{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:EELQSYHJLJTDXSSH5XJ564BOZF","short_pith_number":"pith:EELQSYHJ","schema_version":"1.0","canonical_sha256":"21170960e95a663bca47edd3df702ec96c5db1681d5dffa3a48da32e0476492e","source":{"kind":"arxiv","id":"1811.01100","version":1},"attestation_state":"computed","paper":{"title":"Prior Knowledge Integration for Neural Machine Translation using Posterior Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Huanbo Luan, Jiacheng Zhang, Jingfang Xu, Maosong Sun, Yang Liu","submitted_at":"2018-11-02T21:33:40Z","abstract_excerpt":"Although neural machine translation has made significant progress recently, how to integrate multiple overlapping, arbitrary prior knowledge sources remains a challenge. In this work, we propose to use posterior regularization to provide a general framework for integrating prior knowledge into neural machine translation. We represent prior knowledge sources as features in a log-linear model, which guides the learning process of the neural translation model. Experiments on Chinese-English translation show that our approach leads to significant improvements."},"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":"1811.01100","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-02T21:33:40Z","cross_cats_sorted":[],"title_canon_sha256":"60fc6dd3e18469bdab7c6452949d67d8f994565ad8e0b4b37f66a6c76929b019","abstract_canon_sha256":"d2ee50443f182b9f670619d9711f3a85fd1b7af001cc188e5f8d23181c6f58f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:37.124968Z","signature_b64":"bkPn3KCcjWOF5Rvv/gKAsh4R8c+8zL4gRlqaBxepbbq+Mxu3czzYnU/Tq5GLncMCFM7J1wJwxB4CfeUtQ3qcCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21170960e95a663bca47edd3df702ec96c5db1681d5dffa3a48da32e0476492e","last_reissued_at":"2026-05-18T00:01:37.124540Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:37.124540Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prior Knowledge Integration for Neural Machine Translation using Posterior Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Huanbo Luan, Jiacheng Zhang, Jingfang Xu, Maosong Sun, Yang Liu","submitted_at":"2018-11-02T21:33:40Z","abstract_excerpt":"Although neural machine translation has made significant progress recently, how to integrate multiple overlapping, arbitrary prior knowledge sources remains a challenge. In this work, we propose to use posterior regularization to provide a general framework for integrating prior knowledge into neural machine translation. We represent prior knowledge sources as features in a log-linear model, which guides the learning process of the neural translation model. Experiments on Chinese-English translation show that our approach leads to significant improvements."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.01100","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":"1811.01100","created_at":"2026-05-18T00:01:37.124596+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.01100v1","created_at":"2026-05-18T00:01:37.124596+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.01100","created_at":"2026-05-18T00:01:37.124596+00:00"},{"alias_kind":"pith_short_12","alias_value":"EELQSYHJLJTD","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_16","alias_value":"EELQSYHJLJTDXSSH","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_8","alias_value":"EELQSYHJ","created_at":"2026-05-18T12:32:22.470017+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/EELQSYHJLJTDXSSH5XJ564BOZF","json":"https://pith.science/pith/EELQSYHJLJTDXSSH5XJ564BOZF.json","graph_json":"https://pith.science/api/pith-number/EELQSYHJLJTDXSSH5XJ564BOZF/graph.json","events_json":"https://pith.science/api/pith-number/EELQSYHJLJTDXSSH5XJ564BOZF/events.json","paper":"https://pith.science/paper/EELQSYHJ"},"agent_actions":{"view_html":"https://pith.science/pith/EELQSYHJLJTDXSSH5XJ564BOZF","download_json":"https://pith.science/pith/EELQSYHJLJTDXSSH5XJ564BOZF.json","view_paper":"https://pith.science/paper/EELQSYHJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.01100&json=true","fetch_graph":"https://pith.science/api/pith-number/EELQSYHJLJTDXSSH5XJ564BOZF/graph.json","fetch_events":"https://pith.science/api/pith-number/EELQSYHJLJTDXSSH5XJ564BOZF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EELQSYHJLJTDXSSH5XJ564BOZF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EELQSYHJLJTDXSSH5XJ564BOZF/action/storage_attestation","attest_author":"https://pith.science/pith/EELQSYHJLJTDXSSH5XJ564BOZF/action/author_attestation","sign_citation":"https://pith.science/pith/EELQSYHJLJTDXSSH5XJ564BOZF/action/citation_signature","submit_replication":"https://pith.science/pith/EELQSYHJLJTDXSSH5XJ564BOZF/action/replication_record"}},"created_at":"2026-05-18T00:01:37.124596+00:00","updated_at":"2026-05-18T00:01:37.124596+00:00"}