{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:7XOMYD3M4HZOYWKLF25BYGVW5A","short_pith_number":"pith:7XOMYD3M","schema_version":"1.0","canonical_sha256":"fddccc0f6ce1f2ec594b2eba1c1ab6e83de108178b45d1bb91ca3008974eef60","source":{"kind":"arxiv","id":"1705.00440","version":1},"attestation_state":"computed","paper":{"title":"Data Augmentation for Low-Resource Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Arianna Bisazza, Christof Monz, Marzieh Fadaee","submitted_at":"2017-05-01T08:12:15Z","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"},"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":"1705.00440","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-01T08:12:15Z","cross_cats_sorted":[],"title_canon_sha256":"761274f15468c5d3c49abef7f17835afff47d9232f7bfcad2f3bfc12f5b04d7c","abstract_canon_sha256":"ba1783506d3999beec66b05fb00f06cb0b4ca65b26d08a3d01b75ab4380929d5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:23:45.697355Z","signature_b64":"M0f3faMB9hr3f4/IMwqQsJ1RQDj/nkNeZfDXmaLVCbTJFOhMiuPBegg8A1ssCWMuSuU5fTJYJfRwg2iO8S7BAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fddccc0f6ce1f2ec594b2eba1c1ab6e83de108178b45d1bb91ca3008974eef60","last_reissued_at":"2026-05-18T00:23:45.696834Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:23:45.696834Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data Augmentation for Low-Resource Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Arianna Bisazza, Christof Monz, Marzieh Fadaee","submitted_at":"2017-05-01T08:12:15Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.00440","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":"1705.00440","created_at":"2026-05-18T00:23:45.696903+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.00440v1","created_at":"2026-05-18T00:23:45.696903+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.00440","created_at":"2026-05-18T00:23:45.696903+00:00"},{"alias_kind":"pith_short_12","alias_value":"7XOMYD3M4HZO","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_16","alias_value":"7XOMYD3M4HZOYWKL","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_8","alias_value":"7XOMYD3M","created_at":"2026-05-18T12:31:05.417338+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.14590","citing_title":"Backtranslation and paraphrasing in the LLM era? Comparing data augmentation methods for emotion classification","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7XOMYD3M4HZOYWKLF25BYGVW5A","json":"https://pith.science/pith/7XOMYD3M4HZOYWKLF25BYGVW5A.json","graph_json":"https://pith.science/api/pith-number/7XOMYD3M4HZOYWKLF25BYGVW5A/graph.json","events_json":"https://pith.science/api/pith-number/7XOMYD3M4HZOYWKLF25BYGVW5A/events.json","paper":"https://pith.science/paper/7XOMYD3M"},"agent_actions":{"view_html":"https://pith.science/pith/7XOMYD3M4HZOYWKLF25BYGVW5A","download_json":"https://pith.science/pith/7XOMYD3M4HZOYWKLF25BYGVW5A.json","view_paper":"https://pith.science/paper/7XOMYD3M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.00440&json=true","fetch_graph":"https://pith.science/api/pith-number/7XOMYD3M4HZOYWKLF25BYGVW5A/graph.json","fetch_events":"https://pith.science/api/pith-number/7XOMYD3M4HZOYWKLF25BYGVW5A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7XOMYD3M4HZOYWKLF25BYGVW5A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7XOMYD3M4HZOYWKLF25BYGVW5A/action/storage_attestation","attest_author":"https://pith.science/pith/7XOMYD3M4HZOYWKLF25BYGVW5A/action/author_attestation","sign_citation":"https://pith.science/pith/7XOMYD3M4HZOYWKLF25BYGVW5A/action/citation_signature","submit_replication":"https://pith.science/pith/7XOMYD3M4HZOYWKLF25BYGVW5A/action/replication_record"}},"created_at":"2026-05-18T00:23:45.696903+00:00","updated_at":"2026-05-18T00:23:45.696903+00:00"}