{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:7XOMYD3M4HZOYWKLF25BYGVW5A","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":"ba1783506d3999beec66b05fb00f06cb0b4ca65b26d08a3d01b75ab4380929d5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-01T08:12:15Z","title_canon_sha256":"761274f15468c5d3c49abef7f17835afff47d9232f7bfcad2f3bfc12f5b04d7c"},"schema_version":"1.0","source":{"id":"1705.00440","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.00440","created_at":"2026-05-18T00:23:45Z"},{"alias_kind":"arxiv_version","alias_value":"1705.00440v1","created_at":"2026-05-18T00:23:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.00440","created_at":"2026-05-18T00:23:45Z"},{"alias_kind":"pith_short_12","alias_value":"7XOMYD3M4HZO","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_16","alias_value":"7XOMYD3M4HZOYWKL","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_8","alias_value":"7XOMYD3M","created_at":"2026-05-18T12:31:05Z"}],"graph_snapshots":[{"event_id":"sha256:dc8b4ce757d35a195a342bf5f7fd33e944ef9304bb797430811d1b9ec6121b04","target":"graph","created_at":"2026-05-18T00:23:45Z","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":"The quality of a Neural Machine Translation system depends substantially on the availability of sizable parallel corpora. For low-resource language pairs this is not the case, resulting in poor translation quality. Inspired by work in computer vision, we propose a novel data augmentation approach that targets low-frequency words by generating new sentence pairs containing rare words in new, synthetically created contexts. Experimental results on simulated low-resource settings show that our method improves translation quality by up to 2.9 BLEU points over the baseline and up to 3.2 BLEU over b","authors_text":"Arianna Bisazza, Christof Monz, Marzieh Fadaee","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-01T08:12:15Z","title":"Data Augmentation for Low-Resource Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.00440","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:d13c36c824849af38907ba6cbc1c241aeaa217d314bfeb9e891c2f0d56fb63bc","target":"record","created_at":"2026-05-18T00:23:45Z","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":"ba1783506d3999beec66b05fb00f06cb0b4ca65b26d08a3d01b75ab4380929d5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-01T08:12:15Z","title_canon_sha256":"761274f15468c5d3c49abef7f17835afff47d9232f7bfcad2f3bfc12f5b04d7c"},"schema_version":"1.0","source":{"id":"1705.00440","kind":"arxiv","version":1}},"canonical_sha256":"fddccc0f6ce1f2ec594b2eba1c1ab6e83de108178b45d1bb91ca3008974eef60","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fddccc0f6ce1f2ec594b2eba1c1ab6e83de108178b45d1bb91ca3008974eef60","first_computed_at":"2026-05-18T00:23:45.696834Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:23:45.696834Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"M0f3faMB9hr3f4/IMwqQsJ1RQDj/nkNeZfDXmaLVCbTJFOhMiuPBegg8A1ssCWMuSuU5fTJYJfRwg2iO8S7BAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:23:45.697355Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.00440","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d13c36c824849af38907ba6cbc1c241aeaa217d314bfeb9e891c2f0d56fb63bc","sha256:dc8b4ce757d35a195a342bf5f7fd33e944ef9304bb797430811d1b9ec6121b04"],"state_sha256":"719247bd948efcbeb6eef2f1107e871cc8c199492723863382c296c4ad563029"}