{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:NV3N6RY2G4C5BBN4QMHOOBJQ5E","short_pith_number":"pith:NV3N6RY2","schema_version":"1.0","canonical_sha256":"6d76df471a3705d085bc830ee70530e90c50d469d1e1722a59a4d277fb732116","source":{"kind":"arxiv","id":"1603.06147","version":4},"attestation_state":"computed","paper":{"title":"A Character-Level Decoder without Explicit Segmentation for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Junyoung Chung, Kyunghyun Cho, Yoshua Bengio","submitted_at":"2016-03-19T21:35:04Z","abstract_excerpt":"The existing machine translation systems, whether phrase-based or neural, have relied almost exclusively on word-level modelling with explicit segmentation. In this paper, we ask a fundamental question: can neural machine translation generate a character sequence without any explicit segmentation? To answer this question, we evaluate an attention-based encoder-decoder with a subword-level encoder and a character-level decoder on four language pairs--En-Cs, En-De, En-Ru and En-Fi-- using the parallel corpora from WMT'15. Our experiments show that the models with a character-level decoder outper"},"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":"1603.06147","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-03-19T21:35:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"29483c4d393ca7787406c608607853b4ddcb283923362559ab1d170b9f8a442e","abstract_canon_sha256":"bfa03b6c57db97932e0ccf89430b8f5d1d7b97a38e807fe3066d7f34c84501a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:12:12.031841Z","signature_b64":"ROGsHh061JAYcay/qEY7SXgElOLmmclLQwCLFqQvxYZs+Zex5eQsaChxBvIPU6whkCpRxW+lGOd9Nb9Dlo79Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d76df471a3705d085bc830ee70530e90c50d469d1e1722a59a4d277fb732116","last_reissued_at":"2026-05-18T01:12:12.031289Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:12:12.031289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Character-Level Decoder without Explicit Segmentation for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Junyoung Chung, Kyunghyun Cho, Yoshua Bengio","submitted_at":"2016-03-19T21:35:04Z","abstract_excerpt":"The existing machine translation systems, whether phrase-based or neural, have relied almost exclusively on word-level modelling with explicit segmentation. In this paper, we ask a fundamental question: can neural machine translation generate a character sequence without any explicit segmentation? To answer this question, we evaluate an attention-based encoder-decoder with a subword-level encoder and a character-level decoder on four language pairs--En-Cs, En-De, En-Ru and En-Fi-- using the parallel corpora from WMT'15. Our experiments show that the models with a character-level decoder outper"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.06147","kind":"arxiv","version":4},"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":"1603.06147","created_at":"2026-05-18T01:12:12.031393+00:00"},{"alias_kind":"arxiv_version","alias_value":"1603.06147v4","created_at":"2026-05-18T01:12:12.031393+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.06147","created_at":"2026-05-18T01:12:12.031393+00:00"},{"alias_kind":"pith_short_12","alias_value":"NV3N6RY2G4C5","created_at":"2026-05-18T12:30:36.002864+00:00"},{"alias_kind":"pith_short_16","alias_value":"NV3N6RY2G4C5BBN4","created_at":"2026-05-18T12:30:36.002864+00:00"},{"alias_kind":"pith_short_8","alias_value":"NV3N6RY2","created_at":"2026-05-18T12:30:36.002864+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.01300","citing_title":"Learning to Reformulate the Queries on the WEB","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"1609.08144","citing_title":"Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NV3N6RY2G4C5BBN4QMHOOBJQ5E","json":"https://pith.science/pith/NV3N6RY2G4C5BBN4QMHOOBJQ5E.json","graph_json":"https://pith.science/api/pith-number/NV3N6RY2G4C5BBN4QMHOOBJQ5E/graph.json","events_json":"https://pith.science/api/pith-number/NV3N6RY2G4C5BBN4QMHOOBJQ5E/events.json","paper":"https://pith.science/paper/NV3N6RY2"},"agent_actions":{"view_html":"https://pith.science/pith/NV3N6RY2G4C5BBN4QMHOOBJQ5E","download_json":"https://pith.science/pith/NV3N6RY2G4C5BBN4QMHOOBJQ5E.json","view_paper":"https://pith.science/paper/NV3N6RY2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1603.06147&json=true","fetch_graph":"https://pith.science/api/pith-number/NV3N6RY2G4C5BBN4QMHOOBJQ5E/graph.json","fetch_events":"https://pith.science/api/pith-number/NV3N6RY2G4C5BBN4QMHOOBJQ5E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NV3N6RY2G4C5BBN4QMHOOBJQ5E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NV3N6RY2G4C5BBN4QMHOOBJQ5E/action/storage_attestation","attest_author":"https://pith.science/pith/NV3N6RY2G4C5BBN4QMHOOBJQ5E/action/author_attestation","sign_citation":"https://pith.science/pith/NV3N6RY2G4C5BBN4QMHOOBJQ5E/action/citation_signature","submit_replication":"https://pith.science/pith/NV3N6RY2G4C5BBN4QMHOOBJQ5E/action/replication_record"}},"created_at":"2026-05-18T01:12:12.031393+00:00","updated_at":"2026-05-18T01:12:12.031393+00:00"}