{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:TJHO2P7WRC745MMC4PBY6PORFK","short_pith_number":"pith:TJHO2P7W","schema_version":"1.0","canonical_sha256":"9a4eed3ff688bfceb182e3c38f3dd12abd9dc2a742033890443f3be804f7bd34","source":{"kind":"arxiv","id":"1810.07391","version":1},"attestation_state":"computed","paper":{"title":"Sequence to Sequence Mixture Model for Diverse Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gholamreza Haffari, Mohammad Norouzi, Xuanli He","submitted_at":"2018-10-17T05:42:49Z","abstract_excerpt":"Sequence to sequence (SEQ2SEQ) models often lack diversity in their generated translations. This can be attributed to the limitation of SEQ2SEQ models in capturing lexical and syntactic variations in a parallel corpus resulting from different styles, genres, topics, or ambiguity of the translation process. In this paper, we develop a novel sequence to sequence mixture (S2SMIX) model that improves both translation diversity and quality by adopting a committee of specialized translation models rather than a single translation model. Each mixture component selects its own training dataset via opt"},"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":"1810.07391","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-17T05:42:49Z","cross_cats_sorted":[],"title_canon_sha256":"61662ed4c42c014a3d191de9830c480b6a3de34b5c5ccd320f5884137fc3b5e5","abstract_canon_sha256":"f5635013eb13895c42aae8098e024539c28e8ee6bb7265bd560d7744149183c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:56.534988Z","signature_b64":"p2cnhzOlhdauWiCl1wmoA5KMHWD9SeMKjQJVd1KEIF9HxDi3N1ZZePiKlJgmm6vijkOJKbduStu3Yz5wSwadCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a4eed3ff688bfceb182e3c38f3dd12abd9dc2a742033890443f3be804f7bd34","last_reissued_at":"2026-05-18T00:02:56.534222Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:56.534222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sequence to Sequence Mixture Model for Diverse Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gholamreza Haffari, Mohammad Norouzi, Xuanli He","submitted_at":"2018-10-17T05:42:49Z","abstract_excerpt":"Sequence to sequence (SEQ2SEQ) models often lack diversity in their generated translations. This can be attributed to the limitation of SEQ2SEQ models in capturing lexical and syntactic variations in a parallel corpus resulting from different styles, genres, topics, or ambiguity of the translation process. In this paper, we develop a novel sequence to sequence mixture (S2SMIX) model that improves both translation diversity and quality by adopting a committee of specialized translation models rather than a single translation model. Each mixture component selects its own training dataset via opt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.07391","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":""},"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":"1810.07391","created_at":"2026-05-18T00:02:56.534341+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.07391v1","created_at":"2026-05-18T00:02:56.534341+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.07391","created_at":"2026-05-18T00:02:56.534341+00:00"},{"alias_kind":"pith_short_12","alias_value":"TJHO2P7WRC74","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_16","alias_value":"TJHO2P7WRC745MMC","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_8","alias_value":"TJHO2P7W","created_at":"2026-05-18T12:32:53.628368+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/TJHO2P7WRC745MMC4PBY6PORFK","json":"https://pith.science/pith/TJHO2P7WRC745MMC4PBY6PORFK.json","graph_json":"https://pith.science/api/pith-number/TJHO2P7WRC745MMC4PBY6PORFK/graph.json","events_json":"https://pith.science/api/pith-number/TJHO2P7WRC745MMC4PBY6PORFK/events.json","paper":"https://pith.science/paper/TJHO2P7W"},"agent_actions":{"view_html":"https://pith.science/pith/TJHO2P7WRC745MMC4PBY6PORFK","download_json":"https://pith.science/pith/TJHO2P7WRC745MMC4PBY6PORFK.json","view_paper":"https://pith.science/paper/TJHO2P7W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.07391&json=true","fetch_graph":"https://pith.science/api/pith-number/TJHO2P7WRC745MMC4PBY6PORFK/graph.json","fetch_events":"https://pith.science/api/pith-number/TJHO2P7WRC745MMC4PBY6PORFK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TJHO2P7WRC745MMC4PBY6PORFK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TJHO2P7WRC745MMC4PBY6PORFK/action/storage_attestation","attest_author":"https://pith.science/pith/TJHO2P7WRC745MMC4PBY6PORFK/action/author_attestation","sign_citation":"https://pith.science/pith/TJHO2P7WRC745MMC4PBY6PORFK/action/citation_signature","submit_replication":"https://pith.science/pith/TJHO2P7WRC745MMC4PBY6PORFK/action/replication_record"}},"created_at":"2026-05-18T00:02:56.534341+00:00","updated_at":"2026-05-18T00:02:56.534341+00:00"}