{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:BZJUKSOU5HLI4PMRRNQHNP3N27","short_pith_number":"pith:BZJUKSOU","schema_version":"1.0","canonical_sha256":"0e534549d4e9d68e3d918b6076bf6dd7ff46ba0875e38ca3d0a6bf5cc5bcc8ee","source":{"kind":"arxiv","id":"2011.01482","version":1},"attestation_state":"computed","paper":{"title":"Layer-Wise Multi-View Learning for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Changliang Li, Jingbo Zhu, Qiang Wang, Tong Xiao, Yue Zhang","submitted_at":"2020-11-03T05:06:37Z","abstract_excerpt":"Traditional neural machine translation is limited to the topmost encoder layer's context representation and cannot directly perceive the lower encoder layers. Existing solutions usually rely on the adjustment of network architecture, making the calculation more complicated or introducing additional structural restrictions. In this work, we propose layer-wise multi-view learning to solve this problem, circumventing the necessity to change the model structure. We regard each encoder layer's off-the-shelf output, a by-product in layer-by-layer encoding, as the redundant view for the input sentenc"},"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":"2011.01482","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-03T05:06:37Z","cross_cats_sorted":[],"title_canon_sha256":"a71154f07ae3540ecfff97defa1a44008e8f31690eb43d82d2ce9abb7a1dc81e","abstract_canon_sha256":"9f5a1d6cf6f01dc519db22a737c192a70263de95d3db803ecdea86be805ee93e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:48:32.902960Z","signature_b64":"JM6+Wz51mtdlMrvDYpcO6zSdS3tO7cEoTKXjgaKPb0jjR4fyEiIMwfQAbuA7zaKwkinXq1IMbsuMJL+liEbLAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e534549d4e9d68e3d918b6076bf6dd7ff46ba0875e38ca3d0a6bf5cc5bcc8ee","last_reissued_at":"2026-07-05T01:48:32.902557Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:48:32.902557Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Layer-Wise Multi-View Learning for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Changliang Li, Jingbo Zhu, Qiang Wang, Tong Xiao, Yue Zhang","submitted_at":"2020-11-03T05:06:37Z","abstract_excerpt":"Traditional neural machine translation is limited to the topmost encoder layer's context representation and cannot directly perceive the lower encoder layers. Existing solutions usually rely on the adjustment of network architecture, making the calculation more complicated or introducing additional structural restrictions. In this work, we propose layer-wise multi-view learning to solve this problem, circumventing the necessity to change the model structure. We regard each encoder layer's off-the-shelf output, a by-product in layer-by-layer encoding, as the redundant view for the input sentenc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.01482","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/2011.01482/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":"2011.01482","created_at":"2026-07-05T01:48:32.902610+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.01482v1","created_at":"2026-07-05T01:48:32.902610+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.01482","created_at":"2026-07-05T01:48:32.902610+00:00"},{"alias_kind":"pith_short_12","alias_value":"BZJUKSOU5HLI","created_at":"2026-07-05T01:48:32.902610+00:00"},{"alias_kind":"pith_short_16","alias_value":"BZJUKSOU5HLI4PMR","created_at":"2026-07-05T01:48:32.902610+00:00"},{"alias_kind":"pith_short_8","alias_value":"BZJUKSOU","created_at":"2026-07-05T01:48:32.902610+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/BZJUKSOU5HLI4PMRRNQHNP3N27","json":"https://pith.science/pith/BZJUKSOU5HLI4PMRRNQHNP3N27.json","graph_json":"https://pith.science/api/pith-number/BZJUKSOU5HLI4PMRRNQHNP3N27/graph.json","events_json":"https://pith.science/api/pith-number/BZJUKSOU5HLI4PMRRNQHNP3N27/events.json","paper":"https://pith.science/paper/BZJUKSOU"},"agent_actions":{"view_html":"https://pith.science/pith/BZJUKSOU5HLI4PMRRNQHNP3N27","download_json":"https://pith.science/pith/BZJUKSOU5HLI4PMRRNQHNP3N27.json","view_paper":"https://pith.science/paper/BZJUKSOU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.01482&json=true","fetch_graph":"https://pith.science/api/pith-number/BZJUKSOU5HLI4PMRRNQHNP3N27/graph.json","fetch_events":"https://pith.science/api/pith-number/BZJUKSOU5HLI4PMRRNQHNP3N27/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BZJUKSOU5HLI4PMRRNQHNP3N27/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BZJUKSOU5HLI4PMRRNQHNP3N27/action/storage_attestation","attest_author":"https://pith.science/pith/BZJUKSOU5HLI4PMRRNQHNP3N27/action/author_attestation","sign_citation":"https://pith.science/pith/BZJUKSOU5HLI4PMRRNQHNP3N27/action/citation_signature","submit_replication":"https://pith.science/pith/BZJUKSOU5HLI4PMRRNQHNP3N27/action/replication_record"}},"created_at":"2026-07-05T01:48:32.902610+00:00","updated_at":"2026-07-05T01:48:32.902610+00:00"}