{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:3KE4T2S6PDTF7HYFHDTYL6I2IZ","short_pith_number":"pith:3KE4T2S6","schema_version":"1.0","canonical_sha256":"da89c9ea5e78e65f9f0538e785f91a4668d404f134311cfa45890aad39396794","source":{"kind":"arxiv","id":"2012.00571","version":1},"attestation_state":"computed","paper":{"title":"Denoising Pre-Training and Data Augmentation Strategies for Enhanced RDF Verbalization with Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Betty Fabre, Johannes Heinecke, Lina Rojas-Barahona, Sebastien Montella, Tanguy Urvoy","submitted_at":"2020-12-01T15:25:47Z","abstract_excerpt":"The task of verbalization of RDF triples has known a growth in popularity due to the rising ubiquity of Knowledge Bases (KBs). The formalism of RDF triples is a simple and efficient way to store facts at a large scale. However, its abstract representation makes it difficult for humans to interpret. For this purpose, the WebNLG challenge aims at promoting automated RDF-to-text generation. We propose to leverage pre-trainings from augmented data with the Transformer model using a data augmentation strategy. Our experiment results show a minimum relative increases of 3.73%, 126.05% and 88.16% in "},"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":"2012.00571","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-01T15:25:47Z","cross_cats_sorted":[],"title_canon_sha256":"29efb1e62e241351e08974bcc25d2f71e519b660876c6912ee5b00c85fa27d80","abstract_canon_sha256":"495cf577d339bc07ffc01076367f737ac7883751023bba620c9828ea3a5909ff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:56:17.914914Z","signature_b64":"1vZ+tTgiwRTKZEgz/viustK4oylIuqQ2LoYRXCp9jqfiKL1Vdo6odFo2KN5Em6gfASJgQ1ntodknHsdzp1ZeDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da89c9ea5e78e65f9f0538e785f91a4668d404f134311cfa45890aad39396794","last_reissued_at":"2026-07-05T01:56:17.914451Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:56:17.914451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Denoising Pre-Training and Data Augmentation Strategies for Enhanced RDF Verbalization with Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Betty Fabre, Johannes Heinecke, Lina Rojas-Barahona, Sebastien Montella, Tanguy Urvoy","submitted_at":"2020-12-01T15:25:47Z","abstract_excerpt":"The task of verbalization of RDF triples has known a growth in popularity due to the rising ubiquity of Knowledge Bases (KBs). The formalism of RDF triples is a simple and efficient way to store facts at a large scale. However, its abstract representation makes it difficult for humans to interpret. For this purpose, the WebNLG challenge aims at promoting automated RDF-to-text generation. We propose to leverage pre-trainings from augmented data with the Transformer model using a data augmentation strategy. Our experiment results show a minimum relative increases of 3.73%, 126.05% and 88.16% in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.00571","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2012.00571/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2012.00571","created_at":"2026-07-05T01:56:17.914506+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.00571v1","created_at":"2026-07-05T01:56:17.914506+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.00571","created_at":"2026-07-05T01:56:17.914506+00:00"},{"alias_kind":"pith_short_12","alias_value":"3KE4T2S6PDTF","created_at":"2026-07-05T01:56:17.914506+00:00"},{"alias_kind":"pith_short_16","alias_value":"3KE4T2S6PDTF7HYF","created_at":"2026-07-05T01:56:17.914506+00:00"},{"alias_kind":"pith_short_8","alias_value":"3KE4T2S6","created_at":"2026-07-05T01:56:17.914506+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3KE4T2S6PDTF7HYFHDTYL6I2IZ","json":"https://pith.science/pith/3KE4T2S6PDTF7HYFHDTYL6I2IZ.json","graph_json":"https://pith.science/api/pith-number/3KE4T2S6PDTF7HYFHDTYL6I2IZ/graph.json","events_json":"https://pith.science/api/pith-number/3KE4T2S6PDTF7HYFHDTYL6I2IZ/events.json","paper":"https://pith.science/paper/3KE4T2S6"},"agent_actions":{"view_html":"https://pith.science/pith/3KE4T2S6PDTF7HYFHDTYL6I2IZ","download_json":"https://pith.science/pith/3KE4T2S6PDTF7HYFHDTYL6I2IZ.json","view_paper":"https://pith.science/paper/3KE4T2S6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.00571&json=true","fetch_graph":"https://pith.science/api/pith-number/3KE4T2S6PDTF7HYFHDTYL6I2IZ/graph.json","fetch_events":"https://pith.science/api/pith-number/3KE4T2S6PDTF7HYFHDTYL6I2IZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3KE4T2S6PDTF7HYFHDTYL6I2IZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3KE4T2S6PDTF7HYFHDTYL6I2IZ/action/storage_attestation","attest_author":"https://pith.science/pith/3KE4T2S6PDTF7HYFHDTYL6I2IZ/action/author_attestation","sign_citation":"https://pith.science/pith/3KE4T2S6PDTF7HYFHDTYL6I2IZ/action/citation_signature","submit_replication":"https://pith.science/pith/3KE4T2S6PDTF7HYFHDTYL6I2IZ/action/replication_record"}},"created_at":"2026-07-05T01:56:17.914506+00:00","updated_at":"2026-07-05T01:56:17.914506+00:00"}