{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:OVVSRNWXN6VZEP3KHFZQTWFVPH","short_pith_number":"pith:OVVSRNWX","schema_version":"1.0","canonical_sha256":"756b28b6d76fab923f6a397309d8b579f6b9401a19015433156865c635e780c1","source":{"kind":"arxiv","id":"1811.05826","version":1},"attestation_state":"computed","paper":{"title":"Char2char Generation with Reranking for the E2E NLG Challenge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Eric Gaussier, Marc Dymetman, Shubham Agarwal","submitted_at":"2018-11-04T22:56:50Z","abstract_excerpt":"This paper describes our submission to the E2E NLG Challenge. Recently, neural seq2seq approaches have become mainstream in NLG, often resorting to pre- (respectively post-) processing delexicalization (relexicalization) steps at the word-level to handle rare words. By contrast, we train a simple character level seq2seq model, which requires no pre/post-processing (delexicalization, tokenization or even lowercasing), with surprisingly good results. For further improvement, we explore two re-ranking approaches for scoring candidates. We also introduce a synthetic dataset creation procedure, whi"},"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":"1811.05826","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-04T22:56:50Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6711171fcf54a3afd8a628148a2532d2a468c21193967d5ac2f5b1f8b5a7a4c2","abstract_canon_sha256":"1b308d7798e32c3cc00b4e40c96c7bab5408a2bf4f73fe882379506e696d03e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:42.025511Z","signature_b64":"b6BlnsassF6k4iFv+cEiQskrgicb8HZqBpLGH+ftq12cvdIasUfuRCopOwzJwYKk+bXVCa73Aix5Rwj+xUqiDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"756b28b6d76fab923f6a397309d8b579f6b9401a19015433156865c635e780c1","last_reissued_at":"2026-05-18T00:00:42.025095Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:42.025095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Char2char Generation with Reranking for the E2E NLG Challenge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Eric Gaussier, Marc Dymetman, Shubham Agarwal","submitted_at":"2018-11-04T22:56:50Z","abstract_excerpt":"This paper describes our submission to the E2E NLG Challenge. Recently, neural seq2seq approaches have become mainstream in NLG, often resorting to pre- (respectively post-) processing delexicalization (relexicalization) steps at the word-level to handle rare words. By contrast, we train a simple character level seq2seq model, which requires no pre/post-processing (delexicalization, tokenization or even lowercasing), with surprisingly good results. For further improvement, we explore two re-ranking approaches for scoring candidates. We also introduce a synthetic dataset creation procedure, whi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.05826","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":"1811.05826","created_at":"2026-05-18T00:00:42.025158+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.05826v1","created_at":"2026-05-18T00:00:42.025158+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.05826","created_at":"2026-05-18T00:00:42.025158+00:00"},{"alias_kind":"pith_short_12","alias_value":"OVVSRNWXN6VZ","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_16","alias_value":"OVVSRNWXN6VZEP3K","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_8","alias_value":"OVVSRNWX","created_at":"2026-05-18T12:32:43.782077+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/OVVSRNWXN6VZEP3KHFZQTWFVPH","json":"https://pith.science/pith/OVVSRNWXN6VZEP3KHFZQTWFVPH.json","graph_json":"https://pith.science/api/pith-number/OVVSRNWXN6VZEP3KHFZQTWFVPH/graph.json","events_json":"https://pith.science/api/pith-number/OVVSRNWXN6VZEP3KHFZQTWFVPH/events.json","paper":"https://pith.science/paper/OVVSRNWX"},"agent_actions":{"view_html":"https://pith.science/pith/OVVSRNWXN6VZEP3KHFZQTWFVPH","download_json":"https://pith.science/pith/OVVSRNWXN6VZEP3KHFZQTWFVPH.json","view_paper":"https://pith.science/paper/OVVSRNWX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.05826&json=true","fetch_graph":"https://pith.science/api/pith-number/OVVSRNWXN6VZEP3KHFZQTWFVPH/graph.json","fetch_events":"https://pith.science/api/pith-number/OVVSRNWXN6VZEP3KHFZQTWFVPH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OVVSRNWXN6VZEP3KHFZQTWFVPH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OVVSRNWXN6VZEP3KHFZQTWFVPH/action/storage_attestation","attest_author":"https://pith.science/pith/OVVSRNWXN6VZEP3KHFZQTWFVPH/action/author_attestation","sign_citation":"https://pith.science/pith/OVVSRNWXN6VZEP3KHFZQTWFVPH/action/citation_signature","submit_replication":"https://pith.science/pith/OVVSRNWXN6VZEP3KHFZQTWFVPH/action/replication_record"}},"created_at":"2026-05-18T00:00:42.025158+00:00","updated_at":"2026-05-18T00:00:42.025158+00:00"}