{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:MVYCAJD4JCTGN5HQZT3FEV42O4","short_pith_number":"pith:MVYCAJD4","schema_version":"1.0","canonical_sha256":"657020247c48a666f4f0ccf652579a773f58cd0cd943b5974729774f6cc1d320","source":{"kind":"arxiv","id":"1811.01116","version":2},"attestation_state":"computed","paper":{"title":"Bi-Directional Differentiable Input Reconstruction for Low-Resource Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Marine Carpuat, Weijia Xu, Xing Niu","submitted_at":"2018-11-02T22:55:04Z","abstract_excerpt":"We aim to better exploit the limited amounts of parallel text available in low-resource settings by introducing a differentiable reconstruction loss for neural machine translation (NMT). This loss compares original inputs to reconstructed inputs, obtained by back-translating translation hypotheses into the input language. We leverage differentiable sampling and bi-directional NMT to train models end-to-end, without introducing additional parameters. This approach achieves small but consistent BLEU improvements on four language pairs in both translation directions, and outperforms an alternativ"},"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":"1811.01116","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-02T22:55:04Z","cross_cats_sorted":[],"title_canon_sha256":"ef840fb57a93d28d51cd66fd9fc6f179f75423c0da52d765d407c3b9ff0545c7","abstract_canon_sha256":"4fa52483f8748fb7246cc868f1df2fc6ef0e712e983c852bcd90ebc37c0a0dd9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:27.474598Z","signature_b64":"tAZQ7u6rAkxrwI2/7u8u6Z0MWYqhsRnJbk+SP+fiQ9h/KwLSkGdR6kfo1mmhkAa+riCZKWEsGHn92MHtrvbzDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"657020247c48a666f4f0ccf652579a773f58cd0cd943b5974729774f6cc1d320","last_reissued_at":"2026-05-17T23:49:27.474044Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:27.474044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bi-Directional Differentiable Input Reconstruction for Low-Resource Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Marine Carpuat, Weijia Xu, Xing Niu","submitted_at":"2018-11-02T22:55:04Z","abstract_excerpt":"We aim to better exploit the limited amounts of parallel text available in low-resource settings by introducing a differentiable reconstruction loss for neural machine translation (NMT). This loss compares original inputs to reconstructed inputs, obtained by back-translating translation hypotheses into the input language. We leverage differentiable sampling and bi-directional NMT to train models end-to-end, without introducing additional parameters. This approach achieves small but consistent BLEU improvements on four language pairs in both translation directions, and outperforms an alternativ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.01116","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":"1811.01116","created_at":"2026-05-17T23:49:27.474130+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.01116v2","created_at":"2026-05-17T23:49:27.474130+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.01116","created_at":"2026-05-17T23:49:27.474130+00:00"},{"alias_kind":"pith_short_12","alias_value":"MVYCAJD4JCTG","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_16","alias_value":"MVYCAJD4JCTGN5HQ","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_8","alias_value":"MVYCAJD4","created_at":"2026-05-18T12:32:40.477152+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/MVYCAJD4JCTGN5HQZT3FEV42O4","json":"https://pith.science/pith/MVYCAJD4JCTGN5HQZT3FEV42O4.json","graph_json":"https://pith.science/api/pith-number/MVYCAJD4JCTGN5HQZT3FEV42O4/graph.json","events_json":"https://pith.science/api/pith-number/MVYCAJD4JCTGN5HQZT3FEV42O4/events.json","paper":"https://pith.science/paper/MVYCAJD4"},"agent_actions":{"view_html":"https://pith.science/pith/MVYCAJD4JCTGN5HQZT3FEV42O4","download_json":"https://pith.science/pith/MVYCAJD4JCTGN5HQZT3FEV42O4.json","view_paper":"https://pith.science/paper/MVYCAJD4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.01116&json=true","fetch_graph":"https://pith.science/api/pith-number/MVYCAJD4JCTGN5HQZT3FEV42O4/graph.json","fetch_events":"https://pith.science/api/pith-number/MVYCAJD4JCTGN5HQZT3FEV42O4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MVYCAJD4JCTGN5HQZT3FEV42O4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MVYCAJD4JCTGN5HQZT3FEV42O4/action/storage_attestation","attest_author":"https://pith.science/pith/MVYCAJD4JCTGN5HQZT3FEV42O4/action/author_attestation","sign_citation":"https://pith.science/pith/MVYCAJD4JCTGN5HQZT3FEV42O4/action/citation_signature","submit_replication":"https://pith.science/pith/MVYCAJD4JCTGN5HQZT3FEV42O4/action/replication_record"}},"created_at":"2026-05-17T23:49:27.474130+00:00","updated_at":"2026-05-17T23:49:27.474130+00:00"}