{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:55VUNC6LB6QKFNENXSRJNFIZGM","short_pith_number":"pith:55VUNC6L","schema_version":"1.0","canonical_sha256":"ef6b468bcb0fa0a2b48dbca2969519331c87ddd3643dd216f9ee99f9f953646e","source":{"kind":"arxiv","id":"1912.07239","version":1},"attestation_state":"computed","paper":{"title":"Iterative Dual Domain Adaptation for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiali Zeng, Jiebo Luo, Jinsong Su, Yang Liu, Yaojie Lu, Yongjing Yin, Yubin Ge","submitted_at":"2019-12-16T08:21:28Z","abstract_excerpt":"Previous studies on the domain adaptation for neural machine translation (NMT) mainly focus on the one-pass transferring out-of-domain translation knowledge to in-domain NMT model. In this paper, we argue that such a strategy fails to fully extract the domain-shared translation knowledge, and repeatedly utilizing corpora of different domains can lead to better distillation of domain-shared translation knowledge. To this end, we propose an iterative dual domain adaptation framework for NMT. Specifically, we first pre-train in-domain and out-of-domain NMT models using their own training corpora "},"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":"1912.07239","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-12-16T08:21:28Z","cross_cats_sorted":[],"title_canon_sha256":"dae245a211a33aef3a9caf54e2055edcaf4bdb20d2d7b7f2a0109f69c32b7871","abstract_canon_sha256":"a91859c8dee23d8401dc52534421f7ed28be870b42844af143717653c4f6204e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:26:19.841509Z","signature_b64":"3ihEbOgqwpY1Vxu1npQ2GNpdYbYwaa/O2hHWqkg6YwQupcFw+ZbNsSvsEnqFRUUvK+KYRqTC/q26tz35JpROCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef6b468bcb0fa0a2b48dbca2969519331c87ddd3643dd216f9ee99f9f953646e","last_reissued_at":"2026-07-05T00:26:19.841112Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:26:19.841112Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Iterative Dual Domain Adaptation for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiali Zeng, Jiebo Luo, Jinsong Su, Yang Liu, Yaojie Lu, Yongjing Yin, Yubin Ge","submitted_at":"2019-12-16T08:21:28Z","abstract_excerpt":"Previous studies on the domain adaptation for neural machine translation (NMT) mainly focus on the one-pass transferring out-of-domain translation knowledge to in-domain NMT model. In this paper, we argue that such a strategy fails to fully extract the domain-shared translation knowledge, and repeatedly utilizing corpora of different domains can lead to better distillation of domain-shared translation knowledge. To this end, we propose an iterative dual domain adaptation framework for NMT. Specifically, we first pre-train in-domain and out-of-domain NMT models using their own training corpora "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.07239","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/1912.07239/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":"1912.07239","created_at":"2026-07-05T00:26:19.841173+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.07239v1","created_at":"2026-07-05T00:26:19.841173+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.07239","created_at":"2026-07-05T00:26:19.841173+00:00"},{"alias_kind":"pith_short_12","alias_value":"55VUNC6LB6QK","created_at":"2026-07-05T00:26:19.841173+00:00"},{"alias_kind":"pith_short_16","alias_value":"55VUNC6LB6QKFNEN","created_at":"2026-07-05T00:26:19.841173+00:00"},{"alias_kind":"pith_short_8","alias_value":"55VUNC6L","created_at":"2026-07-05T00:26:19.841173+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/55VUNC6LB6QKFNENXSRJNFIZGM","json":"https://pith.science/pith/55VUNC6LB6QKFNENXSRJNFIZGM.json","graph_json":"https://pith.science/api/pith-number/55VUNC6LB6QKFNENXSRJNFIZGM/graph.json","events_json":"https://pith.science/api/pith-number/55VUNC6LB6QKFNENXSRJNFIZGM/events.json","paper":"https://pith.science/paper/55VUNC6L"},"agent_actions":{"view_html":"https://pith.science/pith/55VUNC6LB6QKFNENXSRJNFIZGM","download_json":"https://pith.science/pith/55VUNC6LB6QKFNENXSRJNFIZGM.json","view_paper":"https://pith.science/paper/55VUNC6L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.07239&json=true","fetch_graph":"https://pith.science/api/pith-number/55VUNC6LB6QKFNENXSRJNFIZGM/graph.json","fetch_events":"https://pith.science/api/pith-number/55VUNC6LB6QKFNENXSRJNFIZGM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/55VUNC6LB6QKFNENXSRJNFIZGM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/55VUNC6LB6QKFNENXSRJNFIZGM/action/storage_attestation","attest_author":"https://pith.science/pith/55VUNC6LB6QKFNENXSRJNFIZGM/action/author_attestation","sign_citation":"https://pith.science/pith/55VUNC6LB6QKFNENXSRJNFIZGM/action/citation_signature","submit_replication":"https://pith.science/pith/55VUNC6LB6QKFNENXSRJNFIZGM/action/replication_record"}},"created_at":"2026-07-05T00:26:19.841173+00:00","updated_at":"2026-07-05T00:26:19.841173+00:00"}