{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HMPX3OPUDONQSOA5F24VQ5JVSI","short_pith_number":"pith:HMPX3OPU","schema_version":"1.0","canonical_sha256":"3b1f7db9f41b9b09381d2eb95875359211d211cf827cbcf0b84858de180d4a50","source":{"kind":"arxiv","id":"2502.04537","version":1},"attestation_state":"computed","paper":{"title":"Multilingual Non-Autoregressive Machine Translation without Knowledge Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenyang Huang, Fei Huang, Hao Zhou, Lili Mou, Osmar R. Za\\\"iane, Zaixiang Zheng","submitted_at":"2025-02-06T22:16:28Z","abstract_excerpt":"Multilingual neural machine translation (MNMT) aims at using one single model for multiple translation directions. Recent work applies non-autoregressive Transformers to improve the efficiency of MNMT, but requires expensive knowledge distillation (KD) processes. To this end, we propose an M-DAT approach to non-autoregressive multilingual machine translation. Our system leverages the recent advance of the directed acyclic Transformer (DAT), which does not require KD. We further propose a pivot back-translation (PivotBT) approach to improve the generalization to unseen translation directions. E"},"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":"2502.04537","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-06T22:16:28Z","cross_cats_sorted":[],"title_canon_sha256":"8d859b7b013473fe688217e0e0fd8ec2cc7a728ab0ef7a2160b29d6f87c4cb0b","abstract_canon_sha256":"6b5949bfbcca699aa2c3848acb7d3f3bf783fd9a2e76e17ea58d9bd3d2575aa6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:10:53.075755Z","signature_b64":"gGsl+Qs/ryOqHXH8do2NuwYpQ/LBhlYwxwxXsInqLbWWPKfaB3dmlnjWChrYGsgUCyH9rTr+jnx+ySpFsz8yBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b1f7db9f41b9b09381d2eb95875359211d211cf827cbcf0b84858de180d4a50","last_reissued_at":"2026-07-05T10:10:53.075285Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:10:53.075285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multilingual Non-Autoregressive Machine Translation without Knowledge Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenyang Huang, Fei Huang, Hao Zhou, Lili Mou, Osmar R. Za\\\"iane, Zaixiang Zheng","submitted_at":"2025-02-06T22:16:28Z","abstract_excerpt":"Multilingual neural machine translation (MNMT) aims at using one single model for multiple translation directions. Recent work applies non-autoregressive Transformers to improve the efficiency of MNMT, but requires expensive knowledge distillation (KD) processes. To this end, we propose an M-DAT approach to non-autoregressive multilingual machine translation. Our system leverages the recent advance of the directed acyclic Transformer (DAT), which does not require KD. We further propose a pivot back-translation (PivotBT) approach to improve the generalization to unseen translation directions. E"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04537","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/2502.04537/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":"2502.04537","created_at":"2026-07-05T10:10:53.075368+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.04537v1","created_at":"2026-07-05T10:10:53.075368+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04537","created_at":"2026-07-05T10:10:53.075368+00:00"},{"alias_kind":"pith_short_12","alias_value":"HMPX3OPUDONQ","created_at":"2026-07-05T10:10:53.075368+00:00"},{"alias_kind":"pith_short_16","alias_value":"HMPX3OPUDONQSOA5","created_at":"2026-07-05T10:10:53.075368+00:00"},{"alias_kind":"pith_short_8","alias_value":"HMPX3OPU","created_at":"2026-07-05T10:10:53.075368+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/HMPX3OPUDONQSOA5F24VQ5JVSI","json":"https://pith.science/pith/HMPX3OPUDONQSOA5F24VQ5JVSI.json","graph_json":"https://pith.science/api/pith-number/HMPX3OPUDONQSOA5F24VQ5JVSI/graph.json","events_json":"https://pith.science/api/pith-number/HMPX3OPUDONQSOA5F24VQ5JVSI/events.json","paper":"https://pith.science/paper/HMPX3OPU"},"agent_actions":{"view_html":"https://pith.science/pith/HMPX3OPUDONQSOA5F24VQ5JVSI","download_json":"https://pith.science/pith/HMPX3OPUDONQSOA5F24VQ5JVSI.json","view_paper":"https://pith.science/paper/HMPX3OPU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.04537&json=true","fetch_graph":"https://pith.science/api/pith-number/HMPX3OPUDONQSOA5F24VQ5JVSI/graph.json","fetch_events":"https://pith.science/api/pith-number/HMPX3OPUDONQSOA5F24VQ5JVSI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HMPX3OPUDONQSOA5F24VQ5JVSI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HMPX3OPUDONQSOA5F24VQ5JVSI/action/storage_attestation","attest_author":"https://pith.science/pith/HMPX3OPUDONQSOA5F24VQ5JVSI/action/author_attestation","sign_citation":"https://pith.science/pith/HMPX3OPUDONQSOA5F24VQ5JVSI/action/citation_signature","submit_replication":"https://pith.science/pith/HMPX3OPUDONQSOA5F24VQ5JVSI/action/replication_record"}},"created_at":"2026-07-05T10:10:53.075368+00:00","updated_at":"2026-07-05T10:10:53.075368+00:00"}