{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:HNSIBNQ6SWWWZ5BHEP7V5JDHZN","short_pith_number":"pith:HNSIBNQ6","schema_version":"1.0","canonical_sha256":"3b6480b61e95ad6cf42723ff5ea467cb415cdc9821540087f8eef78a396faec9","source":{"kind":"arxiv","id":"1703.00782","version":1},"attestation_state":"computed","paper":{"title":"Lock-Free Parallel Perceptron for Graph-based Dependency Parsing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Shuming Ma, Xu Sun","submitted_at":"2017-03-02T13:49:23Z","abstract_excerpt":"Dependency parsing is an important NLP task. A popular approach for dependency parsing is structured perceptron. Still, graph-based dependency parsing has the time complexity of $O(n^3)$, and it suffers from slow training. To deal with this problem, we propose a parallel algorithm called parallel perceptron. The parallel algorithm can make full use of a multi-core computer which saves a lot of training time. Based on experiments we observe that dependency parsing with parallel perceptron can achieve 8-fold faster training speed than traditional structured perceptron methods when using 10 threa"},"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":"1703.00782","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-03-02T13:49:23Z","cross_cats_sorted":[],"title_canon_sha256":"9275e94105642319371ebed00df1cea1058b80f1c940496afb20b46a8651ed30","abstract_canon_sha256":"234b4e36934b4579522837bda8a7507cb1fdb3fbce5a4d4f73b8d05bea88e4e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:49:40.778807Z","signature_b64":"8NhtkxXWS3Z+4TCemS1r3B2Vlq9O+6ZusyXR5gUu90d95q0oXBwhA1OM0BIDYqt/Kj7J/wQ9E54vIKRhozTDBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b6480b61e95ad6cf42723ff5ea467cb415cdc9821540087f8eef78a396faec9","last_reissued_at":"2026-05-18T00:49:40.778168Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:49:40.778168Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lock-Free Parallel Perceptron for Graph-based Dependency Parsing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Shuming Ma, Xu Sun","submitted_at":"2017-03-02T13:49:23Z","abstract_excerpt":"Dependency parsing is an important NLP task. A popular approach for dependency parsing is structured perceptron. Still, graph-based dependency parsing has the time complexity of $O(n^3)$, and it suffers from slow training. To deal with this problem, we propose a parallel algorithm called parallel perceptron. The parallel algorithm can make full use of a multi-core computer which saves a lot of training time. Based on experiments we observe that dependency parsing with parallel perceptron can achieve 8-fold faster training speed than traditional structured perceptron methods when using 10 threa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.00782","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":"1703.00782","created_at":"2026-05-18T00:49:40.778262+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.00782v1","created_at":"2026-05-18T00:49:40.778262+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.00782","created_at":"2026-05-18T00:49:40.778262+00:00"},{"alias_kind":"pith_short_12","alias_value":"HNSIBNQ6SWWW","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_16","alias_value":"HNSIBNQ6SWWWZ5BH","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_8","alias_value":"HNSIBNQ6","created_at":"2026-05-18T12:31:18.294218+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/HNSIBNQ6SWWWZ5BHEP7V5JDHZN","json":"https://pith.science/pith/HNSIBNQ6SWWWZ5BHEP7V5JDHZN.json","graph_json":"https://pith.science/api/pith-number/HNSIBNQ6SWWWZ5BHEP7V5JDHZN/graph.json","events_json":"https://pith.science/api/pith-number/HNSIBNQ6SWWWZ5BHEP7V5JDHZN/events.json","paper":"https://pith.science/paper/HNSIBNQ6"},"agent_actions":{"view_html":"https://pith.science/pith/HNSIBNQ6SWWWZ5BHEP7V5JDHZN","download_json":"https://pith.science/pith/HNSIBNQ6SWWWZ5BHEP7V5JDHZN.json","view_paper":"https://pith.science/paper/HNSIBNQ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.00782&json=true","fetch_graph":"https://pith.science/api/pith-number/HNSIBNQ6SWWWZ5BHEP7V5JDHZN/graph.json","fetch_events":"https://pith.science/api/pith-number/HNSIBNQ6SWWWZ5BHEP7V5JDHZN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HNSIBNQ6SWWWZ5BHEP7V5JDHZN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HNSIBNQ6SWWWZ5BHEP7V5JDHZN/action/storage_attestation","attest_author":"https://pith.science/pith/HNSIBNQ6SWWWZ5BHEP7V5JDHZN/action/author_attestation","sign_citation":"https://pith.science/pith/HNSIBNQ6SWWWZ5BHEP7V5JDHZN/action/citation_signature","submit_replication":"https://pith.science/pith/HNSIBNQ6SWWWZ5BHEP7V5JDHZN/action/replication_record"}},"created_at":"2026-05-18T00:49:40.778262+00:00","updated_at":"2026-05-18T00:49:40.778262+00:00"}