{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:WE2B4J2ENNRT7C6NSV23VNK4AP","short_pith_number":"pith:WE2B4J2E","schema_version":"1.0","canonical_sha256":"b1341e27446b633f8bcd9575bab55c03c280c2f2a9d915c5d0d6a72fb9fbbaa1","source":{"kind":"arxiv","id":"1911.09333","version":1},"attestation_state":"computed","paper":{"title":"Generating Diverse Translation by Manipulating Multi-Head Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hao-Ran Wei, Jiajun Chen, Shujian Huang, Xin-Yu Dai, Zewei Sun","submitted_at":"2019-11-21T08:22:07Z","abstract_excerpt":"Transformer model has been widely used on machine translation tasks and obtained state-of-the-art results. In this paper, we report an interesting phenomenon in its encoder-decoder multi-head attention: different attention heads of the final decoder layer align to different word translation candidates. We empirically verify this discovery and propose a method to generate diverse translations by manipulating heads. Furthermore, we make use of these diverse translations with the back-translation technique for better data augmentation. Experiment results show that our method generates diverse tra"},"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":"1911.09333","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-21T08:22:07Z","cross_cats_sorted":[],"title_canon_sha256":"c86e296a97008f23d4c880d69f0a71d7b44f0e2fad807733f76355a9b9fa0b72","abstract_canon_sha256":"d17d71b708a51d38c06de631e7eaeda340008df632dce8a8c002127c26eaad05"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:20:59.393870Z","signature_b64":"9B/N6atinBrI5JOQnTpQkNdIM9yvytKWT71F0etVqPaU87wy14YbZoxW+CMOEWN3NGL0x7nDzU1MLK+IjE/6Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1341e27446b633f8bcd9575bab55c03c280c2f2a9d915c5d0d6a72fb9fbbaa1","last_reissued_at":"2026-07-05T00:20:59.393406Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:20:59.393406Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generating Diverse Translation by Manipulating Multi-Head Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hao-Ran Wei, Jiajun Chen, Shujian Huang, Xin-Yu Dai, Zewei Sun","submitted_at":"2019-11-21T08:22:07Z","abstract_excerpt":"Transformer model has been widely used on machine translation tasks and obtained state-of-the-art results. In this paper, we report an interesting phenomenon in its encoder-decoder multi-head attention: different attention heads of the final decoder layer align to different word translation candidates. We empirically verify this discovery and propose a method to generate diverse translations by manipulating heads. Furthermore, we make use of these diverse translations with the back-translation technique for better data augmentation. Experiment results show that our method generates diverse tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.09333","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1911.09333/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"1911.09333","created_at":"2026-07-05T00:20:59.393457+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.09333v1","created_at":"2026-07-05T00:20:59.393457+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.09333","created_at":"2026-07-05T00:20:59.393457+00:00"},{"alias_kind":"pith_short_12","alias_value":"WE2B4J2ENNRT","created_at":"2026-07-05T00:20:59.393457+00:00"},{"alias_kind":"pith_short_16","alias_value":"WE2B4J2ENNRT7C6N","created_at":"2026-07-05T00:20:59.393457+00:00"},{"alias_kind":"pith_short_8","alias_value":"WE2B4J2E","created_at":"2026-07-05T00:20:59.393457+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/WE2B4J2ENNRT7C6NSV23VNK4AP","json":"https://pith.science/pith/WE2B4J2ENNRT7C6NSV23VNK4AP.json","graph_json":"https://pith.science/api/pith-number/WE2B4J2ENNRT7C6NSV23VNK4AP/graph.json","events_json":"https://pith.science/api/pith-number/WE2B4J2ENNRT7C6NSV23VNK4AP/events.json","paper":"https://pith.science/paper/WE2B4J2E"},"agent_actions":{"view_html":"https://pith.science/pith/WE2B4J2ENNRT7C6NSV23VNK4AP","download_json":"https://pith.science/pith/WE2B4J2ENNRT7C6NSV23VNK4AP.json","view_paper":"https://pith.science/paper/WE2B4J2E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.09333&json=true","fetch_graph":"https://pith.science/api/pith-number/WE2B4J2ENNRT7C6NSV23VNK4AP/graph.json","fetch_events":"https://pith.science/api/pith-number/WE2B4J2ENNRT7C6NSV23VNK4AP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WE2B4J2ENNRT7C6NSV23VNK4AP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WE2B4J2ENNRT7C6NSV23VNK4AP/action/storage_attestation","attest_author":"https://pith.science/pith/WE2B4J2ENNRT7C6NSV23VNK4AP/action/author_attestation","sign_citation":"https://pith.science/pith/WE2B4J2ENNRT7C6NSV23VNK4AP/action/citation_signature","submit_replication":"https://pith.science/pith/WE2B4J2ENNRT7C6NSV23VNK4AP/action/replication_record"}},"created_at":"2026-07-05T00:20:59.393457+00:00","updated_at":"2026-07-05T00:20:59.393457+00:00"}