{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:474H5CNV4UOXV3OU2YALWKF55F","short_pith_number":"pith:474H5CNV","schema_version":"1.0","canonical_sha256":"e7f87e89b5e51d7aedd4d600bb28bde97f1b5c9d1dea966aa681c96d0065ed50","source":{"kind":"arxiv","id":"1809.01534","version":1},"attestation_state":"computed","paper":{"title":"Utilizing Character and Word Embeddings for Text Normalization with Sequence-to-Sequence Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Daniel Watson, Nasser Zalmout, Nizar Habash","submitted_at":"2018-09-05T16:44:04Z","abstract_excerpt":"Text normalization is an important enabling technology for several NLP tasks. Recently, neural-network-based approaches have outperformed well-established models in this task. However, in languages other than English, there has been little exploration in this direction. Both the scarcity of annotated data and the complexity of the language increase the difficulty of the problem. To address these challenges, we use a sequence-to-sequence model with character-based attention, which in addition to its self-learned character embeddings, uses word embeddings pre-trained with an approach that also m"},"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":"1809.01534","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-05T16:44:04Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"ce072f301353d0a2937bbde2b6bba08071267fdc819985385330527f7e74d2bf","abstract_canon_sha256":"39c344c3c5595bcc21adb0aabfcdd50e70b207f584f46801b955b98bef928390"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:27.295189Z","signature_b64":"5Zb6d0+gUNszeDhnmJc5hpUjHm9zUeil4Rn5YZEP2JVGg85NmYHOJauVvWm8fOXeS31+H//YhpSIGIbIFecHCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7f87e89b5e51d7aedd4d600bb28bde97f1b5c9d1dea966aa681c96d0065ed50","last_reissued_at":"2026-05-18T00:06:27.294643Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:27.294643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Utilizing Character and Word Embeddings for Text Normalization with Sequence-to-Sequence Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Daniel Watson, Nasser Zalmout, Nizar Habash","submitted_at":"2018-09-05T16:44:04Z","abstract_excerpt":"Text normalization is an important enabling technology for several NLP tasks. Recently, neural-network-based approaches have outperformed well-established models in this task. However, in languages other than English, there has been little exploration in this direction. Both the scarcity of annotated data and the complexity of the language increase the difficulty of the problem. To address these challenges, we use a sequence-to-sequence model with character-based attention, which in addition to its self-learned character embeddings, uses word embeddings pre-trained with an approach that also m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.01534","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":"1809.01534","created_at":"2026-05-18T00:06:27.294742+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.01534v1","created_at":"2026-05-18T00:06:27.294742+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.01534","created_at":"2026-05-18T00:06:27.294742+00:00"},{"alias_kind":"pith_short_12","alias_value":"474H5CNV4UOX","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_16","alias_value":"474H5CNV4UOXV3OU","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_8","alias_value":"474H5CNV","created_at":"2026-05-18T12:32:05.422762+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/474H5CNV4UOXV3OU2YALWKF55F","json":"https://pith.science/pith/474H5CNV4UOXV3OU2YALWKF55F.json","graph_json":"https://pith.science/api/pith-number/474H5CNV4UOXV3OU2YALWKF55F/graph.json","events_json":"https://pith.science/api/pith-number/474H5CNV4UOXV3OU2YALWKF55F/events.json","paper":"https://pith.science/paper/474H5CNV"},"agent_actions":{"view_html":"https://pith.science/pith/474H5CNV4UOXV3OU2YALWKF55F","download_json":"https://pith.science/pith/474H5CNV4UOXV3OU2YALWKF55F.json","view_paper":"https://pith.science/paper/474H5CNV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.01534&json=true","fetch_graph":"https://pith.science/api/pith-number/474H5CNV4UOXV3OU2YALWKF55F/graph.json","fetch_events":"https://pith.science/api/pith-number/474H5CNV4UOXV3OU2YALWKF55F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/474H5CNV4UOXV3OU2YALWKF55F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/474H5CNV4UOXV3OU2YALWKF55F/action/storage_attestation","attest_author":"https://pith.science/pith/474H5CNV4UOXV3OU2YALWKF55F/action/author_attestation","sign_citation":"https://pith.science/pith/474H5CNV4UOXV3OU2YALWKF55F/action/citation_signature","submit_replication":"https://pith.science/pith/474H5CNV4UOXV3OU2YALWKF55F/action/replication_record"}},"created_at":"2026-05-18T00:06:27.294742+00:00","updated_at":"2026-05-18T00:06:27.294742+00:00"}