{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:JFSGTZY2PK6APNRGMTZLBOQQFN","short_pith_number":"pith:JFSGTZY2","schema_version":"1.0","canonical_sha256":"496469e71a7abc07b62664f2b0ba102b508af6abe678ab9b9f89f74bed159355","source":{"kind":"arxiv","id":"1805.04813","version":2},"attestation_state":"computed","paper":{"title":"Triangular Architecture for Rare Language Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ming Zhou, Mu Li, Shuai Ma, Shujie Liu, Shuo Ren, Wenhu Chen","submitted_at":"2018-05-13T03:35:09Z","abstract_excerpt":"Neural Machine Translation (NMT) performs poor on the low-resource language pair $(X,Z)$, especially when $Z$ is a rare language. By introducing another rich language $Y$, we propose a novel triangular training architecture (TA-NMT) to leverage bilingual data $(Y,Z)$ (may be small) and $(X,Y)$ (can be rich) to improve the translation performance of low-resource pairs. In this triangular architecture, $Z$ is taken as the intermediate latent variable, and translation models of $Z$ are jointly optimized with a unified bidirectional EM algorithm under the goal of maximizing the translation likelih"},"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":"1805.04813","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-13T03:35:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"38ab568a0ce119a974b7e2ad930ee22a58617a981b58e4d1505787970e2c0b2e","abstract_canon_sha256":"8e21f499ee213c58c03047c1a77f660da106c4306709511371bf03c54d488fa9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:10:59.608300Z","signature_b64":"RvOJrwRNTZ3IQS9eZPKQ3lOHQqTRg52hEKLo2WA84sWdTIcl036Biu+1nvs3HbFeR78+VFC7zFN9NofgwooPCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"496469e71a7abc07b62664f2b0ba102b508af6abe678ab9b9f89f74bed159355","last_reissued_at":"2026-05-18T00:10:59.607534Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:10:59.607534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Triangular Architecture for Rare Language Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ming Zhou, Mu Li, Shuai Ma, Shujie Liu, Shuo Ren, Wenhu Chen","submitted_at":"2018-05-13T03:35:09Z","abstract_excerpt":"Neural Machine Translation (NMT) performs poor on the low-resource language pair $(X,Z)$, especially when $Z$ is a rare language. By introducing another rich language $Y$, we propose a novel triangular training architecture (TA-NMT) to leverage bilingual data $(Y,Z)$ (may be small) and $(X,Y)$ (can be rich) to improve the translation performance of low-resource pairs. In this triangular architecture, $Z$ is taken as the intermediate latent variable, and translation models of $Z$ are jointly optimized with a unified bidirectional EM algorithm under the goal of maximizing the translation likelih"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.04813","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":"1805.04813","created_at":"2026-05-18T00:10:59.607670+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.04813v2","created_at":"2026-05-18T00:10:59.607670+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.04813","created_at":"2026-05-18T00:10:59.607670+00:00"},{"alias_kind":"pith_short_12","alias_value":"JFSGTZY2PK6A","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_16","alias_value":"JFSGTZY2PK6APNRG","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_8","alias_value":"JFSGTZY2","created_at":"2026-05-18T12:32:31.084164+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/JFSGTZY2PK6APNRGMTZLBOQQFN","json":"https://pith.science/pith/JFSGTZY2PK6APNRGMTZLBOQQFN.json","graph_json":"https://pith.science/api/pith-number/JFSGTZY2PK6APNRGMTZLBOQQFN/graph.json","events_json":"https://pith.science/api/pith-number/JFSGTZY2PK6APNRGMTZLBOQQFN/events.json","paper":"https://pith.science/paper/JFSGTZY2"},"agent_actions":{"view_html":"https://pith.science/pith/JFSGTZY2PK6APNRGMTZLBOQQFN","download_json":"https://pith.science/pith/JFSGTZY2PK6APNRGMTZLBOQQFN.json","view_paper":"https://pith.science/paper/JFSGTZY2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.04813&json=true","fetch_graph":"https://pith.science/api/pith-number/JFSGTZY2PK6APNRGMTZLBOQQFN/graph.json","fetch_events":"https://pith.science/api/pith-number/JFSGTZY2PK6APNRGMTZLBOQQFN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JFSGTZY2PK6APNRGMTZLBOQQFN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JFSGTZY2PK6APNRGMTZLBOQQFN/action/storage_attestation","attest_author":"https://pith.science/pith/JFSGTZY2PK6APNRGMTZLBOQQFN/action/author_attestation","sign_citation":"https://pith.science/pith/JFSGTZY2PK6APNRGMTZLBOQQFN/action/citation_signature","submit_replication":"https://pith.science/pith/JFSGTZY2PK6APNRGMTZLBOQQFN/action/replication_record"}},"created_at":"2026-05-18T00:10:59.607670+00:00","updated_at":"2026-05-18T00:10:59.607670+00:00"}