T01:17:32.933915Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:17:32.933915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Greedy Transition-Based Dependency Parsing with Discrete and Continuous Supertag Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ali Basirat, Joakim Nivre","submitted_at":"2020-07-09T10:29:19Z","abstract_excerpt":"We study the effect of rich supertag features in greedy transition-based dependency parsing. While previous studies have shown that sparse boolean features representing the 1-best supertag of a word can improve parsing accuracy, we show that we can get further improvements by adding a continuous vector representation of the entire supertag distribution for a word. In this way, we achieve the best results for greedy transition-based parsing with supertag features with $88.6\\%$ LAS and $90.9\\%$ UASon the English Penn Treebank converted to Stanford Dependencies."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.04686","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/2007.04686/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":"2007.04686","created_at":"2026-07-05T01:17:32.933970+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.04686v1","created_at":"2026-07-05T01:17:32.933970+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.04686","created_at":"2026-07-05T01:17:32.933970+00:00"},{"alias_kind":"pith_short_12","alias_value":"FOOPPDTPH7MX","created_at":"2026-07-05T01:17:32.933970+00:00"},{"alias_kind":"pith_short_16","alias_value":"FOOPPDTPH7MXWFEL","created_at":"2026-07-05T01:17:32.933970+00:00"},{"alias_kind":"pith_short_8","alias_value":"FOOPPDTP","created_at":"2026-07-05T01:17:32.933970+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.05977","citing_title":"Mitigating Catastrophic Forgetting with Adaptive Transformer Block Expansion in Federated Fine-Tuning","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FOOPPDTPH7MXWFELFWHR4DTMOG","json":"https://pith.science/pith/FOOPPDTPH7MXWFELFWHR4DTMOG.json","graph_json":"https://pith.science/api/pith-number/FOOPPDTPH7MXWFELFWHR4DTMOG/graph.json","events_json":"https://pith.science/api/pith-number/FOOPPDTPH7MXWFELFWHR4DTMOG/events.json","paper":"https://pith.science/paper/FOOPPDTP"},"agent_actions":{"view_html":"https://pith.science/pith/FOOPPDTPH7MXWFELFWHR4DTMOG","download_json":"https://pith.science/pith/FOOPPDTPH7MXWFELFWHR4DTMOG.json","view_paper":"https://pith.science/paper/FOOPPDTP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.04686&json=true","fetch_graph":"https://pith.science/api/pith-number/FOOPPDTPH7MXWFELFWHR4DTMOG/graph.json","fetch_events":"https://pith.science/api/pith-number/FOOPPDTPH7MXWFELFWHR4DTMOG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FOOPPDTPH7MXWFELFWHR4DTMOG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FOOPPDTPH7MXWFELFWHR4DTMOG/action/storage_attestation","attest_author":"https://pith.science/pith/FOOPPDTPH7MXWFELFWHR4DTMOG/action/author_attestation","sign_citation":"https://pith.science/pith/FOOPPDTPH7MXWFELFWHR4DTMOG/action/citation_signature","submit_replication":"https://pith.science/pith/FOOPPDTPH7MXWFELFWHR4DTMOG/action/replication_record"}},"created_at":"2026-07-05T01:17:32.933970+00:00","updated_at":"2026-07-05T01:17:32.933970+00:00"}