{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:5FYYFXF6LQ2PCKQ6VEIKPZPKFA","short_pith_number":"pith:5FYYFXF6","schema_version":"1.0","canonical_sha256":"e97182dcbe5c34f12a1ea910a7e5ea28003f0a54dc4687417c91b939b89c223e","source":{"kind":"arxiv","id":"1906.03129","version":1},"attestation_state":"computed","paper":{"title":"Word-based Domain Adaptation for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Leonard Dahlmann, Pavel Petrushkov, Sanjika Hewavitharana, Shahram Khadivi, Shen Yan","submitted_at":"2019-06-07T14:32:17Z","abstract_excerpt":"In this paper, we empirically investigate applying word-level weights to adapt neural machine translation to e-commerce domains, where small e-commerce datasets and large out-of-domain datasets are available. In order to mine in-domain like words in the out-of-domain datasets, we compute word weights by using a domain-specific and a non-domain-specific language model followed by smoothing and binary quantization. The baseline model is trained on mixed in-domain and out-of-domain datasets. Experimental results on English to Chinese e-commerce domain translation show that compared to continuing "},"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":"1906.03129","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-07T14:32:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f8d02041e8f48a224288bdd6c6072a826e4b977d3a3bd4b6b98355acf5ce28d1","abstract_canon_sha256":"f6dcd649f3e672374eb8382f313948d7e4bfd0908391e6d28a74e9c5001f3e2b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:54.900159Z","signature_b64":"N+ayjXFk++5eyGH/YTbzHbv82491KPSerLE7kE+vtj37V+QfDQg/F9UQvLToNH/XwjYUFkzcoqzkTB0gXsUbCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e97182dcbe5c34f12a1ea910a7e5ea28003f0a54dc4687417c91b939b89c223e","last_reissued_at":"2026-05-17T23:43:54.899542Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:54.899542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Word-based Domain Adaptation for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Leonard Dahlmann, Pavel Petrushkov, Sanjika Hewavitharana, Shahram Khadivi, Shen Yan","submitted_at":"2019-06-07T14:32:17Z","abstract_excerpt":"In this paper, we empirically investigate applying word-level weights to adapt neural machine translation to e-commerce domains, where small e-commerce datasets and large out-of-domain datasets are available. In order to mine in-domain like words in the out-of-domain datasets, we compute word weights by using a domain-specific and a non-domain-specific language model followed by smoothing and binary quantization. The baseline model is trained on mixed in-domain and out-of-domain datasets. Experimental results on English to Chinese e-commerce domain translation show that compared to continuing "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.03129","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":"1906.03129","created_at":"2026-05-17T23:43:54.899644+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.03129v1","created_at":"2026-05-17T23:43:54.899644+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.03129","created_at":"2026-05-17T23:43:54.899644+00:00"},{"alias_kind":"pith_short_12","alias_value":"5FYYFXF6LQ2P","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"5FYYFXF6LQ2PCKQ6","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"5FYYFXF6","created_at":"2026-05-18T12:33:10.108867+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/5FYYFXF6LQ2PCKQ6VEIKPZPKFA","json":"https://pith.science/pith/5FYYFXF6LQ2PCKQ6VEIKPZPKFA.json","graph_json":"https://pith.science/api/pith-number/5FYYFXF6LQ2PCKQ6VEIKPZPKFA/graph.json","events_json":"https://pith.science/api/pith-number/5FYYFXF6LQ2PCKQ6VEIKPZPKFA/events.json","paper":"https://pith.science/paper/5FYYFXF6"},"agent_actions":{"view_html":"https://pith.science/pith/5FYYFXF6LQ2PCKQ6VEIKPZPKFA","download_json":"https://pith.science/pith/5FYYFXF6LQ2PCKQ6VEIKPZPKFA.json","view_paper":"https://pith.science/paper/5FYYFXF6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.03129&json=true","fetch_graph":"https://pith.science/api/pith-number/5FYYFXF6LQ2PCKQ6VEIKPZPKFA/graph.json","fetch_events":"https://pith.science/api/pith-number/5FYYFXF6LQ2PCKQ6VEIKPZPKFA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5FYYFXF6LQ2PCKQ6VEIKPZPKFA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5FYYFXF6LQ2PCKQ6VEIKPZPKFA/action/storage_attestation","attest_author":"https://pith.science/pith/5FYYFXF6LQ2PCKQ6VEIKPZPKFA/action/author_attestation","sign_citation":"https://pith.science/pith/5FYYFXF6LQ2PCKQ6VEIKPZPKFA/action/citation_signature","submit_replication":"https://pith.science/pith/5FYYFXF6LQ2PCKQ6VEIKPZPKFA/action/replication_record"}},"created_at":"2026-05-17T23:43:54.899644+00:00","updated_at":"2026-05-17T23:43:54.899644+00:00"}