{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:RJ3ZJLF45FX6X56VEK72VG2BWP","short_pith_number":"pith:RJ3ZJLF4","schema_version":"1.0","canonical_sha256":"8a7794acbce96febf7d522bfaa9b41b3fee459ea2c1670184b367a75656c7945","source":{"kind":"arxiv","id":"1907.09527","version":1},"attestation_state":"computed","paper":{"title":"Maximizing Stylistic Control and Semantic Accuracy in NLG: Personality Variation and Discourse Contrast","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Lena Reed, Marilyn Walker, Shereen Oraby, Vrindavan Harrison","submitted_at":"2019-07-22T18:57:14Z","abstract_excerpt":"Neural generation methods for task-oriented dialogue typically generate from a meaning representation that is populated using a database of domain information, such as a table of data describing a restaurant. While earlier work focused solely on the semantic fidelity of outputs, recent work has started to explore methods for controlling the style of the generated text while simultaneously achieving semantic accuracy. Here we experiment with two stylistic benchmark tasks, generating language that exhibits variation in personality, and generating discourse contrast. We report a huge performance "},"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":"1907.09527","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-22T18:57:14Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"91e02e81e7dd87184a80e9e9d06fdf77efa078e9ab7d1e9c502ee4aa4c1a355b","abstract_canon_sha256":"c87335bf1a3bd458c8169f12ba9db877dfbac6efbff652f24f6316161fc061b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:53.009838Z","signature_b64":"x7C0dfohAAg7O04hczMw8hZ9hOdM0+ZQ8U0sheU9yta5V50dBi+cwQ6VRKuOkYljWnitKewGDyblKDVsgf9SAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a7794acbce96febf7d522bfaa9b41b3fee459ea2c1670184b367a75656c7945","last_reissued_at":"2026-05-17T23:39:53.009244Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:53.009244Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Maximizing Stylistic Control and Semantic Accuracy in NLG: Personality Variation and Discourse Contrast","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Lena Reed, Marilyn Walker, Shereen Oraby, Vrindavan Harrison","submitted_at":"2019-07-22T18:57:14Z","abstract_excerpt":"Neural generation methods for task-oriented dialogue typically generate from a meaning representation that is populated using a database of domain information, such as a table of data describing a restaurant. While earlier work focused solely on the semantic fidelity of outputs, recent work has started to explore methods for controlling the style of the generated text while simultaneously achieving semantic accuracy. Here we experiment with two stylistic benchmark tasks, generating language that exhibits variation in personality, and generating discourse contrast. We report a huge performance "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.09527","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":"1907.09527","created_at":"2026-05-17T23:39:53.009338+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.09527v1","created_at":"2026-05-17T23:39:53.009338+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.09527","created_at":"2026-05-17T23:39:53.009338+00:00"},{"alias_kind":"pith_short_12","alias_value":"RJ3ZJLF45FX6","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"RJ3ZJLF45FX6X56V","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"RJ3ZJLF4","created_at":"2026-05-18T12:33:27.125529+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/RJ3ZJLF45FX6X56VEK72VG2BWP","json":"https://pith.science/pith/RJ3ZJLF45FX6X56VEK72VG2BWP.json","graph_json":"https://pith.science/api/pith-number/RJ3ZJLF45FX6X56VEK72VG2BWP/graph.json","events_json":"https://pith.science/api/pith-number/RJ3ZJLF45FX6X56VEK72VG2BWP/events.json","paper":"https://pith.science/paper/RJ3ZJLF4"},"agent_actions":{"view_html":"https://pith.science/pith/RJ3ZJLF45FX6X56VEK72VG2BWP","download_json":"https://pith.science/pith/RJ3ZJLF45FX6X56VEK72VG2BWP.json","view_paper":"https://pith.science/paper/RJ3ZJLF4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.09527&json=true","fetch_graph":"https://pith.science/api/pith-number/RJ3ZJLF45FX6X56VEK72VG2BWP/graph.json","fetch_events":"https://pith.science/api/pith-number/RJ3ZJLF45FX6X56VEK72VG2BWP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RJ3ZJLF45FX6X56VEK72VG2BWP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RJ3ZJLF45FX6X56VEK72VG2BWP/action/storage_attestation","attest_author":"https://pith.science/pith/RJ3ZJLF45FX6X56VEK72VG2BWP/action/author_attestation","sign_citation":"https://pith.science/pith/RJ3ZJLF45FX6X56VEK72VG2BWP/action/citation_signature","submit_replication":"https://pith.science/pith/RJ3ZJLF45FX6X56VEK72VG2BWP/action/replication_record"}},"created_at":"2026-05-17T23:39:53.009338+00:00","updated_at":"2026-05-17T23:39:53.009338+00:00"}