{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:EMHDYVJQHPLHKPRQ3ETF3H4JYF","short_pith_number":"pith:EMHDYVJQ","schema_version":"1.0","canonical_sha256":"230e3c55303bd6753e30d9265d9f89c1577051a0cc0aa67fc6c2b3908806b1ed","source":{"kind":"arxiv","id":"1601.04811","version":6},"attestation_state":"computed","paper":{"title":"Modeling Coverage for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hang Li, Xiaohua Liu, Yang Liu, Zhaopeng Tu, Zhengdong Lu","submitted_at":"2016-01-19T07:09:38Z","abstract_excerpt":"Attention mechanism has enhanced state-of-the-art Neural Machine Translation (NMT) by jointly learning to align and translate. It tends to ignore past alignment information, however, which often leads to over-translation and under-translation. To address this problem, we propose coverage-based NMT in this paper. We maintain a coverage vector to keep track of the attention history. The coverage vector is fed to the attention model to help adjust future attention, which lets NMT system to consider more about untranslated source words. Experiments show that the proposed approach significantly imp"},"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":"1601.04811","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-01-19T07:09:38Z","cross_cats_sorted":[],"title_canon_sha256":"fc972c0666bc2401ff4b03e1e43f61468ffb8b5083e53a54ddad82ce0b57a500","abstract_canon_sha256":"34fd0d7d3c5e03b636e4955e447b7f4869b11e95909eb2c5ff797258b5540d13"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:09:41.875803Z","signature_b64":"EOEK2Fq/st0vwnbrx0F64QO/QCGy68ClpJeZanxA9oIapKnUFPhI1xtyzTGolcB17r7vQbv/iqShokJzGVauDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"230e3c55303bd6753e30d9265d9f89c1577051a0cc0aa67fc6c2b3908806b1ed","last_reissued_at":"2026-05-18T01:09:41.875153Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:09:41.875153Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Modeling Coverage for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hang Li, Xiaohua Liu, Yang Liu, Zhaopeng Tu, Zhengdong Lu","submitted_at":"2016-01-19T07:09:38Z","abstract_excerpt":"Attention mechanism has enhanced state-of-the-art Neural Machine Translation (NMT) by jointly learning to align and translate. It tends to ignore past alignment information, however, which often leads to over-translation and under-translation. To address this problem, we propose coverage-based NMT in this paper. We maintain a coverage vector to keep track of the attention history. The coverage vector is fed to the attention model to help adjust future attention, which lets NMT system to consider more about untranslated source words. Experiments show that the proposed approach significantly imp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1601.04811","kind":"arxiv","version":6},"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":"1601.04811","created_at":"2026-05-18T01:09:41.875239+00:00"},{"alias_kind":"arxiv_version","alias_value":"1601.04811v6","created_at":"2026-05-18T01:09:41.875239+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1601.04811","created_at":"2026-05-18T01:09:41.875239+00:00"},{"alias_kind":"pith_short_12","alias_value":"EMHDYVJQHPLH","created_at":"2026-05-18T12:30:12.583610+00:00"},{"alias_kind":"pith_short_16","alias_value":"EMHDYVJQHPLHKPRQ","created_at":"2026-05-18T12:30:12.583610+00:00"},{"alias_kind":"pith_short_8","alias_value":"EMHDYVJQ","created_at":"2026-05-18T12:30:12.583610+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.00430","citing_title":"MFH: Marrying Frequency Domain with Handwritten Mathematical Expression Recognition","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EMHDYVJQHPLHKPRQ3ETF3H4JYF","json":"https://pith.science/pith/EMHDYVJQHPLHKPRQ3ETF3H4JYF.json","graph_json":"https://pith.science/api/pith-number/EMHDYVJQHPLHKPRQ3ETF3H4JYF/graph.json","events_json":"https://pith.science/api/pith-number/EMHDYVJQHPLHKPRQ3ETF3H4JYF/events.json","paper":"https://pith.science/paper/EMHDYVJQ"},"agent_actions":{"view_html":"https://pith.science/pith/EMHDYVJQHPLHKPRQ3ETF3H4JYF","download_json":"https://pith.science/pith/EMHDYVJQHPLHKPRQ3ETF3H4JYF.json","view_paper":"https://pith.science/paper/EMHDYVJQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1601.04811&json=true","fetch_graph":"https://pith.science/api/pith-number/EMHDYVJQHPLHKPRQ3ETF3H4JYF/graph.json","fetch_events":"https://pith.science/api/pith-number/EMHDYVJQHPLHKPRQ3ETF3H4JYF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EMHDYVJQHPLHKPRQ3ETF3H4JYF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EMHDYVJQHPLHKPRQ3ETF3H4JYF/action/storage_attestation","attest_author":"https://pith.science/pith/EMHDYVJQHPLHKPRQ3ETF3H4JYF/action/author_attestation","sign_citation":"https://pith.science/pith/EMHDYVJQHPLHKPRQ3ETF3H4JYF/action/citation_signature","submit_replication":"https://pith.science/pith/EMHDYVJQHPLHKPRQ3ETF3H4JYF/action/replication_record"}},"created_at":"2026-05-18T01:09:41.875239+00:00","updated_at":"2026-05-18T01:09:41.875239+00:00"}