{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:GPS25F6JYVZFFTBCH5FBU6FDGZ","short_pith_number":"pith:GPS25F6J","schema_version":"1.0","canonical_sha256":"33e5ae97c9c57252cc223f4a1a78a3366dc98067d243405a2dd4da4b5e7d579c","source":{"kind":"arxiv","id":"2004.02577","version":1},"attestation_state":"computed","paper":{"title":"Dictionary-based Data Augmentation for Cross-Domain Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chongxuan Huang, Qun Liu, Tianhao Li, Wei Peng, Yun Chen","submitted_at":"2020-04-06T11:50:49Z","abstract_excerpt":"Existing data augmentation approaches for neural machine translation (NMT) have predominantly relied on back-translating in-domain (IND) monolingual corpora. These methods suffer from issues associated with a domain information gap, which leads to translation errors for low frequency and out-of-vocabulary terminology. This paper proposes a dictionary-based data augmentation (DDA) method for cross-domain NMT. DDA synthesizes a domain-specific dictionary with general domain corpora to automatically generate a large-scale pseudo-IND parallel corpus. The generated pseudo-IND data can be used to en"},"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":"2004.02577","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-06T11:50:49Z","cross_cats_sorted":[],"title_canon_sha256":"720655077d66a88967a999d7d3248b163724c7d19ba99adc824e8a75b95a3dde","abstract_canon_sha256":"0b9e4d65771158e0d4d7a32a890385c43bfb9649317f09d962710015e541b217"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:53:00.601712Z","signature_b64":"t2+IgpkImrsOIJgBP/rGziLRGCJFj8pMOwpyCePLaIjQVYLlFzbC3JJnJFmqLMiO7LwdGlUgF0gdhtR06XNjAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33e5ae97c9c57252cc223f4a1a78a3366dc98067d243405a2dd4da4b5e7d579c","last_reissued_at":"2026-07-05T00:53:00.601212Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:53:00.601212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dictionary-based Data Augmentation for Cross-Domain Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chongxuan Huang, Qun Liu, Tianhao Li, Wei Peng, Yun Chen","submitted_at":"2020-04-06T11:50:49Z","abstract_excerpt":"Existing data augmentation approaches for neural machine translation (NMT) have predominantly relied on back-translating in-domain (IND) monolingual corpora. These methods suffer from issues associated with a domain information gap, which leads to translation errors for low frequency and out-of-vocabulary terminology. This paper proposes a dictionary-based data augmentation (DDA) method for cross-domain NMT. DDA synthesizes a domain-specific dictionary with general domain corpora to automatically generate a large-scale pseudo-IND parallel corpus. The generated pseudo-IND data can be used to en"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.02577","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/2004.02577/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":"2004.02577","created_at":"2026-07-05T00:53:00.601272+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.02577v1","created_at":"2026-07-05T00:53:00.601272+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.02577","created_at":"2026-07-05T00:53:00.601272+00:00"},{"alias_kind":"pith_short_12","alias_value":"GPS25F6JYVZF","created_at":"2026-07-05T00:53:00.601272+00:00"},{"alias_kind":"pith_short_16","alias_value":"GPS25F6JYVZFFTBC","created_at":"2026-07-05T00:53:00.601272+00:00"},{"alias_kind":"pith_short_8","alias_value":"GPS25F6J","created_at":"2026-07-05T00:53:00.601272+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.15069","citing_title":"In-Domain African Languages Translation Using LLMs and Multi-armed Bandits","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GPS25F6JYVZFFTBCH5FBU6FDGZ","json":"https://pith.science/pith/GPS25F6JYVZFFTBCH5FBU6FDGZ.json","graph_json":"https://pith.science/api/pith-number/GPS25F6JYVZFFTBCH5FBU6FDGZ/graph.json","events_json":"https://pith.science/api/pith-number/GPS25F6JYVZFFTBCH5FBU6FDGZ/events.json","paper":"https://pith.science/paper/GPS25F6J"},"agent_actions":{"view_html":"https://pith.science/pith/GPS25F6JYVZFFTBCH5FBU6FDGZ","download_json":"https://pith.science/pith/GPS25F6JYVZFFTBCH5FBU6FDGZ.json","view_paper":"https://pith.science/paper/GPS25F6J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.02577&json=true","fetch_graph":"https://pith.science/api/pith-number/GPS25F6JYVZFFTBCH5FBU6FDGZ/graph.json","fetch_events":"https://pith.science/api/pith-number/GPS25F6JYVZFFTBCH5FBU6FDGZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GPS25F6JYVZFFTBCH5FBU6FDGZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GPS25F6JYVZFFTBCH5FBU6FDGZ/action/storage_attestation","attest_author":"https://pith.science/pith/GPS25F6JYVZFFTBCH5FBU6FDGZ/action/author_attestation","sign_citation":"https://pith.science/pith/GPS25F6JYVZFFTBCH5FBU6FDGZ/action/citation_signature","submit_replication":"https://pith.science/pith/GPS25F6JYVZFFTBCH5FBU6FDGZ/action/replication_record"}},"created_at":"2026-07-05T00:53:00.601272+00:00","updated_at":"2026-07-05T00:53:00.601272+00:00"}