{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:53N37NOVCXV45BMJN4THA5Y6A6","short_pith_number":"pith:53N37NOV","schema_version":"1.0","canonical_sha256":"eedbbfb5d515ebce85896f2670771e0793c3bd07b856584f9dbd9f62fc89c0cb","source":{"kind":"arxiv","id":"1804.05940","version":1},"attestation_state":"computed","paper":{"title":"Approaching Neural Grammatical Error Correction as a Low-Resource Machine Translation Task","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kenneth Heafield, Marcin Junczys-Dowmunt, Roman Grundkiewicz, Shubha Guha","submitted_at":"2018-04-16T21:06:14Z","abstract_excerpt":"Previously, neural methods in grammatical error correction (GEC) did not reach state-of-the-art results compared to phrase-based statistical machine translation (SMT) baselines. We demonstrate parallels between neural GEC and low-resource neural MT and successfully adapt several methods from low-resource MT to neural GEC. We further establish guidelines for trustable results in neural GEC and propose a set of model-independent methods for neural GEC that can be easily applied in most GEC settings. Proposed methods include adding source-side noise, domain-adaptation techniques, a GEC-specific t"},"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":"1804.05940","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-16T21:06:14Z","cross_cats_sorted":[],"title_canon_sha256":"b8825f52c06ca4aa621f93fc3edf9fe2cad913ef3332c0543f82cc8fa8d39723","abstract_canon_sha256":"d969158777c932b1cc03e8c659393a0f39cfb3d54d17a98d31ca44222f2f520f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:18:22.280594Z","signature_b64":"OrUUjGsrgivuXH6wOYO8CCJUgExHQLWSKT1cDEqPqh8CVB8HCZjglAYPesE4yz/rOIkamlTK+zN+MHA3wyEJBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eedbbfb5d515ebce85896f2670771e0793c3bd07b856584f9dbd9f62fc89c0cb","last_reissued_at":"2026-05-18T00:18:22.279847Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:18:22.279847Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Approaching Neural Grammatical Error Correction as a Low-Resource Machine Translation Task","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kenneth Heafield, Marcin Junczys-Dowmunt, Roman Grundkiewicz, Shubha Guha","submitted_at":"2018-04-16T21:06:14Z","abstract_excerpt":"Previously, neural methods in grammatical error correction (GEC) did not reach state-of-the-art results compared to phrase-based statistical machine translation (SMT) baselines. We demonstrate parallels between neural GEC and low-resource neural MT and successfully adapt several methods from low-resource MT to neural GEC. We further establish guidelines for trustable results in neural GEC and propose a set of model-independent methods for neural GEC that can be easily applied in most GEC settings. Proposed methods include adding source-side noise, domain-adaptation techniques, a GEC-specific t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.05940","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":"1804.05940","created_at":"2026-05-18T00:18:22.279971+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.05940v1","created_at":"2026-05-18T00:18:22.279971+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.05940","created_at":"2026-05-18T00:18:22.279971+00:00"},{"alias_kind":"pith_short_12","alias_value":"53N37NOVCXV4","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_16","alias_value":"53N37NOVCXV45BMJ","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_8","alias_value":"53N37NOV","created_at":"2026-05-18T12:32:05.422762+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.23627","citing_title":"Neural Grammatical Error Correction for Romanian","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/53N37NOVCXV45BMJN4THA5Y6A6","json":"https://pith.science/pith/53N37NOVCXV45BMJN4THA5Y6A6.json","graph_json":"https://pith.science/api/pith-number/53N37NOVCXV45BMJN4THA5Y6A6/graph.json","events_json":"https://pith.science/api/pith-number/53N37NOVCXV45BMJN4THA5Y6A6/events.json","paper":"https://pith.science/paper/53N37NOV"},"agent_actions":{"view_html":"https://pith.science/pith/53N37NOVCXV45BMJN4THA5Y6A6","download_json":"https://pith.science/pith/53N37NOVCXV45BMJN4THA5Y6A6.json","view_paper":"https://pith.science/paper/53N37NOV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.05940&json=true","fetch_graph":"https://pith.science/api/pith-number/53N37NOVCXV45BMJN4THA5Y6A6/graph.json","fetch_events":"https://pith.science/api/pith-number/53N37NOVCXV45BMJN4THA5Y6A6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/53N37NOVCXV45BMJN4THA5Y6A6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/53N37NOVCXV45BMJN4THA5Y6A6/action/storage_attestation","attest_author":"https://pith.science/pith/53N37NOVCXV45BMJN4THA5Y6A6/action/author_attestation","sign_citation":"https://pith.science/pith/53N37NOVCXV45BMJN4THA5Y6A6/action/citation_signature","submit_replication":"https://pith.science/pith/53N37NOVCXV45BMJN4THA5Y6A6/action/replication_record"}},"created_at":"2026-05-18T00:18:22.279971+00:00","updated_at":"2026-05-18T00:18:22.279971+00:00"}