{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:IM7IQZBSARRHQKJZBUE56O4Y4L","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c74a90b8001eae1e1d3461d44679af4b862f2167632f283bcb2933355e2304ba","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-20T16:54:43Z","title_canon_sha256":"8be68e0e4370bdd70358006cc57c8468f218c1feda770841350724f9cd7966ef"},"schema_version":"1.0","source":{"id":"1905.08212","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.08212","created_at":"2026-05-17T23:45:47Z"},{"alias_kind":"arxiv_version","alias_value":"1905.08212v1","created_at":"2026-05-17T23:45:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.08212","created_at":"2026-05-17T23:45:47Z"},{"alias_kind":"pith_short_12","alias_value":"IM7IQZBSARRH","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"IM7IQZBSARRHQKJZ","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"IM7IQZBS","created_at":"2026-05-18T12:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:97d745b2e59f1840923d8476e6cb4aabbcfdc1e32b167c6eed4cb7d25e62f712","target":"graph","created_at":"2026-05-17T23:45:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Graham Neubig, Xinyi Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-20T16:54:43Z","title":"Target Conditioned Sampling: Optimizing Data Selection for Multilingual Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.08212","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ead6fd2604ec44f61cee185f1c66c1ac4831dcc4554f2388ffb9761c56281ce6","target":"record","created_at":"2026-05-17T23:45:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c74a90b8001eae1e1d3461d44679af4b862f2167632f283bcb2933355e2304ba","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-20T16:54:43Z","title_canon_sha256":"8be68e0e4370bdd70358006cc57c8468f218c1feda770841350724f9cd7966ef"},"schema_version":"1.0","source":{"id":"1905.08212","kind":"arxiv","version":1}},"canonical_sha256":"433e88643204627829390d09df3b98e2fd3b3209e01de5b929fd97932723db55","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"433e88643204627829390d09df3b98e2fd3b3209e01de5b929fd97932723db55","first_computed_at":"2026-05-17T23:45:47.322126Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:45:47.322126Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R6wrFXFbE/ekyZPN+3ueTloI0aCkSLBpcRrKPxrYoW35V+azBEJ0xX+Lh4hx/wtuUokkJCytU5jj10DxVDSYCA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:45:47.322711Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.08212","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ead6fd2604ec44f61cee185f1c66c1ac4831dcc4554f2388ffb9761c56281ce6","sha256:97d745b2e59f1840923d8476e6cb4aabbcfdc1e32b167c6eed4cb7d25e62f712"],"state_sha256":"421c4a76543b29686141804792c9a9e56cc3d8843a10172b716938168f3fbcf6"}