{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:ROXNHI4VFSJTIL6UFKKXCKPJ3T","short_pith_number":"pith:ROXNHI4V","schema_version":"1.0","canonical_sha256":"8baed3a3952c93342fd42a957129e9dcf5fae02826ac60cd0def299a91948a7a","source":{"kind":"arxiv","id":"1809.01301","version":2},"attestation_state":"computed","paper":{"title":"BPE and CharCNNs for Translation of Morphology: A Cross-Lingual Comparison and Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kevin Duh, Pamela Shapiro","submitted_at":"2018-09-05T02:26:09Z","abstract_excerpt":"Neural Machine Translation (NMT) in low-resource settings and of morphologically rich languages is made difficult in part by data sparsity of vocabulary words. Several methods have been used to help reduce this sparsity, notably Byte-Pair Encoding (BPE) and a character-based CNN layer (charCNN). However, the charCNN has largely been neglected, possibly because it has only been compared to BPE rather than combined with it. We argue for a reconsideration of the charCNN, based on cross-lingual improvements on low-resource data. We translate from 8 languages into English, using a multi-way paralle"},"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":"1809.01301","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-05T02:26:09Z","cross_cats_sorted":[],"title_canon_sha256":"8a9532e32e35f9c2e6df80589442896d181c442ec7bd9029610defb28811d962","abstract_canon_sha256":"9cc691e88f0df5e5b30c11b3aa907e681f7153488c6eb8d6be39f4aaabed425a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:10.954752Z","signature_b64":"AWi4gA6vQCk/XmDjO70TFVdfk4QuvfzSacHzZfJzNpNfPFfy5lL4RwgTOuYZrbKlEq4X5rjxc6PBrzDnfvqSAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8baed3a3952c93342fd42a957129e9dcf5fae02826ac60cd0def299a91948a7a","last_reissued_at":"2026-05-18T00:06:10.954107Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:10.954107Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BPE and CharCNNs for Translation of Morphology: A Cross-Lingual Comparison and Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kevin Duh, Pamela Shapiro","submitted_at":"2018-09-05T02:26:09Z","abstract_excerpt":"Neural Machine Translation (NMT) in low-resource settings and of morphologically rich languages is made difficult in part by data sparsity of vocabulary words. Several methods have been used to help reduce this sparsity, notably Byte-Pair Encoding (BPE) and a character-based CNN layer (charCNN). However, the charCNN has largely been neglected, possibly because it has only been compared to BPE rather than combined with it. We argue for a reconsideration of the charCNN, based on cross-lingual improvements on low-resource data. We translate from 8 languages into English, using a multi-way paralle"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.01301","kind":"arxiv","version":2},"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":"1809.01301","created_at":"2026-05-18T00:06:10.954184+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.01301v2","created_at":"2026-05-18T00:06:10.954184+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.01301","created_at":"2026-05-18T00:06:10.954184+00:00"},{"alias_kind":"pith_short_12","alias_value":"ROXNHI4VFSJT","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_16","alias_value":"ROXNHI4VFSJTIL6U","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_8","alias_value":"ROXNHI4V","created_at":"2026-05-18T12:32:50.500415+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/ROXNHI4VFSJTIL6UFKKXCKPJ3T","json":"https://pith.science/pith/ROXNHI4VFSJTIL6UFKKXCKPJ3T.json","graph_json":"https://pith.science/api/pith-number/ROXNHI4VFSJTIL6UFKKXCKPJ3T/graph.json","events_json":"https://pith.science/api/pith-number/ROXNHI4VFSJTIL6UFKKXCKPJ3T/events.json","paper":"https://pith.science/paper/ROXNHI4V"},"agent_actions":{"view_html":"https://pith.science/pith/ROXNHI4VFSJTIL6UFKKXCKPJ3T","download_json":"https://pith.science/pith/ROXNHI4VFSJTIL6UFKKXCKPJ3T.json","view_paper":"https://pith.science/paper/ROXNHI4V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.01301&json=true","fetch_graph":"https://pith.science/api/pith-number/ROXNHI4VFSJTIL6UFKKXCKPJ3T/graph.json","fetch_events":"https://pith.science/api/pith-number/ROXNHI4VFSJTIL6UFKKXCKPJ3T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ROXNHI4VFSJTIL6UFKKXCKPJ3T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ROXNHI4VFSJTIL6UFKKXCKPJ3T/action/storage_attestation","attest_author":"https://pith.science/pith/ROXNHI4VFSJTIL6UFKKXCKPJ3T/action/author_attestation","sign_citation":"https://pith.science/pith/ROXNHI4VFSJTIL6UFKKXCKPJ3T/action/citation_signature","submit_replication":"https://pith.science/pith/ROXNHI4VFSJTIL6UFKKXCKPJ3T/action/replication_record"}},"created_at":"2026-05-18T00:06:10.954184+00:00","updated_at":"2026-05-18T00:06:10.954184+00:00"}