{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:LZ2LQRB2HRE7KM7RHBOKEYE2RZ","short_pith_number":"pith:LZ2LQRB2","schema_version":"1.0","canonical_sha256":"5e74b8443a3c49f533f1385ca2609a8e776771904ebf88f1c036478397e2fa0d","source":{"kind":"arxiv","id":"1905.11471","version":1},"attestation_state":"computed","paper":{"title":"XLDA: Cross-Lingual Data Augmentation for Natural Language Inference and Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bryan McCann, Caiming Xiong, Jasdeep Singh, Nitish Shirish Keskar, Richard Socher","submitted_at":"2019-05-27T19:44:33Z","abstract_excerpt":"While natural language processing systems often focus on a single language, multilingual transfer learning has the potential to improve performance, especially for low-resource languages. We introduce XLDA, cross-lingual data augmentation, a method that replaces a segment of the input text with its translation in another language. XLDA enhances performance of all 14 tested languages of the cross-lingual natural language inference (XNLI) benchmark. With improvements of up to $4.8\\%$, training with XLDA achieves state-of-the-art performance for Greek, Turkish, and Urdu. XLDA is in contrast to, a"},"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":"1905.11471","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-27T19:44:33Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"35716d7124f385a53c522d79e76a2785edd1905db262814a154d14796b13024c","abstract_canon_sha256":"19079161d3707b0c6d77028111963281e77d09f8c82a9b18dfe1606fca4acab5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:53.329796Z","signature_b64":"RxNWhOPS5tJq/3eUV2a84Hvco9DI6cjTWlK6SSZEUr2YOsgkZu2UbUv59uqzPoldkjSYdV6wZqxD6t5ITrT2DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e74b8443a3c49f533f1385ca2609a8e776771904ebf88f1c036478397e2fa0d","last_reissued_at":"2026-05-17T23:44:53.329114Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:53.329114Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"XLDA: Cross-Lingual Data Augmentation for Natural Language Inference and Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bryan McCann, Caiming Xiong, Jasdeep Singh, Nitish Shirish Keskar, Richard Socher","submitted_at":"2019-05-27T19:44:33Z","abstract_excerpt":"While natural language processing systems often focus on a single language, multilingual transfer learning has the potential to improve performance, especially for low-resource languages. We introduce XLDA, cross-lingual data augmentation, a method that replaces a segment of the input text with its translation in another language. XLDA enhances performance of all 14 tested languages of the cross-lingual natural language inference (XNLI) benchmark. With improvements of up to $4.8\\%$, training with XLDA achieves state-of-the-art performance for Greek, Turkish, and Urdu. XLDA is in contrast to, a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.11471","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":"1905.11471","created_at":"2026-05-17T23:44:53.329224+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.11471v1","created_at":"2026-05-17T23:44:53.329224+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.11471","created_at":"2026-05-17T23:44:53.329224+00:00"},{"alias_kind":"pith_short_12","alias_value":"LZ2LQRB2HRE7","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_16","alias_value":"LZ2LQRB2HRE7KM7R","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_8","alias_value":"LZ2LQRB2","created_at":"2026-05-18T12:33:21.387695+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1911.02116","citing_title":"Unsupervised Cross-lingual Representation Learning at Scale","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LZ2LQRB2HRE7KM7RHBOKEYE2RZ","json":"https://pith.science/pith/LZ2LQRB2HRE7KM7RHBOKEYE2RZ.json","graph_json":"https://pith.science/api/pith-number/LZ2LQRB2HRE7KM7RHBOKEYE2RZ/graph.json","events_json":"https://pith.science/api/pith-number/LZ2LQRB2HRE7KM7RHBOKEYE2RZ/events.json","paper":"https://pith.science/paper/LZ2LQRB2"},"agent_actions":{"view_html":"https://pith.science/pith/LZ2LQRB2HRE7KM7RHBOKEYE2RZ","download_json":"https://pith.science/pith/LZ2LQRB2HRE7KM7RHBOKEYE2RZ.json","view_paper":"https://pith.science/paper/LZ2LQRB2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.11471&json=true","fetch_graph":"https://pith.science/api/pith-number/LZ2LQRB2HRE7KM7RHBOKEYE2RZ/graph.json","fetch_events":"https://pith.science/api/pith-number/LZ2LQRB2HRE7KM7RHBOKEYE2RZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LZ2LQRB2HRE7KM7RHBOKEYE2RZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LZ2LQRB2HRE7KM7RHBOKEYE2RZ/action/storage_attestation","attest_author":"https://pith.science/pith/LZ2LQRB2HRE7KM7RHBOKEYE2RZ/action/author_attestation","sign_citation":"https://pith.science/pith/LZ2LQRB2HRE7KM7RHBOKEYE2RZ/action/citation_signature","submit_replication":"https://pith.science/pith/LZ2LQRB2HRE7KM7RHBOKEYE2RZ/action/replication_record"}},"created_at":"2026-05-17T23:44:53.329224+00:00","updated_at":"2026-05-17T23:44:53.329224+00:00"}