{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:IM7IQZBSARRHQKJZBUE56O4Y4L","short_pith_number":"pith:IM7IQZBS","schema_version":"1.0","canonical_sha256":"433e88643204627829390d09df3b98e2fd3b3209e01de5b929fd97932723db55","source":{"kind":"arxiv","id":"1905.08212","version":1},"attestation_state":"computed","paper":{"title":"Target Conditioned Sampling: Optimizing Data Selection for Multilingual Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Graham Neubig, Xinyi Wang","submitted_at":"2019-05-20T16:54:43Z","abstract_excerpt":"To improve low-resource Neural Machine Translation (NMT) with multilingual corpora, training on the most related high-resource language only is often more effective than using all data available (Neubig and Hu, 2018). However, it is possible that an intelligent data selection strategy can further improve low-resource NMT with data from other auxiliary languages. In this paper, we seek to construct a sampling distribution over all multilingual data, so that it minimizes the training loss of the low-resource language. Based on this formulation, we propose an efficient algorithm, Target Condition"},"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":"1905.08212","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-20T16:54:43Z","cross_cats_sorted":[],"title_canon_sha256":"8be68e0e4370bdd70358006cc57c8468f218c1feda770841350724f9cd7966ef","abstract_canon_sha256":"c74a90b8001eae1e1d3461d44679af4b862f2167632f283bcb2933355e2304ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:47.322711Z","signature_b64":"R6wrFXFbE/ekyZPN+3ueTloI0aCkSLBpcRrKPxrYoW35V+azBEJ0xX+Lh4hx/wtuUokkJCytU5jj10DxVDSYCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"433e88643204627829390d09df3b98e2fd3b3209e01de5b929fd97932723db55","last_reissued_at":"2026-05-17T23:45:47.322126Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:47.322126Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Target Conditioned Sampling: Optimizing Data Selection for Multilingual Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Graham Neubig, Xinyi Wang","submitted_at":"2019-05-20T16:54:43Z","abstract_excerpt":"To improve low-resource Neural Machine Translation (NMT) with multilingual corpora, training on the most related high-resource language only is often more effective than using all data available (Neubig and Hu, 2018). However, it is possible that an intelligent data selection strategy can further improve low-resource NMT with data from other auxiliary languages. In this paper, we seek to construct a sampling distribution over all multilingual data, so that it minimizes the training loss of the low-resource language. Based on this formulation, we propose an efficient algorithm, Target Condition"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.08212","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":"1905.08212","created_at":"2026-05-17T23:45:47.322198+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.08212v1","created_at":"2026-05-17T23:45:47.322198+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.08212","created_at":"2026-05-17T23:45:47.322198+00:00"},{"alias_kind":"pith_short_12","alias_value":"IM7IQZBSARRH","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"IM7IQZBSARRHQKJZ","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"IM7IQZBS","created_at":"2026-05-18T12:33:18.533446+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.20720","citing_title":"COMPASS: COntinual Multilingual PEFT with Adaptive Semantic Sampling","ref_index":122,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IM7IQZBSARRHQKJZBUE56O4Y4L","json":"https://pith.science/pith/IM7IQZBSARRHQKJZBUE56O4Y4L.json","graph_json":"https://pith.science/api/pith-number/IM7IQZBSARRHQKJZBUE56O4Y4L/graph.json","events_json":"https://pith.science/api/pith-number/IM7IQZBSARRHQKJZBUE56O4Y4L/events.json","paper":"https://pith.science/paper/IM7IQZBS"},"agent_actions":{"view_html":"https://pith.science/pith/IM7IQZBSARRHQKJZBUE56O4Y4L","download_json":"https://pith.science/pith/IM7IQZBSARRHQKJZBUE56O4Y4L.json","view_paper":"https://pith.science/paper/IM7IQZBS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.08212&json=true","fetch_graph":"https://pith.science/api/pith-number/IM7IQZBSARRHQKJZBUE56O4Y4L/graph.json","fetch_events":"https://pith.science/api/pith-number/IM7IQZBSARRHQKJZBUE56O4Y4L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IM7IQZBSARRHQKJZBUE56O4Y4L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IM7IQZBSARRHQKJZBUE56O4Y4L/action/storage_attestation","attest_author":"https://pith.science/pith/IM7IQZBSARRHQKJZBUE56O4Y4L/action/author_attestation","sign_citation":"https://pith.science/pith/IM7IQZBSARRHQKJZBUE56O4Y4L/action/citation_signature","submit_replication":"https://pith.science/pith/IM7IQZBSARRHQKJZBUE56O4Y4L/action/replication_record"}},"created_at":"2026-05-17T23:45:47.322198+00:00","updated_at":"2026-05-17T23:45:47.322198+00:00"}