{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:ZPLG3OQTGS5HPZ6S57244PLHBR","short_pith_number":"pith:ZPLG3OQT","schema_version":"1.0","canonical_sha256":"cbd66dba1334ba77e7d2eff5ce3d670c5df1c32b1038ab33e00eef03fda83856","source":{"kind":"arxiv","id":"1806.00044","version":3},"attestation_state":"computed","paper":{"title":"Text normalization using memory augmented neural networks","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aman Hussain, Subhojeet Pramanik","submitted_at":"2018-05-31T18:37:37Z","abstract_excerpt":"We perform text normalization, i.e. the transformation of words from the written to the spoken form, using a memory augmented neural network. With the addition of dynamic memory access and storage mechanism, we present a neural architecture that will serve as a language-agnostic text normalization system while avoiding the kind of unacceptable errors made by the LSTM-based recurrent neural networks. By successfully reducing the frequency of such mistakes, we show that this novel architecture is indeed a better alternative. Our proposed system requires significantly lesser amounts of data, trai"},"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":"1806.00044","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2018-05-31T18:37:37Z","cross_cats_sorted":[],"title_canon_sha256":"b4ff48efcc8e9775eafb1b21a57a9507484c589ef88c482c716177dedd0a0568","abstract_canon_sha256":"1a5d3ff4c24357bb0dba6ff6f8f0583f7d3cd3396c8ae832d69e2ba23a4a3498"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:27.716615Z","signature_b64":"2ZSIAu0+C2xiZl0+bpNHGaI4BLdBbvhMGhkhzY4W9OoiqlEBYqjukhzUICVjJWhnN0R2gZZ7OnLaIOJW/d1rAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cbd66dba1334ba77e7d2eff5ce3d670c5df1c32b1038ab33e00eef03fda83856","last_reissued_at":"2026-05-17T23:49:27.716083Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:27.716083Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Text normalization using memory augmented neural networks","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aman Hussain, Subhojeet Pramanik","submitted_at":"2018-05-31T18:37:37Z","abstract_excerpt":"We perform text normalization, i.e. the transformation of words from the written to the spoken form, using a memory augmented neural network. With the addition of dynamic memory access and storage mechanism, we present a neural architecture that will serve as a language-agnostic text normalization system while avoiding the kind of unacceptable errors made by the LSTM-based recurrent neural networks. By successfully reducing the frequency of such mistakes, we show that this novel architecture is indeed a better alternative. Our proposed system requires significantly lesser amounts of data, trai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.00044","kind":"arxiv","version":3},"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":"1806.00044","created_at":"2026-05-17T23:49:27.716165+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.00044v3","created_at":"2026-05-17T23:49:27.716165+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.00044","created_at":"2026-05-17T23:49:27.716165+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZPLG3OQTGS5H","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZPLG3OQTGS5HPZ6S","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZPLG3OQT","created_at":"2026-05-18T12:33:07.085635+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/ZPLG3OQTGS5HPZ6S57244PLHBR","json":"https://pith.science/pith/ZPLG3OQTGS5HPZ6S57244PLHBR.json","graph_json":"https://pith.science/api/pith-number/ZPLG3OQTGS5HPZ6S57244PLHBR/graph.json","events_json":"https://pith.science/api/pith-number/ZPLG3OQTGS5HPZ6S57244PLHBR/events.json","paper":"https://pith.science/paper/ZPLG3OQT"},"agent_actions":{"view_html":"https://pith.science/pith/ZPLG3OQTGS5HPZ6S57244PLHBR","download_json":"https://pith.science/pith/ZPLG3OQTGS5HPZ6S57244PLHBR.json","view_paper":"https://pith.science/paper/ZPLG3OQT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.00044&json=true","fetch_graph":"https://pith.science/api/pith-number/ZPLG3OQTGS5HPZ6S57244PLHBR/graph.json","fetch_events":"https://pith.science/api/pith-number/ZPLG3OQTGS5HPZ6S57244PLHBR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZPLG3OQTGS5HPZ6S57244PLHBR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZPLG3OQTGS5HPZ6S57244PLHBR/action/storage_attestation","attest_author":"https://pith.science/pith/ZPLG3OQTGS5HPZ6S57244PLHBR/action/author_attestation","sign_citation":"https://pith.science/pith/ZPLG3OQTGS5HPZ6S57244PLHBR/action/citation_signature","submit_replication":"https://pith.science/pith/ZPLG3OQTGS5HPZ6S57244PLHBR/action/replication_record"}},"created_at":"2026-05-17T23:49:27.716165+00:00","updated_at":"2026-05-17T23:49:27.716165+00:00"}