{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:FR5UATBPIR6XII5JQNVF2T6DK5","short_pith_number":"pith:FR5UATBP","schema_version":"1.0","canonical_sha256":"2c7b404c2f447d7423a9836a5d4fc3574de30768607e6ad3b4ec9a05811760d6","source":{"kind":"arxiv","id":"1906.00575","version":3},"attestation_state":"computed","paper":{"title":"Jointly Learning Semantic Parser and Natural Language Generator via Dual Information Maximization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hai Ye, Lu Wang, Wenjie Li","submitted_at":"2019-06-03T05:00:09Z","abstract_excerpt":"Semantic parsing aims to transform natural language (NL) utterances into formal meaning representations (MRs), whereas an NL generator achieves the reverse: producing a NL description for some given MRs. Despite this intrinsic connection, the two tasks are often studied separately in prior work. In this paper, we model the duality of these two tasks via a joint learning framework, and demonstrate its effectiveness of boosting the performance on both tasks. Concretely, we propose a novel method of dual information maximization (DIM) to regularize the learning process, where DIM empirically maxi"},"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":"1906.00575","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-03T05:00:09Z","cross_cats_sorted":[],"title_canon_sha256":"a5d062f52fce2badac88cf513010b9719b6d5e0eab22227c46764fd7b0bae6d4","abstract_canon_sha256":"2dda05024740399c9e7951a3fa1b84fbf7ee7e14d9f06ae9a68199e08bda507b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:22.821720Z","signature_b64":"iCwRNdDos9Y1c80ngpULg/KNz7oN+WQqpLN+xQcOOUEJe7tSjg/MGUMVX634ragxyB1pjeUYFWOpllhvzqhXBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c7b404c2f447d7423a9836a5d4fc3574de30768607e6ad3b4ec9a05811760d6","last_reissued_at":"2026-05-17T23:43:22.821023Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:22.821023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Jointly Learning Semantic Parser and Natural Language Generator via Dual Information Maximization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hai Ye, Lu Wang, Wenjie Li","submitted_at":"2019-06-03T05:00:09Z","abstract_excerpt":"Semantic parsing aims to transform natural language (NL) utterances into formal meaning representations (MRs), whereas an NL generator achieves the reverse: producing a NL description for some given MRs. Despite this intrinsic connection, the two tasks are often studied separately in prior work. In this paper, we model the duality of these two tasks via a joint learning framework, and demonstrate its effectiveness of boosting the performance on both tasks. Concretely, we propose a novel method of dual information maximization (DIM) to regularize the learning process, where DIM empirically maxi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.00575","kind":"arxiv","version":3},"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":"1906.00575","created_at":"2026-05-17T23:43:22.821122+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.00575v3","created_at":"2026-05-17T23:43:22.821122+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.00575","created_at":"2026-05-17T23:43:22.821122+00:00"},{"alias_kind":"pith_short_12","alias_value":"FR5UATBPIR6X","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_16","alias_value":"FR5UATBPIR6XII5J","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_8","alias_value":"FR5UATBP","created_at":"2026-05-18T12:33:15.570797+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.11521","citing_title":"Deep Ranking Based Cost-sensitive Multi-label Learning for Distant Supervision Relation Extraction","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FR5UATBPIR6XII5JQNVF2T6DK5","json":"https://pith.science/pith/FR5UATBPIR6XII5JQNVF2T6DK5.json","graph_json":"https://pith.science/api/pith-number/FR5UATBPIR6XII5JQNVF2T6DK5/graph.json","events_json":"https://pith.science/api/pith-number/FR5UATBPIR6XII5JQNVF2T6DK5/events.json","paper":"https://pith.science/paper/FR5UATBP"},"agent_actions":{"view_html":"https://pith.science/pith/FR5UATBPIR6XII5JQNVF2T6DK5","download_json":"https://pith.science/pith/FR5UATBPIR6XII5JQNVF2T6DK5.json","view_paper":"https://pith.science/paper/FR5UATBP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.00575&json=true","fetch_graph":"https://pith.science/api/pith-number/FR5UATBPIR6XII5JQNVF2T6DK5/graph.json","fetch_events":"https://pith.science/api/pith-number/FR5UATBPIR6XII5JQNVF2T6DK5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FR5UATBPIR6XII5JQNVF2T6DK5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FR5UATBPIR6XII5JQNVF2T6DK5/action/storage_attestation","attest_author":"https://pith.science/pith/FR5UATBPIR6XII5JQNVF2T6DK5/action/author_attestation","sign_citation":"https://pith.science/pith/FR5UATBPIR6XII5JQNVF2T6DK5/action/citation_signature","submit_replication":"https://pith.science/pith/FR5UATBPIR6XII5JQNVF2T6DK5/action/replication_record"}},"created_at":"2026-05-17T23:43:22.821122+00:00","updated_at":"2026-05-17T23:43:22.821122+00:00"}