{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:JLQGM2S5EGJUDV3S3KARIMDBX4","short_pith_number":"pith:JLQGM2S5","schema_version":"1.0","canonical_sha256":"4ae0666a5d219341d772da81143061bf2034587da8fca37cdd983f7450f85686","source":{"kind":"arxiv","id":"1809.02393","version":2},"attestation_state":"computed","paper":{"title":"Improving Neural Question Generation using Answer Separation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.CL","authors_text":"Hwanhee Lee, Joongbo Shin, Kyomin Jung, Yanghoon Kim","submitted_at":"2018-09-07T10:35:42Z","abstract_excerpt":"Neural question generation (NQG) is the task of generating a question from a given passage with deep neural networks. Previous NQG models suffer from a problem that a significant proportion of the generated questions include words in the question target, resulting in the generation of unintended questions. In this paper, we propose answer-separated seq2seq, which better utilizes the information from both the passage and the target answer. By replacing the target answer in the original passage with a special token, our model learns to identify which interrogative word should be used. We also pr"},"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":"1809.02393","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-07T10:35:42Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"2fda485450f75daf4700767e0556ae60421f2e316b35bb23168a697a435c5e73","abstract_canon_sha256":"829f91b04886880a53291e35bbfdfbef95a8341175631c062d74cfb00300e47f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:29.699955Z","signature_b64":"ldFTbpCKJhMhqeRWZLp4zemTka/2zzBXNK2t5Gp0ZuXw5kbD3rl9IATN4A0ousmu9/NSqus0igl3PjJB7ewiDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ae0666a5d219341d772da81143061bf2034587da8fca37cdd983f7450f85686","last_reissued_at":"2026-05-18T00:00:29.699546Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:29.699546Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Neural Question Generation using Answer Separation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.CL","authors_text":"Hwanhee Lee, Joongbo Shin, Kyomin Jung, Yanghoon Kim","submitted_at":"2018-09-07T10:35:42Z","abstract_excerpt":"Neural question generation (NQG) is the task of generating a question from a given passage with deep neural networks. Previous NQG models suffer from a problem that a significant proportion of the generated questions include words in the question target, resulting in the generation of unintended questions. In this paper, we propose answer-separated seq2seq, which better utilizes the information from both the passage and the target answer. By replacing the target answer in the original passage with a special token, our model learns to identify which interrogative word should be used. We also pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.02393","kind":"arxiv","version":2},"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":"1809.02393","created_at":"2026-05-18T00:00:29.699608+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.02393v2","created_at":"2026-05-18T00:00:29.699608+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.02393","created_at":"2026-05-18T00:00:29.699608+00:00"},{"alias_kind":"pith_short_12","alias_value":"JLQGM2S5EGJU","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_16","alias_value":"JLQGM2S5EGJUDV3S","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_8","alias_value":"JLQGM2S5","created_at":"2026-05-18T12:32:31.084164+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1909.05355","citing_title":"Let's Ask Again: Refine Network for Automatic Question Generation","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JLQGM2S5EGJUDV3S3KARIMDBX4","json":"https://pith.science/pith/JLQGM2S5EGJUDV3S3KARIMDBX4.json","graph_json":"https://pith.science/api/pith-number/JLQGM2S5EGJUDV3S3KARIMDBX4/graph.json","events_json":"https://pith.science/api/pith-number/JLQGM2S5EGJUDV3S3KARIMDBX4/events.json","paper":"https://pith.science/paper/JLQGM2S5"},"agent_actions":{"view_html":"https://pith.science/pith/JLQGM2S5EGJUDV3S3KARIMDBX4","download_json":"https://pith.science/pith/JLQGM2S5EGJUDV3S3KARIMDBX4.json","view_paper":"https://pith.science/paper/JLQGM2S5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.02393&json=true","fetch_graph":"https://pith.science/api/pith-number/JLQGM2S5EGJUDV3S3KARIMDBX4/graph.json","fetch_events":"https://pith.science/api/pith-number/JLQGM2S5EGJUDV3S3KARIMDBX4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JLQGM2S5EGJUDV3S3KARIMDBX4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JLQGM2S5EGJUDV3S3KARIMDBX4/action/storage_attestation","attest_author":"https://pith.science/pith/JLQGM2S5EGJUDV3S3KARIMDBX4/action/author_attestation","sign_citation":"https://pith.science/pith/JLQGM2S5EGJUDV3S3KARIMDBX4/action/citation_signature","submit_replication":"https://pith.science/pith/JLQGM2S5EGJUDV3S3KARIMDBX4/action/replication_record"}},"created_at":"2026-05-18T00:00:29.699608+00:00","updated_at":"2026-05-18T00:00:29.699608+00:00"}