{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:GTU5R2XAFDML6H756MFAB7QWLM","short_pith_number":"pith:GTU5R2XA","schema_version":"1.0","canonical_sha256":"34e9d8eae028d8bf1ffdf30a00fe165b17c1cdbfa8277900cedd783d398ac873","source":{"kind":"arxiv","id":"1709.06265","version":2},"attestation_state":"computed","paper":{"title":"Dynamic Oracle for Neural Machine Translation in Decoding Phase","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hao Zhou, Jia-Jun Chen, Shu-Jian Huang, Xin-Yu Dai, Zi-Yi Dou","submitted_at":"2017-09-19T06:07:12Z","abstract_excerpt":"The past several years have witnessed the rapid progress of end-to-end Neural Machine Translation (NMT). However, there exists discrepancy between training and inference in NMT when decoding, which may lead to serious problems since the model might be in a part of the state space it has never seen during training. To address the issue, Scheduled Sampling has been proposed. However, there are certain limitations in Scheduled Sampling and we propose two dynamic oracle-based methods to improve it. We manage to mitigate the discrepancy by changing the training process towards a less guided scheme "},"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":"1709.06265","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-19T06:07:12Z","cross_cats_sorted":[],"title_canon_sha256":"2bf50a8cdf5923690299887cfa54335420c1a0353be66e6b8cfa922e9b7f23f8","abstract_canon_sha256":"7c1e56d637e5ad4deb10d1dfb08af77bfa3f1e5023430c50d625e5ffff7b15de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:32:38.861621Z","signature_b64":"1BLsd7JuLyEp1O/W9OvwCox/462CYPOjSRXXCPQ2GTOBUL0/x4KHobFRInrZYp2xmf+86ROAs7IPzhAycJ7mCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34e9d8eae028d8bf1ffdf30a00fe165b17c1cdbfa8277900cedd783d398ac873","last_reissued_at":"2026-05-18T00:32:38.861024Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:32:38.861024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamic Oracle for Neural Machine Translation in Decoding Phase","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hao Zhou, Jia-Jun Chen, Shu-Jian Huang, Xin-Yu Dai, Zi-Yi Dou","submitted_at":"2017-09-19T06:07:12Z","abstract_excerpt":"The past several years have witnessed the rapid progress of end-to-end Neural Machine Translation (NMT). However, there exists discrepancy between training and inference in NMT when decoding, which may lead to serious problems since the model might be in a part of the state space it has never seen during training. To address the issue, Scheduled Sampling has been proposed. However, there are certain limitations in Scheduled Sampling and we propose two dynamic oracle-based methods to improve it. We manage to mitigate the discrepancy by changing the training process towards a less guided scheme "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.06265","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":"1709.06265","created_at":"2026-05-18T00:32:38.861123+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.06265v2","created_at":"2026-05-18T00:32:38.861123+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.06265","created_at":"2026-05-18T00:32:38.861123+00:00"},{"alias_kind":"pith_short_12","alias_value":"GTU5R2XAFDML","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_16","alias_value":"GTU5R2XAFDML6H75","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_8","alias_value":"GTU5R2XA","created_at":"2026-05-18T12:31:18.294218+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/GTU5R2XAFDML6H756MFAB7QWLM","json":"https://pith.science/pith/GTU5R2XAFDML6H756MFAB7QWLM.json","graph_json":"https://pith.science/api/pith-number/GTU5R2XAFDML6H756MFAB7QWLM/graph.json","events_json":"https://pith.science/api/pith-number/GTU5R2XAFDML6H756MFAB7QWLM/events.json","paper":"https://pith.science/paper/GTU5R2XA"},"agent_actions":{"view_html":"https://pith.science/pith/GTU5R2XAFDML6H756MFAB7QWLM","download_json":"https://pith.science/pith/GTU5R2XAFDML6H756MFAB7QWLM.json","view_paper":"https://pith.science/paper/GTU5R2XA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.06265&json=true","fetch_graph":"https://pith.science/api/pith-number/GTU5R2XAFDML6H756MFAB7QWLM/graph.json","fetch_events":"https://pith.science/api/pith-number/GTU5R2XAFDML6H756MFAB7QWLM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GTU5R2XAFDML6H756MFAB7QWLM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GTU5R2XAFDML6H756MFAB7QWLM/action/storage_attestation","attest_author":"https://pith.science/pith/GTU5R2XAFDML6H756MFAB7QWLM/action/author_attestation","sign_citation":"https://pith.science/pith/GTU5R2XAFDML6H756MFAB7QWLM/action/citation_signature","submit_replication":"https://pith.science/pith/GTU5R2XAFDML6H756MFAB7QWLM/action/replication_record"}},"created_at":"2026-05-18T00:32:38.861123+00:00","updated_at":"2026-05-18T00:32:38.861123+00:00"}