{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:KJC3JR6X4ENZ5RZUDC4IH3JYZX","short_pith_number":"pith:KJC3JR6X","schema_version":"1.0","canonical_sha256":"5245b4c7d7e11b9ec73418b883ed38cdfd4f40776b7b7a7951f1d8709ff7fc36","source":{"kind":"arxiv","id":"1807.05324","version":1},"attestation_state":"computed","paper":{"title":"Generating Synthetic Data for Neural Keyword-to-Question Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Heng Ding, Krisztian Balog","submitted_at":"2018-07-14T03:24:31Z","abstract_excerpt":"Search typically relies on keyword queries, but these are often semantically ambiguous. We propose to overcome this by offering users natural language questions, based on their keyword queries, to disambiguate their intent. This keyword-to-question task may be addressed using neural machine translation techniques. Neural translation models, however, require massive amounts of training data (keyword-question pairs), which is unavailable for this task. The main idea of this paper is to generate large amounts of synthetic training data from a small seed set of hand-labeled keyword-question pairs."},"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":"1807.05324","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-07-14T03:24:31Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"ec766d4fbbb04bd21c0f1e2c7d8f597c0a2ed3b0b45c1cd4761fdb52c5f22f82","abstract_canon_sha256":"32bd09a0da2040e574ec2c2509d0fd04485a89579191451629649979ad0a5cb8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:10:36.571141Z","signature_b64":"KEG59tPLQiyXL99i0mH4ikYy/zsA7A+K5YQ64Rdt8rZo4qKOvrLQAiza5lcIre54GeukOD0VWhI1R5Am1IODDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5245b4c7d7e11b9ec73418b883ed38cdfd4f40776b7b7a7951f1d8709ff7fc36","last_reissued_at":"2026-05-18T00:10:36.570607Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:10:36.570607Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generating Synthetic Data for Neural Keyword-to-Question Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Heng Ding, Krisztian Balog","submitted_at":"2018-07-14T03:24:31Z","abstract_excerpt":"Search typically relies on keyword queries, but these are often semantically ambiguous. We propose to overcome this by offering users natural language questions, based on their keyword queries, to disambiguate their intent. This keyword-to-question task may be addressed using neural machine translation techniques. Neural translation models, however, require massive amounts of training data (keyword-question pairs), which is unavailable for this task. The main idea of this paper is to generate large amounts of synthetic training data from a small seed set of hand-labeled keyword-question pairs."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.05324","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":"1807.05324","created_at":"2026-05-18T00:10:36.570678+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.05324v1","created_at":"2026-05-18T00:10:36.570678+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.05324","created_at":"2026-05-18T00:10:36.570678+00:00"},{"alias_kind":"pith_short_12","alias_value":"KJC3JR6X4ENZ","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_16","alias_value":"KJC3JR6X4ENZ5RZU","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_8","alias_value":"KJC3JR6X","created_at":"2026-05-18T12:32:33.847187+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/KJC3JR6X4ENZ5RZUDC4IH3JYZX","json":"https://pith.science/pith/KJC3JR6X4ENZ5RZUDC4IH3JYZX.json","graph_json":"https://pith.science/api/pith-number/KJC3JR6X4ENZ5RZUDC4IH3JYZX/graph.json","events_json":"https://pith.science/api/pith-number/KJC3JR6X4ENZ5RZUDC4IH3JYZX/events.json","paper":"https://pith.science/paper/KJC3JR6X"},"agent_actions":{"view_html":"https://pith.science/pith/KJC3JR6X4ENZ5RZUDC4IH3JYZX","download_json":"https://pith.science/pith/KJC3JR6X4ENZ5RZUDC4IH3JYZX.json","view_paper":"https://pith.science/paper/KJC3JR6X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.05324&json=true","fetch_graph":"https://pith.science/api/pith-number/KJC3JR6X4ENZ5RZUDC4IH3JYZX/graph.json","fetch_events":"https://pith.science/api/pith-number/KJC3JR6X4ENZ5RZUDC4IH3JYZX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KJC3JR6X4ENZ5RZUDC4IH3JYZX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KJC3JR6X4ENZ5RZUDC4IH3JYZX/action/storage_attestation","attest_author":"https://pith.science/pith/KJC3JR6X4ENZ5RZUDC4IH3JYZX/action/author_attestation","sign_citation":"https://pith.science/pith/KJC3JR6X4ENZ5RZUDC4IH3JYZX/action/citation_signature","submit_replication":"https://pith.science/pith/KJC3JR6X4ENZ5RZUDC4IH3JYZX/action/replication_record"}},"created_at":"2026-05-18T00:10:36.570678+00:00","updated_at":"2026-05-18T00:10:36.570678+00:00"}