{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TUXYSPVXMVAFKYWVXF7ICKCLWV","short_pith_number":"pith:TUXYSPVX","schema_version":"1.0","canonical_sha256":"9d2f893eb765405562d5b97e81284bb54c6d83b309670e36182c1bdb3cf3fbd2","source":{"kind":"arxiv","id":"2306.01382","version":2},"attestation_state":"computed","paper":{"title":"Leveraging Auxiliary Domain Parallel Data in Intermediate Task Fine-tuning for Low-resource Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andrew Ho, Anthony Rinaldi, En-Shiun Annie Lee, Jonah Mackey, Rikki Hung, Sarubi Thillainathan, Shravan Nayak, Surangika Ranathunga, Yining Wang","submitted_at":"2023-06-02T09:05:18Z","abstract_excerpt":"NMT systems trained on Pre-trained Multilingual Sequence-Sequence (PMSS) models flounder when sufficient amounts of parallel data is not available for fine-tuning. This specifically holds for languages missing/under-represented in these models. The problem gets aggravated when the data comes from different domains. In this paper, we show that intermediate-task fine-tuning (ITFT) of PMSS models is extremely beneficial for domain-specific NMT, especially when target domain data is limited/unavailable and the considered languages are missing or under-represented in the PMSS model. We quantify the"},"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":"2306.01382","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-02T09:05:18Z","cross_cats_sorted":[],"title_canon_sha256":"b313ef600fcb522f1704c3518de38ae549b37eea7a1479348fcc100e6db17438","abstract_canon_sha256":"6b3fc45ae03a36887827480e0d68edaf96eb0c3428fd5febf390f19cbcbb02e0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:53:38.823381Z","signature_b64":"V/eWW5QYeDr5mQ/HN8UPBWuCV2IB+oPMJ/N6t0qvlwO3iNhQ2MmElwicbPNdpWqaPzn1Ol8QxFLhMuP39aIoAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d2f893eb765405562d5b97e81284bb54c6d83b309670e36182c1bdb3cf3fbd2","last_reissued_at":"2026-07-05T06:53:38.822891Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:53:38.822891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Auxiliary Domain Parallel Data in Intermediate Task Fine-tuning for Low-resource Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andrew Ho, Anthony Rinaldi, En-Shiun Annie Lee, Jonah Mackey, Rikki Hung, Sarubi Thillainathan, Shravan Nayak, Surangika Ranathunga, Yining Wang","submitted_at":"2023-06-02T09:05:18Z","abstract_excerpt":"NMT systems trained on Pre-trained Multilingual Sequence-Sequence (PMSS) models flounder when sufficient amounts of parallel data is not available for fine-tuning. This specifically holds for languages missing/under-represented in these models. The problem gets aggravated when the data comes from different domains. In this paper, we show that intermediate-task fine-tuning (ITFT) of PMSS models is extremely beneficial for domain-specific NMT, especially when target domain data is limited/unavailable and the considered languages are missing or under-represented in the PMSS model. We quantify the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.01382","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2306.01382/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":"2306.01382","created_at":"2026-07-05T06:53:38.822949+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.01382v2","created_at":"2026-07-05T06:53:38.822949+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.01382","created_at":"2026-07-05T06:53:38.822949+00:00"},{"alias_kind":"pith_short_12","alias_value":"TUXYSPVXMVAF","created_at":"2026-07-05T06:53:38.822949+00:00"},{"alias_kind":"pith_short_16","alias_value":"TUXYSPVXMVAFKYWV","created_at":"2026-07-05T06:53:38.822949+00:00"},{"alias_kind":"pith_short_8","alias_value":"TUXYSPVX","created_at":"2026-07-05T06:53:38.822949+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/TUXYSPVXMVAFKYWVXF7ICKCLWV","json":"https://pith.science/pith/TUXYSPVXMVAFKYWVXF7ICKCLWV.json","graph_json":"https://pith.science/api/pith-number/TUXYSPVXMVAFKYWVXF7ICKCLWV/graph.json","events_json":"https://pith.science/api/pith-number/TUXYSPVXMVAFKYWVXF7ICKCLWV/events.json","paper":"https://pith.science/paper/TUXYSPVX"},"agent_actions":{"view_html":"https://pith.science/pith/TUXYSPVXMVAFKYWVXF7ICKCLWV","download_json":"https://pith.science/pith/TUXYSPVXMVAFKYWVXF7ICKCLWV.json","view_paper":"https://pith.science/paper/TUXYSPVX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.01382&json=true","fetch_graph":"https://pith.science/api/pith-number/TUXYSPVXMVAFKYWVXF7ICKCLWV/graph.json","fetch_events":"https://pith.science/api/pith-number/TUXYSPVXMVAFKYWVXF7ICKCLWV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TUXYSPVXMVAFKYWVXF7ICKCLWV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TUXYSPVXMVAFKYWVXF7ICKCLWV/action/storage_attestation","attest_author":"https://pith.science/pith/TUXYSPVXMVAFKYWVXF7ICKCLWV/action/author_attestation","sign_citation":"https://pith.science/pith/TUXYSPVXMVAFKYWVXF7ICKCLWV/action/citation_signature","submit_replication":"https://pith.science/pith/TUXYSPVXMVAFKYWVXF7ICKCLWV/action/replication_record"}},"created_at":"2026-07-05T06:53:38.822949+00:00","updated_at":"2026-07-05T06:53:38.822949+00:00"}