{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:UR3IQQ34MP72WFIC67ILK7YFVO","short_pith_number":"pith:UR3IQQ34","schema_version":"1.0","canonical_sha256":"a47688437c63ffab1502f7d0b57f05ab9ae279c5590a0540e99b9b17116c0f95","source":{"kind":"arxiv","id":"1906.07220","version":1},"attestation_state":"computed","paper":{"title":"Constrained Decoding for Neural NLG from Compositional Representations in Task-Oriented Dialogue","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anusha Balakrishnan, Jinfeng Rao, Kartikeya Upasani, Michael White, Rajen Subba","submitted_at":"2019-06-17T18:54:51Z","abstract_excerpt":"Generating fluent natural language responses from structured semantic representations is a critical step in task-oriented conversational systems. Avenues like the E2E NLG Challenge have encouraged the development of neural approaches, particularly sequence-to-sequence (Seq2Seq) models for this problem. The semantic representations used, however, are often underspecified, which places a higher burden on the generation model for sentence planning, and also limits the extent to which generated responses can be controlled in a live system. In this paper, we (1) propose using tree-structured semant"},"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":"1906.07220","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-17T18:54:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"00f962ebb1f5b53789a5791f435eee5352ee755577773b1faa7fcf8db033fdb1","abstract_canon_sha256":"20e504a66f78ef48410b7ca92f505b2f3bd059e89d724c6d690f9fba5b6c4c78"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:08.521028Z","signature_b64":"jT50jiMipsQzaEFnoV4am2uMJJT19ifG3GIfYZw8xg19Cw+9OQDO0bL33P2uEi3LRlDdCF8muNqUR48wMqj8Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a47688437c63ffab1502f7d0b57f05ab9ae279c5590a0540e99b9b17116c0f95","last_reissued_at":"2026-05-17T23:43:08.520584Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:08.520584Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Constrained Decoding for Neural NLG from Compositional Representations in Task-Oriented Dialogue","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anusha Balakrishnan, Jinfeng Rao, Kartikeya Upasani, Michael White, Rajen Subba","submitted_at":"2019-06-17T18:54:51Z","abstract_excerpt":"Generating fluent natural language responses from structured semantic representations is a critical step in task-oriented conversational systems. Avenues like the E2E NLG Challenge have encouraged the development of neural approaches, particularly sequence-to-sequence (Seq2Seq) models for this problem. The semantic representations used, however, are often underspecified, which places a higher burden on the generation model for sentence planning, and also limits the extent to which generated responses can be controlled in a live system. In this paper, we (1) propose using tree-structured semant"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.07220","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":"1906.07220","created_at":"2026-05-17T23:43:08.520653+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.07220v1","created_at":"2026-05-17T23:43:08.520653+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.07220","created_at":"2026-05-17T23:43:08.520653+00:00"},{"alias_kind":"pith_short_12","alias_value":"UR3IQQ34MP72","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"UR3IQQ34MP72WFIC","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"UR3IQQ34","created_at":"2026-05-18T12:33:30.264802+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/UR3IQQ34MP72WFIC67ILK7YFVO","json":"https://pith.science/pith/UR3IQQ34MP72WFIC67ILK7YFVO.json","graph_json":"https://pith.science/api/pith-number/UR3IQQ34MP72WFIC67ILK7YFVO/graph.json","events_json":"https://pith.science/api/pith-number/UR3IQQ34MP72WFIC67ILK7YFVO/events.json","paper":"https://pith.science/paper/UR3IQQ34"},"agent_actions":{"view_html":"https://pith.science/pith/UR3IQQ34MP72WFIC67ILK7YFVO","download_json":"https://pith.science/pith/UR3IQQ34MP72WFIC67ILK7YFVO.json","view_paper":"https://pith.science/paper/UR3IQQ34","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.07220&json=true","fetch_graph":"https://pith.science/api/pith-number/UR3IQQ34MP72WFIC67ILK7YFVO/graph.json","fetch_events":"https://pith.science/api/pith-number/UR3IQQ34MP72WFIC67ILK7YFVO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UR3IQQ34MP72WFIC67ILK7YFVO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UR3IQQ34MP72WFIC67ILK7YFVO/action/storage_attestation","attest_author":"https://pith.science/pith/UR3IQQ34MP72WFIC67ILK7YFVO/action/author_attestation","sign_citation":"https://pith.science/pith/UR3IQQ34MP72WFIC67ILK7YFVO/action/citation_signature","submit_replication":"https://pith.science/pith/UR3IQQ34MP72WFIC67ILK7YFVO/action/replication_record"}},"created_at":"2026-05-17T23:43:08.520653+00:00","updated_at":"2026-05-17T23:43:08.520653+00:00"}