{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FNFXDBX726TXZMHSYHDC54FSZZ","short_pith_number":"pith:FNFXDBX7","schema_version":"1.0","canonical_sha256":"2b4b7186ffd7a77cb0f2c1c62ef0b2ce5d52b5255e592da55039527db6e4f2b8","source":{"kind":"arxiv","id":"2306.02242","version":1},"attestation_state":"computed","paper":{"title":"Extract and Attend: Improving Entity Translation in Neural Machine Translation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Junliang Guo, Rui Wang, Tao Qin, Tie-Yan Liu, Xu Tan, Yichong Leng, Zixin Zeng","submitted_at":"2023-06-04T03:05:25Z","abstract_excerpt":"While Neural Machine Translation(NMT) has achieved great progress in recent years, it still suffers from inaccurate translation of entities (e.g., person/organization name, location), due to the lack of entity training instances. When we humans encounter an unknown entity during translation, we usually first look up in a dictionary and then organize the entity translation together with the translations of other parts to form a smooth target sentence. Inspired by this translation process, we propose an Extract-and-Attend approach to enhance entity translation in NMT, where the translation candi"},"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":"2306.02242","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-04T03:05:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8bbfaee49157b0bf7f4d24506ff45303d44b8b3b72497cac10d825439857712a","abstract_canon_sha256":"24086784c6ae12400e4a144e0309812490d7f503b6337747d83e1647ba135c36"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:17:14.760957Z","signature_b64":"4GnvoTAmU3EoFWVlmmgoCq5ids5hbxPeFmQm4zlIJKdMDxL6M7dgeb9IHoiY3mm1czYgonwCrgyYpCbPCE1tAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b4b7186ffd7a77cb0f2c1c62ef0b2ce5d52b5255e592da55039527db6e4f2b8","last_reissued_at":"2026-07-05T06:17:14.760485Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:17:14.760485Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Extract and Attend: Improving Entity Translation in Neural Machine Translation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Junliang Guo, Rui Wang, Tao Qin, Tie-Yan Liu, Xu Tan, Yichong Leng, Zixin Zeng","submitted_at":"2023-06-04T03:05:25Z","abstract_excerpt":"While Neural Machine Translation(NMT) has achieved great progress in recent years, it still suffers from inaccurate translation of entities (e.g., person/organization name, location), due to the lack of entity training instances. When we humans encounter an unknown entity during translation, we usually first look up in a dictionary and then organize the entity translation together with the translations of other parts to form a smooth target sentence. Inspired by this translation process, we propose an Extract-and-Attend approach to enhance entity translation in NMT, where the translation candi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.02242","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/2306.02242/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":"2306.02242","created_at":"2026-07-05T06:17:14.760543+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.02242v1","created_at":"2026-07-05T06:17:14.760543+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.02242","created_at":"2026-07-05T06:17:14.760543+00:00"},{"alias_kind":"pith_short_12","alias_value":"FNFXDBX726TX","created_at":"2026-07-05T06:17:14.760543+00:00"},{"alias_kind":"pith_short_16","alias_value":"FNFXDBX726TXZMHS","created_at":"2026-07-05T06:17:14.760543+00:00"},{"alias_kind":"pith_short_8","alias_value":"FNFXDBX7","created_at":"2026-07-05T06:17:14.760543+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.18318","citing_title":"Enhancing Entity Aware Machine Translation with Multi-task Learning","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FNFXDBX726TXZMHSYHDC54FSZZ","json":"https://pith.science/pith/FNFXDBX726TXZMHSYHDC54FSZZ.json","graph_json":"https://pith.science/api/pith-number/FNFXDBX726TXZMHSYHDC54FSZZ/graph.json","events_json":"https://pith.science/api/pith-number/FNFXDBX726TXZMHSYHDC54FSZZ/events.json","paper":"https://pith.science/paper/FNFXDBX7"},"agent_actions":{"view_html":"https://pith.science/pith/FNFXDBX726TXZMHSYHDC54FSZZ","download_json":"https://pith.science/pith/FNFXDBX726TXZMHSYHDC54FSZZ.json","view_paper":"https://pith.science/paper/FNFXDBX7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.02242&json=true","fetch_graph":"https://pith.science/api/pith-number/FNFXDBX726TXZMHSYHDC54FSZZ/graph.json","fetch_events":"https://pith.science/api/pith-number/FNFXDBX726TXZMHSYHDC54FSZZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FNFXDBX726TXZMHSYHDC54FSZZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FNFXDBX726TXZMHSYHDC54FSZZ/action/storage_attestation","attest_author":"https://pith.science/pith/FNFXDBX726TXZMHSYHDC54FSZZ/action/author_attestation","sign_citation":"https://pith.science/pith/FNFXDBX726TXZMHSYHDC54FSZZ/action/citation_signature","submit_replication":"https://pith.science/pith/FNFXDBX726TXZMHSYHDC54FSZZ/action/replication_record"}},"created_at":"2026-07-05T06:17:14.760543+00:00","updated_at":"2026-07-05T06:17:14.760543+00:00"}