{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:ABBSNBBEFV7N6OY7Y4MLRZUDQD","short_pith_number":"pith:ABBSNBBE","schema_version":"1.0","canonical_sha256":"00432684242d7edf3b1fc718b8e68380fab5c77e51b939b7d11b6cd529ff4d65","source":{"kind":"arxiv","id":"1808.07512","version":2},"attestation_state":"computed","paper":{"title":"SwitchOut: an Efficient Data Augmentation Algorithm for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Graham Neubig, Hieu Pham, Xinyi Wang, Zihang Dai","submitted_at":"2018-08-22T18:26:43Z","abstract_excerpt":"In this work, we examine methods for data augmentation for text-based tasks such as neural machine translation (NMT). We formulate the design of a data augmentation policy with desirable properties as an optimization problem, and derive a generic analytic solution. This solution not only subsumes some existing augmentation schemes, but also leads to an extremely simple data augmentation strategy for NMT: randomly replacing words in both the source sentence and the target sentence with other random words from their corresponding vocabularies. We name this method SwitchOut. Experiments on three "},"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":"1808.07512","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-22T18:26:43Z","cross_cats_sorted":[],"title_canon_sha256":"000c7186b667d3acbceca645f0f99be806ff6a18a87b38defece417582ffe7df","abstract_canon_sha256":"dd6a605be6892953836cac77cad63f9037418955cbdd47424e0d9116ad4c542a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:07:05.195142Z","signature_b64":"3BftBU1u4Qt/VzcmTwes6fAttP/meT0G+CsU6HxDYT+Gz8KyMgIBFNHkNwBrKsrijV5BkqszHfNVC307xRadBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00432684242d7edf3b1fc718b8e68380fab5c77e51b939b7d11b6cd529ff4d65","last_reissued_at":"2026-05-18T00:07:05.194420Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:07:05.194420Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SwitchOut: an Efficient Data Augmentation Algorithm for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Graham Neubig, Hieu Pham, Xinyi Wang, Zihang Dai","submitted_at":"2018-08-22T18:26:43Z","abstract_excerpt":"In this work, we examine methods for data augmentation for text-based tasks such as neural machine translation (NMT). We formulate the design of a data augmentation policy with desirable properties as an optimization problem, and derive a generic analytic solution. This solution not only subsumes some existing augmentation schemes, but also leads to an extremely simple data augmentation strategy for NMT: randomly replacing words in both the source sentence and the target sentence with other random words from their corresponding vocabularies. We name this method SwitchOut. Experiments on three "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.07512","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":""},"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":"1808.07512","created_at":"2026-05-18T00:07:05.194536+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.07512v2","created_at":"2026-05-18T00:07:05.194536+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.07512","created_at":"2026-05-18T00:07:05.194536+00:00"},{"alias_kind":"pith_short_12","alias_value":"ABBSNBBEFV7N","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_16","alias_value":"ABBSNBBEFV7N6OY7","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_8","alias_value":"ABBSNBBE","created_at":"2026-05-18T12:32:13.499390+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.08393","citing_title":"Robust Machine Translation with Domain Sensitive Pseudo-Sources: Baidu-OSU WMT19 MT Robustness Shared Task System Report","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ABBSNBBEFV7N6OY7Y4MLRZUDQD","json":"https://pith.science/pith/ABBSNBBEFV7N6OY7Y4MLRZUDQD.json","graph_json":"https://pith.science/api/pith-number/ABBSNBBEFV7N6OY7Y4MLRZUDQD/graph.json","events_json":"https://pith.science/api/pith-number/ABBSNBBEFV7N6OY7Y4MLRZUDQD/events.json","paper":"https://pith.science/paper/ABBSNBBE"},"agent_actions":{"view_html":"https://pith.science/pith/ABBSNBBEFV7N6OY7Y4MLRZUDQD","download_json":"https://pith.science/pith/ABBSNBBEFV7N6OY7Y4MLRZUDQD.json","view_paper":"https://pith.science/paper/ABBSNBBE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.07512&json=true","fetch_graph":"https://pith.science/api/pith-number/ABBSNBBEFV7N6OY7Y4MLRZUDQD/graph.json","fetch_events":"https://pith.science/api/pith-number/ABBSNBBEFV7N6OY7Y4MLRZUDQD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ABBSNBBEFV7N6OY7Y4MLRZUDQD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ABBSNBBEFV7N6OY7Y4MLRZUDQD/action/storage_attestation","attest_author":"https://pith.science/pith/ABBSNBBEFV7N6OY7Y4MLRZUDQD/action/author_attestation","sign_citation":"https://pith.science/pith/ABBSNBBEFV7N6OY7Y4MLRZUDQD/action/citation_signature","submit_replication":"https://pith.science/pith/ABBSNBBEFV7N6OY7Y4MLRZUDQD/action/replication_record"}},"created_at":"2026-05-18T00:07:05.194536+00:00","updated_at":"2026-05-18T00:07:05.194536+00:00"}