{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:6XQAD74MN4HNQX4TFKCWBBABSL","short_pith_number":"pith:6XQAD74M","schema_version":"1.0","canonical_sha256":"f5e001ff8c6f0ed85f932a8560840192cb015366920b89a0a19cd47ab745cc5a","source":{"kind":"arxiv","id":"1412.2007","version":2},"attestation_state":"computed","paper":{"title":"On Using Very Large Target Vocabulary for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kyunghyun Cho, Roland Memisevic, S\\'ebastien Jean, Yoshua Bengio","submitted_at":"2014-12-05T14:26:27Z","abstract_excerpt":"Neural machine translation, a recently proposed approach to machine translation based purely on neural networks, has shown promising results compared to the existing approaches such as phrase-based statistical machine translation. Despite its recent success, neural machine translation has its limitation in handling a larger vocabulary, as training complexity as well as decoding complexity increase proportionally to the number of target words. In this paper, we propose a method that allows us to use a very large target vocabulary without increasing training complexity, based on importance sampl"},"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":"1412.2007","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-12-05T14:26:27Z","cross_cats_sorted":[],"title_canon_sha256":"8f788f31ffbd00d8bf74528c0ff46fd93b00e1017b63b3a07fd7ed1222b9d047","abstract_canon_sha256":"553eaa85d51bb837faae92735086b7f1a803970bea8131642d4de1ea35d46f66"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:21:26.433870Z","signature_b64":"s9keuP8hrd0uUg6B8hztzqBHsl4TBVGh7qQBIda+MSV+dMZu1zdFEQ9X4GPDoRFAC/WjUGpBdDLq88sV0axkCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5e001ff8c6f0ed85f932a8560840192cb015366920b89a0a19cd47ab745cc5a","last_reissued_at":"2026-05-18T02:21:26.433143Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:21:26.433143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Using Very Large Target Vocabulary for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kyunghyun Cho, Roland Memisevic, S\\'ebastien Jean, Yoshua Bengio","submitted_at":"2014-12-05T14:26:27Z","abstract_excerpt":"Neural machine translation, a recently proposed approach to machine translation based purely on neural networks, has shown promising results compared to the existing approaches such as phrase-based statistical machine translation. Despite its recent success, neural machine translation has its limitation in handling a larger vocabulary, as training complexity as well as decoding complexity increase proportionally to the number of target words. In this paper, we propose a method that allows us to use a very large target vocabulary without increasing training complexity, based on importance sampl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1412.2007","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":"1412.2007","created_at":"2026-05-18T02:21:26.433248+00:00"},{"alias_kind":"arxiv_version","alias_value":"1412.2007v2","created_at":"2026-05-18T02:21:26.433248+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.2007","created_at":"2026-05-18T02:21:26.433248+00:00"},{"alias_kind":"pith_short_12","alias_value":"6XQAD74MN4HN","created_at":"2026-05-18T12:28:16.859392+00:00"},{"alias_kind":"pith_short_16","alias_value":"6XQAD74MN4HNQX4T","created_at":"2026-05-18T12:28:16.859392+00:00"},{"alias_kind":"pith_short_8","alias_value":"6XQAD74M","created_at":"2026-05-18T12:28:16.859392+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2104.14294","citing_title":"Emerging Properties in Self-Supervised Vision Transformers","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2309.16588","citing_title":"Vision Transformers Need Registers","ref_index":167,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6XQAD74MN4HNQX4TFKCWBBABSL","json":"https://pith.science/pith/6XQAD74MN4HNQX4TFKCWBBABSL.json","graph_json":"https://pith.science/api/pith-number/6XQAD74MN4HNQX4TFKCWBBABSL/graph.json","events_json":"https://pith.science/api/pith-number/6XQAD74MN4HNQX4TFKCWBBABSL/events.json","paper":"https://pith.science/paper/6XQAD74M"},"agent_actions":{"view_html":"https://pith.science/pith/6XQAD74MN4HNQX4TFKCWBBABSL","download_json":"https://pith.science/pith/6XQAD74MN4HNQX4TFKCWBBABSL.json","view_paper":"https://pith.science/paper/6XQAD74M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1412.2007&json=true","fetch_graph":"https://pith.science/api/pith-number/6XQAD74MN4HNQX4TFKCWBBABSL/graph.json","fetch_events":"https://pith.science/api/pith-number/6XQAD74MN4HNQX4TFKCWBBABSL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6XQAD74MN4HNQX4TFKCWBBABSL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6XQAD74MN4HNQX4TFKCWBBABSL/action/storage_attestation","attest_author":"https://pith.science/pith/6XQAD74MN4HNQX4TFKCWBBABSL/action/author_attestation","sign_citation":"https://pith.science/pith/6XQAD74MN4HNQX4TFKCWBBABSL/action/citation_signature","submit_replication":"https://pith.science/pith/6XQAD74MN4HNQX4TFKCWBBABSL/action/replication_record"}},"created_at":"2026-05-18T02:21:26.433248+00:00","updated_at":"2026-05-18T02:21:26.433248+00:00"}