{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T07:10:11Z","timestamp":1777705811386,"version":"3.51.4"},"reference-count":45,"publisher":"SAGE Publications","issue":"5","license":[{"start":{"date-parts":[[2021,12,24]],"date-time":"2021-12-24T00:00:00Z","timestamp":1640304000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"published-print":{"date-parts":[[2022,3,31]]},"abstract":"<jats:p>The traditional end-to-end Neural Question Generation (NQG) models tend to generate generic and bland questions, as there are two obscure points: 1) the modifications of the answer in the context can be used as the clues to the answer mentioned in the question, while they are generally not unique and can be used independently for generating diverse questions; 2) the same question content can also be asked in diverse ways, which depends on personal preference in practice. The above-mentioned two points are indeed two variables to conduct question generation, but they are not annotated in the original dataset and are thus ignored by the traditional end-to-end models. In this paper we propose a framework that clarifies those two points through two sub-modules to better conduct question generation. We take experiments based on the GPT-2 model and the SQuAD dataset, and prove that our framework can improve the performance measured by similarity metrics, while it also provides appropriate alternatives for controllable diversity enhancement.<\/jats:p>","DOI":"10.3233\/jifs-219249","type":"journal-article","created":{"date-parts":[[2021,12,24]],"date-time":"2021-12-24T10:27:44Z","timestamp":1640341664000},"page":"4611-4622","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":2,"title":["Question type and answer related keywords aware question generation"],"prefix":"10.1177","volume":"42","author":[{"given":"Jianfei","family":"Zhang","sequence":"first","affiliation":[{"name":"State Key Laboratory of Software Development Environment, Beihang University, Beijing, China"},{"name":"School of Computer Science and Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenge","family":"Rong","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Software Development Environment, Beihang University, Beijing, China"},{"name":"School of Computer Science and Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dali","family":"Chen","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhang","family":"Xiong","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Software Development Environment, Beihang University, Beijing, China"},{"name":"School of Computer Science and Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","published-online":{"date-parts":[[2021,12,24]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"crossref","unstructured":"KimY. LeeH. ShinJ. and JungK. Improving neural question generation using answer separation in Proceedings of the 33rd AAAI Conference on Artificial Intelligence (2019) pp. 6602\u20136609.","DOI":"10.1609\/aaai.v33i01.33016602"},{"key":"e_1_3_2_3_2","doi-asserted-by":"crossref","unstructured":"TsaiD.C.L. HuangA.Y.Q. LuO.H.T. and YangS.J.H. Automatic question generation for repeated testing to improve student learning outcome in Proceedings of the 21st International Conference on Advanced Learning Technologies (2021) pp. 339\u2013341.","DOI":"10.1109\/ICALT52272.2021.00108"},{"key":"e_1_3_2_4_2","doi-asserted-by":"crossref","unstructured":"DuanN. TangD. ChenP. and ZhouM. Question generation for question answering in Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing (2017) pp. 866\u2013874.","DOI":"10.18653\/v1\/D17-1090"},{"key":"e_1_3_2_5_2","doi-asserted-by":"crossref","unstructured":"LeeC. ChenT. ChenL. YangP. and TsaiR.T. Automatic question generation from children\u2019s stories for companion chatbot in Proceedings of the 2018 IEEE International Conference on Information Reuse and Integration (2018) pp. 491\u2013494.","DOI":"10.1109\/IRI.2018.00078"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/365153.365168"},{"key":"e_1_3_2_7_2","doi-asserted-by":"crossref","unstructured":"SultanM.A. ChandelS. AstudilloR.F. and CastelliV. On the importance of diversity in question generation for QA in Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (2020) pp. 5651\u20135656.","DOI":"10.18653\/v1\/2020.acl-main.500"},{"key":"e_1_3_2_8_2","doi-asserted-by":"crossref","unstructured":"HarrisonV. and WalkerM.A. Neural generation of diverse questions using answer focus contextual and linguistic features in Proceedings of the 11th International Conference on Natural Language Generation (2018) pp. 296\u2013306.","DOI":"10.18653\/v1\/W18-6536"},{"key":"e_1_3_2_9_2","unstructured":"WangS. and JiangJ. Machine comprehension using matchlstm and answer pointer in Proceedings of the 5th International Conference on Learning Representations 2017."},{"key":"e_1_3_2_10_2","doi-asserted-by":"crossref","unstructured":"ZhouQ. YangN. WeiF. TanC. BaoH. and ZhouM. Neural question generation from text: A preliminary study in Proceedings of the 6th CCF International Conference on Natural Language Processing and Chinese Computing (2017) pp. 662\u2013671.","DOI":"10.1007\/978-3-319-73618-1_56"},{"key":"e_1_3_2_11_2","doi-asserted-by":"crossref","unstructured":"ChoK. van MerrienboerB. GulcehreC. BahdanauD. BougaresF. SchwenkH. and BengioY. Learning phrase representations using RNN encoder-decoder for statistical machine translation in Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (2014) pp. 1724\u20131734.","DOI":"10.3115\/v1\/D14-1179"},{"key":"e_1_3_2_12_2","doi-asserted-by":"crossref","unstructured":"KoehnP. and KnowlesR. Six challenges for neural machine translation in Proceedings of the 1st Workshop on Neural Machine Translation (2017) pp. 28\u201339.","DOI":"10.18653\/v1\/W17-3204"},{"key":"e_1_3_2_13_2","doi-asserted-by":"crossref","unstructured":"StahlbergF. and ByrneB. On NMT search errors and model errors: Cat got your tongue? in Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing (2019) pp. 3354\u20133360.","DOI":"10.18653\/v1\/D19-1331"},{"key":"e_1_3_2_14_2","unstructured":"CohenE. and BeckJ.C. Empirical analysis of beam search performance degradation in neural sequence models in Proceedings of the 36th International Conference on Machine Learning (2019) pp. 1290\u20131299."},{"key":"e_1_3_2_15_2","unstructured":"SutskeverI. VinyalsO. and LeQ.V. Sequence to sequence learning with neural networks in Proceedings of 2014 Annual Conference on Neural Information Processing Systems (2014) pp. 3104\u20133112."},{"key":"e_1_3_2_16_2","doi-asserted-by":"crossref","unstructured":"BakerC.F. FillmoreC.J. and LoweJ.B. The berkeley framenet project in Proceedings of the 36th Annual Meeting of the Association for Computational Linguistics and the 17th International Conference on Computational Linguistics (1998) pp. 86\u201390.","DOI":"10.3115\/980845.980860"},{"key":"e_1_3_2_17_2","doi-asserted-by":"crossref","unstructured":"ZhouW. ZhangM. and WuY. Question-type driven question generation in Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing (2019) pp. 6031\u20136036.","DOI":"10.18653\/v1\/D19-1622"},{"key":"e_1_3_2_18_2","unstructured":"HuW. LiuB. MaJ. ZhaoD. and YanR. Aspect-based question generation in Proceedings of the 6th International Conference on Learning Representations 2018."},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2897773"},{"key":"e_1_3_2_20_2","doi-asserted-by":"crossref","unstructured":"MaX. ZhuQ. ZhouY. and LiX. Improving question generation with sentence-level semantic matching and answer position inferring in Proceedings of the 34th AAAI Conference on Artificial Intelligence (2020) pp. 8464\u20138471.","DOI":"10.1609\/aaai.v34i05.6366"},{"key":"e_1_3_2_21_2","unstructured":"SubramanianS. WangT. YuanX. and TrischlerA. Neural models for key phrase detection and question generation CoRR vol. abs\/1706.04560 2017."},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1007\/s40593-019-00186-y"},{"key":"e_1_3_2_23_2","first-page":"213","article-title":"Automatic question generation from sentences","author":"Ali H.","year":"2010","unstructured":"AliH., ChaliY. and HasanS.A., Automatic question generation from sentences, in Actes de la 17e conference surle Traitement Automatique des Langues Naturelles. Articles courts (2010), pp. 213\u2013218.","journal-title":"Actes de la 17e conference surle Traitement Automatique des Langues Naturelles. Articles courts"},{"key":"e_1_3_2_24_2","doi-asserted-by":"crossref","unstructured":"ChaliY. and GolestaniradS. Ranking automatically generated questions using common human queries in Proceedings of the Ninth International Natural Language Generation Conference (2016) pp. 217\u2013221.","DOI":"10.18653\/v1\/W16-6635"},{"key":"e_1_3_2_25_2","doi-asserted-by":"crossref","unstructured":"ChoK. van MerrienboerB. BahdanauD. and BengioY. On the properties of neural machine translation: Encoder-decoder approaches in Proceedings of Eighth Workshop on Syntax Semantics and Structure in Statistical Translation (2014) pp. 103\u2013111.","DOI":"10.3115\/v1\/W14-4012"},{"key":"e_1_3_2_26_2","unstructured":"BahdanauD. ChoK. and BengioY. Neural machine translation by jointly learning to align and translate in Proceedings of the 3rd International Conference on Learning Representations 2015."},{"key":"e_1_3_2_27_2","doi-asserted-by":"crossref","unstructured":"LuongT. PhamH. and ManningC.D. Effective approaches to attention-based neural machine translation in Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing (2015) pp. 1412\u20131421.","DOI":"10.18653\/v1\/D15-1166"},{"key":"e_1_3_2_28_2","doi-asserted-by":"crossref","unstructured":"SunX. LiuJ. LyuY. HeW. MaY. and WangS. Answer focused and position-aware neural question generation in Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (2018) pp. 3930\u20133939.","DOI":"10.18653\/v1\/D18-1427"},{"key":"e_1_3_2_29_2","doi-asserted-by":"crossref","unstructured":"ZhaoY. NiX. DingY. and KeQ. Paragraph-level neural question generation with maxout pointer and gated selfattention networks in Proceedings of the 2018 Conference on Empirical Methods in Natural LanguageProcessing (2018) pp. 3901\u20133910.","DOI":"10.18653\/v1\/D18-1424"},{"key":"e_1_3_2_30_2","doi-asserted-by":"crossref","unstructured":"DuX. ShaoJ. and CardieC. Learning to ask: Neural question generation for reading comprehension in Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (2017) pp. 1342\u20131352.","DOI":"10.18653\/v1\/P17-1123"},{"key":"e_1_3_2_31_2","doi-asserted-by":"crossref","unstructured":"GuJ. LuZ. LiH. and LiV.O.K. Incorporating copying mechanism in sequence-to-sequence learning in Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics 2016.","DOI":"10.18653\/v1\/P16-1154"},{"key":"e_1_3_2_32_2","doi-asserted-by":"crossref","unstructured":"SeeA. LiuP.J. and ManningC.D. Get to the point: Summarization with pointer-generator networks in Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (2017) pp. 1073\u20131083.","DOI":"10.18653\/v1\/P17-1099"},{"key":"e_1_3_2_33_2","doi-asserted-by":"crossref","unstructured":"HuangX. QiJ. SunY. and ZhangR. Latent reasoning for low-resource question generation in Findings of the Association for Computational Linguistics: ACL\/IJCNLP (2021) pp. 3008\u20133022.","DOI":"10.18653\/v1\/2021.findings-acl.265"},{"key":"e_1_3_2_34_2","doi-asserted-by":"crossref","unstructured":"XieJ. ChenF. CaiY. and LinZ. A double phases generation network for yes or no question generation (student abstract) in Proceedings of the 35th AAAI Conference on Artificial Intelligence (2021) pp. 15 931\u201315 932.","DOI":"10.1609\/aaai.v35i18.17962"},{"key":"e_1_3_2_35_2","first-page":"376","article-title":"Generating natural language question-answer pairs from a knowledge graph using a RNN based question generation model","author":"Reddy S.","year":"2017","unstructured":"ReddyS., RaghuD., KhapraM.M. and JoshiS., Generating natural language question-answer pairs from a knowledge graph using a RNN based question generation model, in Proceedings of the 15th Conference of the European Chapter of the Association forComputational Linguistics (2017), pp. 376\u2013385.","journal-title":"Proceedings of the 15th Conference of the European Chapter of the Association forComputational Linguistics"},{"key":"e_1_3_2_36_2","doi-asserted-by":"crossref","unstructured":"ElSaharH. GravierC. and LaforestF. Zero-shot question generation from knowledge graphs for unseen predicates and entity types in Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (2018) pp. 218\u2013228.","DOI":"10.18653\/v1\/N18-1020"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.5087\/dad.2012.204"},{"key":"e_1_3_2_38_2","first-page":"54","article-title":"Question generation from a knowledge base","volume":"8876","author":"Chaudhri V.K.","year":"2014","unstructured":"ChaudhriV.K., ClarkP.E., OverholtzerA. and SpauldingA., Question generation from a knowledge base, in Proceedings of the 19thInternational Conference on Knowledge Engineering and KnowledgeManagement8876 (2014), pp. 54\u201365.","journal-title":"Proceedings of the 19thInternational Conference on Knowledge Engineering and KnowledgeManagement"},{"key":"e_1_3_2_39_2","unstructured":"DevlinJ. ChangM. LeeK. and ToutanovaK. BERT: pretraining of deep bidirectional transformers for language understanding in Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (2019) pp. 4171\u20134186."},{"issue":"8","key":"e_1_3_2_40_2","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford A.","year":"2019","unstructured":"RadfordA., WuJ., ChildR., LuanD., AmodeiD., SutskeverI., et al., Language models are unsupervised multitask learners, OpenAI Blog1(8) (2019), pp. 9.","journal-title":"OpenAI Blog"},{"key":"e_1_3_2_41_2","doi-asserted-by":"crossref","unstructured":"RajpurkarP. ZhangJ. LopyrevK. and LiangP. SQuAD: 100 000+ questions for machine comprehension of text in Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing (2016) pp. 2383\u20132392.","DOI":"10.18653\/v1\/D16-1264"},{"key":"e_1_3_2_42_2","doi-asserted-by":"crossref","unstructured":"PapineniK. RoukosS. WardT. and ZhuW. BLEU: a method for automatic evaluation of machine translation in Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (2002) pp. 311\u2013318.","DOI":"10.3115\/1073083.1073135"},{"key":"e_1_3_2_43_2","unstructured":"LinC.-Y. Rouge: A package for automatic evaluation of summaries in Text summarization Branches Out (2004) pp. 74\u201381."},{"key":"e_1_3_2_44_2","doi-asserted-by":"crossref","unstructured":"DenkowskiM.J. and LavieA. Meteor universal: Language pecific translation evaluation for any target language in Proceedings of the 9th Workshop on Statistical Machine Translation (2014) pp. 376\u2013380.","DOI":"10.3115\/v1\/W14-3348"},{"key":"e_1_3_2_45_2","doi-asserted-by":"crossref","unstructured":"VedantamR. ZitnickC.L. and ParikhD. CIDEr: Consensus-based image description evaluation in Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition (2015) pp. 4566\u20134575.","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"e_1_3_2_46_2","doi-asserted-by":"crossref","unstructured":"DuX. and CardieC. Harvesting paragraph-level questionanswer pairs from wikipedia in Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (2018) pp. 1907\u20131917.","DOI":"10.18653\/v1\/P18-1177"}],"container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/JIFS-219249","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.3233\/JIFS-219249","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/JIFS-219249","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:45:17Z","timestamp":1777455917000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.3233\/JIFS-219249"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,24]]},"references-count":45,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2022,3,31]]}},"alternative-id":["10.3233\/JIFS-219249"],"URL":"https:\/\/doi.org\/10.3233\/jifs-219249","relation":{},"ISSN":["1064-1246","1875-8967"],"issn-type":[{"value":"1064-1246","type":"print"},{"value":"1875-8967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,12,24]]}}}