{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:5EOUNUCBA5VKDYHJ4F3OO7ZRIH","short_pith_number":"pith:5EOUNUCB","schema_version":"1.0","canonical_sha256":"e91d46d041076aa1e0e9e176e77f3141ceb05fde2076abb5d035fa631bc082ed","source":{"kind":"arxiv","id":"1710.03476","version":1},"attestation_state":"computed","paper":{"title":"MoNoise: Modeling Noise Using a Modular Normalization System","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gertjan van Noord, Rob van der Goot","submitted_at":"2017-10-10T09:41:46Z","abstract_excerpt":"We propose MoNoise: a normalization model focused on generalizability and efficiency, it aims at being easily reusable and adaptable. Normalization is the task of translating texts from a non- canonical domain to a more canonical domain, in our case: from social media data to standard language. Our proposed model is based on a modular candidate generation in which each module is responsible for a different type of normalization action. The most important generation modules are a spelling correction system and a word embeddings module. Depending on the definition of the normalization task, a st"},"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":"1710.03476","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-10-10T09:41:46Z","cross_cats_sorted":[],"title_canon_sha256":"5298c3bc202c4a0a72c92e01798d075cfac5fb7146dadc3a20eb9330ae8285e9","abstract_canon_sha256":"3388ae4356dea99520c2a14a2862b5532c2a1fac92d66db5ac3bfdcfffef25f6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:33:11.812529Z","signature_b64":"moogmjCbfz9bcnnZrgI8d2I2LqkNxcQLIXmD+KCZNfF2OZqlEI5FQLIRtSgPK9oorXS6DmlRcPYBw/Z66VGXBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e91d46d041076aa1e0e9e176e77f3141ceb05fde2076abb5d035fa631bc082ed","last_reissued_at":"2026-05-18T00:33:11.812047Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:33:11.812047Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MoNoise: Modeling Noise Using a Modular Normalization System","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gertjan van Noord, Rob van der Goot","submitted_at":"2017-10-10T09:41:46Z","abstract_excerpt":"We propose MoNoise: a normalization model focused on generalizability and efficiency, it aims at being easily reusable and adaptable. Normalization is the task of translating texts from a non- canonical domain to a more canonical domain, in our case: from social media data to standard language. Our proposed model is based on a modular candidate generation in which each module is responsible for a different type of normalization action. The most important generation modules are a spelling correction system and a word embeddings module. Depending on the definition of the normalization task, a st"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.03476","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":"1710.03476","created_at":"2026-05-18T00:33:11.812115+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.03476v1","created_at":"2026-05-18T00:33:11.812115+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.03476","created_at":"2026-05-18T00:33:11.812115+00:00"},{"alias_kind":"pith_short_12","alias_value":"5EOUNUCBA5VK","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_16","alias_value":"5EOUNUCBA5VKDYHJ","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_8","alias_value":"5EOUNUCB","created_at":"2026-05-18T12:31:00.734936+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/5EOUNUCBA5VKDYHJ4F3OO7ZRIH","json":"https://pith.science/pith/5EOUNUCBA5VKDYHJ4F3OO7ZRIH.json","graph_json":"https://pith.science/api/pith-number/5EOUNUCBA5VKDYHJ4F3OO7ZRIH/graph.json","events_json":"https://pith.science/api/pith-number/5EOUNUCBA5VKDYHJ4F3OO7ZRIH/events.json","paper":"https://pith.science/paper/5EOUNUCB"},"agent_actions":{"view_html":"https://pith.science/pith/5EOUNUCBA5VKDYHJ4F3OO7ZRIH","download_json":"https://pith.science/pith/5EOUNUCBA5VKDYHJ4F3OO7ZRIH.json","view_paper":"https://pith.science/paper/5EOUNUCB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.03476&json=true","fetch_graph":"https://pith.science/api/pith-number/5EOUNUCBA5VKDYHJ4F3OO7ZRIH/graph.json","fetch_events":"https://pith.science/api/pith-number/5EOUNUCBA5VKDYHJ4F3OO7ZRIH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5EOUNUCBA5VKDYHJ4F3OO7ZRIH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5EOUNUCBA5VKDYHJ4F3OO7ZRIH/action/storage_attestation","attest_author":"https://pith.science/pith/5EOUNUCBA5VKDYHJ4F3OO7ZRIH/action/author_attestation","sign_citation":"https://pith.science/pith/5EOUNUCBA5VKDYHJ4F3OO7ZRIH/action/citation_signature","submit_replication":"https://pith.science/pith/5EOUNUCBA5VKDYHJ4F3OO7ZRIH/action/replication_record"}},"created_at":"2026-05-18T00:33:11.812115+00:00","updated_at":"2026-05-18T00:33:11.812115+00:00"}