{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:WLAWZDZBA5XLFXCDFT7IXJXRSN","short_pith_number":"pith:WLAWZDZB","schema_version":"1.0","canonical_sha256":"b2c16c8f21076eb2dc432cfe8ba6f19366a81e0c5eb48412a898b99e39bf7d8e","source":{"kind":"arxiv","id":"1704.06855","version":2},"attestation_state":"computed","paper":{"title":"Deep Multitask Learning for Semantic Dependency Parsing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hao Peng, Noah A. Smith, Sam Thomson","submitted_at":"2017-04-22T22:56:04Z","abstract_excerpt":"We present a deep neural architecture that parses sentences into three semantic dependency graph formalisms. By using efficient, nearly arc-factored inference and a bidirectional-LSTM composed with a multi-layer perceptron, our base system is able to significantly improve the state of the art for semantic dependency parsing, without using hand-engineered features or syntax. We then explore two multitask learning approaches---one that shares parameters across formalisms, and one that uses higher-order structures to predict the graphs jointly. We find that both approaches improve performance acr"},"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":"1704.06855","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-04-22T22:56:04Z","cross_cats_sorted":[],"title_canon_sha256":"4c55d5a0d55ca53dd07010c43458ce15a28a00d5ab1a686228a65047db75c190","abstract_canon_sha256":"67f29aec2fd7bfce84999d5f5da88dc11f79dbcaef8be01c2f7433e6274aa285"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:45:31.846882Z","signature_b64":"Qz904an/Ucc7gFbbzlBrzjdOkjZjfUUfMFCll4WE6f1SpIFhP3VvbVRzmKtNlNDqvjvSD8ZcAzR/kSblKd/KDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2c16c8f21076eb2dc432cfe8ba6f19366a81e0c5eb48412a898b99e39bf7d8e","last_reissued_at":"2026-05-18T00:45:31.846240Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:45:31.846240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Multitask Learning for Semantic Dependency Parsing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hao Peng, Noah A. Smith, Sam Thomson","submitted_at":"2017-04-22T22:56:04Z","abstract_excerpt":"We present a deep neural architecture that parses sentences into three semantic dependency graph formalisms. By using efficient, nearly arc-factored inference and a bidirectional-LSTM composed with a multi-layer perceptron, our base system is able to significantly improve the state of the art for semantic dependency parsing, without using hand-engineered features or syntax. We then explore two multitask learning approaches---one that shares parameters across formalisms, and one that uses higher-order structures to predict the graphs jointly. We find that both approaches improve performance acr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.06855","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":""},"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":"1704.06855","created_at":"2026-05-18T00:45:31.846336+00:00"},{"alias_kind":"arxiv_version","alias_value":"1704.06855v2","created_at":"2026-05-18T00:45:31.846336+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.06855","created_at":"2026-05-18T00:45:31.846336+00:00"},{"alias_kind":"pith_short_12","alias_value":"WLAWZDZBA5XL","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_16","alias_value":"WLAWZDZBA5XLFXCD","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_8","alias_value":"WLAWZDZB","created_at":"2026-05-18T12:31:53.515858+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/WLAWZDZBA5XLFXCDFT7IXJXRSN","json":"https://pith.science/pith/WLAWZDZBA5XLFXCDFT7IXJXRSN.json","graph_json":"https://pith.science/api/pith-number/WLAWZDZBA5XLFXCDFT7IXJXRSN/graph.json","events_json":"https://pith.science/api/pith-number/WLAWZDZBA5XLFXCDFT7IXJXRSN/events.json","paper":"https://pith.science/paper/WLAWZDZB"},"agent_actions":{"view_html":"https://pith.science/pith/WLAWZDZBA5XLFXCDFT7IXJXRSN","download_json":"https://pith.science/pith/WLAWZDZBA5XLFXCDFT7IXJXRSN.json","view_paper":"https://pith.science/paper/WLAWZDZB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1704.06855&json=true","fetch_graph":"https://pith.science/api/pith-number/WLAWZDZBA5XLFXCDFT7IXJXRSN/graph.json","fetch_events":"https://pith.science/api/pith-number/WLAWZDZBA5XLFXCDFT7IXJXRSN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WLAWZDZBA5XLFXCDFT7IXJXRSN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WLAWZDZBA5XLFXCDFT7IXJXRSN/action/storage_attestation","attest_author":"https://pith.science/pith/WLAWZDZBA5XLFXCDFT7IXJXRSN/action/author_attestation","sign_citation":"https://pith.science/pith/WLAWZDZBA5XLFXCDFT7IXJXRSN/action/citation_signature","submit_replication":"https://pith.science/pith/WLAWZDZBA5XLFXCDFT7IXJXRSN/action/replication_record"}},"created_at":"2026-05-18T00:45:31.846336+00:00","updated_at":"2026-05-18T00:45:31.846336+00:00"}