{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:HMSPSW7ZO77FLONUDIVZR5MI6V","short_pith_number":"pith:HMSPSW7Z","schema_version":"1.0","canonical_sha256":"3b24f95bf977fe55b9b41a2b98f588f54e11ba48f017712bcd697a0a39bf6a6d","source":{"kind":"arxiv","id":"1604.00788","version":2},"attestation_state":"computed","paper":{"title":"Achieving Open Vocabulary Neural Machine Translation with Hybrid Word-Character Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Christopher D. Manning, Minh-Thang Luong","submitted_at":"2016-04-04T09:30:54Z","abstract_excerpt":"Nearly all previous work on neural machine translation (NMT) has used quite restricted vocabularies, perhaps with a subsequent method to patch in unknown words. This paper presents a novel word-character solution to achieving open vocabulary NMT. We build hybrid systems that translate mostly at the word level and consult the character components for rare words. Our character-level recurrent neural networks compute source word representations and recover unknown target words when needed. The twofold advantage of such a hybrid approach is that it is much faster and easier to train than character"},"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":"1604.00788","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-04-04T09:30:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"697afa20e5a6dad0938d768881bc8a76b75769bee6678b872e1b2470d0dbcafe","abstract_canon_sha256":"c4416ad2aed26f4b5f46522290cbf524aea44b51fd828b95e4808aa126366630"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:11:58.954341Z","signature_b64":"EPh1cKEVz9QL292zqKM+vK+PUg90t90NinwuWLGfV6vq8l0HUcZCxTuFF2iXdJ/tOFPzgx9uOhV2kKrMeiaqCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b24f95bf977fe55b9b41a2b98f588f54e11ba48f017712bcd697a0a39bf6a6d","last_reissued_at":"2026-05-18T01:11:58.953970Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:11:58.953970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Achieving Open Vocabulary Neural Machine Translation with Hybrid Word-Character Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Christopher D. Manning, Minh-Thang Luong","submitted_at":"2016-04-04T09:30:54Z","abstract_excerpt":"Nearly all previous work on neural machine translation (NMT) has used quite restricted vocabularies, perhaps with a subsequent method to patch in unknown words. This paper presents a novel word-character solution to achieving open vocabulary NMT. We build hybrid systems that translate mostly at the word level and consult the character components for rare words. Our character-level recurrent neural networks compute source word representations and recover unknown target words when needed. The twofold advantage of such a hybrid approach is that it is much faster and easier to train than character"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.00788","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":"1604.00788","created_at":"2026-05-18T01:11:58.954028+00:00"},{"alias_kind":"arxiv_version","alias_value":"1604.00788v2","created_at":"2026-05-18T01:11:58.954028+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.00788","created_at":"2026-05-18T01:11:58.954028+00:00"},{"alias_kind":"pith_short_12","alias_value":"HMSPSW7ZO77F","created_at":"2026-05-18T12:30:19.053100+00:00"},{"alias_kind":"pith_short_16","alias_value":"HMSPSW7ZO77FLONU","created_at":"2026-05-18T12:30:19.053100+00:00"},{"alias_kind":"pith_short_8","alias_value":"HMSPSW7Z","created_at":"2026-05-18T12:30:19.053100+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.05019","citing_title":"Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges","ref_index":15,"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":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HMSPSW7ZO77FLONUDIVZR5MI6V","json":"https://pith.science/pith/HMSPSW7ZO77FLONUDIVZR5MI6V.json","graph_json":"https://pith.science/api/pith-number/HMSPSW7ZO77FLONUDIVZR5MI6V/graph.json","events_json":"https://pith.science/api/pith-number/HMSPSW7ZO77FLONUDIVZR5MI6V/events.json","paper":"https://pith.science/paper/HMSPSW7Z"},"agent_actions":{"view_html":"https://pith.science/pith/HMSPSW7ZO77FLONUDIVZR5MI6V","download_json":"https://pith.science/pith/HMSPSW7ZO77FLONUDIVZR5MI6V.json","view_paper":"https://pith.science/paper/HMSPSW7Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1604.00788&json=true","fetch_graph":"https://pith.science/api/pith-number/HMSPSW7ZO77FLONUDIVZR5MI6V/graph.json","fetch_events":"https://pith.science/api/pith-number/HMSPSW7ZO77FLONUDIVZR5MI6V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HMSPSW7ZO77FLONUDIVZR5MI6V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HMSPSW7ZO77FLONUDIVZR5MI6V/action/storage_attestation","attest_author":"https://pith.science/pith/HMSPSW7ZO77FLONUDIVZR5MI6V/action/author_attestation","sign_citation":"https://pith.science/pith/HMSPSW7ZO77FLONUDIVZR5MI6V/action/citation_signature","submit_replication":"https://pith.science/pith/HMSPSW7ZO77FLONUDIVZR5MI6V/action/replication_record"}},"created_at":"2026-05-18T01:11:58.954028+00:00","updated_at":"2026-05-18T01:11:58.954028+00:00"}