{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T01:24:55Z","timestamp":1772846695109,"version":"3.50.1"},"reference-count":70,"publisher":"Oxford University Press (OUP)","issue":"7","license":[{"start":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T00:00:00Z","timestamp":1625097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1811264"],"award-info":[{"award-number":["U1811264"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1911203"],"award-info":[{"award-number":["U1911203"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61906217"],"award-info":[{"award-number":["61906217"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U2001211"],"award-info":[{"award-number":["U2001211"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1711262"],"award-info":[{"award-number":["U1711262"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1611264"],"award-info":[{"award-number":["U1611264"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1711261"],"award-info":[{"award-number":["U1711261"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1811261"],"award-info":[{"award-number":["U1811261"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Guangdong Basic and Applied Basic Research Foundation","doi-asserted-by":"crossref","award":["2019B1515130001"],"award-info":[{"award-number":["2019B1515130001"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Key-Area Research and Development Program of Guangdong Province","award":["2018B010107005"],"award-info":[{"award-number":["2018B010107005"]}]},{"name":"Research Foundation of Science and Technology Plan Project in Guangdong Province","award":["2017B030308007"],"award-info":[{"award-number":["2017B030308007"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,8,24]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>The task of question generation (QG) aims to create valid questions and correlated answers from the given text. Despite the neural QG approaches have achieved promising results, they are typically developed for languages with rich annotated training data. Because of the high annotation cost, it is difficult to deploy to other low-resource languages. Besides, different samples have their own characteristics on the aspects of text contextual structure, question type and correlations. Without capturing these diversified characteristics, the traditional one-size-fits-all model is hard to generate the best results. To address this problem, we study the task of cross-lingual QG from an adaptive learning perspective. Concretely, we first build a basic QG model on a multilingual space using the labelled data. In this way, we can transfer the supervision from the high-resource language to the language lacking labelled data. We then design a task-specific meta-learner to optimize the basic QG model. Each sample and its similar instances are viewed as a pseudo-QG task. The asking patterns and logical forms contained in the similar samples can be used as a guide to fine-tune the model fitly and produce the optimal results accordingly. Considering that each sample contains the text, question and answer, with unknown semantic correlations among them, we propose a context-dependent retriever to measure the similarity of such structured inputs. Experimental results on three languages of three typical data sets show the effectiveness of our approach.<\/jats:p>","DOI":"10.1093\/comjnl\/bxab106","type":"journal-article","created":{"date-parts":[[2021,6,30]],"date-time":"2021-06-30T12:57:44Z","timestamp":1625057864000},"page":"1056-1068","source":"Crossref","is-referenced-by-count":4,"title":["Adaptive Cross-Lingual Question Generation with Minimal Resources"],"prefix":"10.1093","volume":"64","author":[{"given":"Jianxing","family":"Yu","sequence":"first","affiliation":[{"name":"Guangdong Key Laboratory of Big Data Analysis and Processing, Sun Yat-sen University, Guangzhou 510006, China; and Pazhou Lab, Guangzhou, 510330, China"}]},{"given":"Shiqi","family":"Wang","sequence":"additional","affiliation":[{"name":"Guangdong Key Laboratory of Big Data Analysis and Processing, Sun Yat-sen University, Guangzhou 510006, China; and Pazhou Lab, Guangzhou, 510330, China"}]},{"given":"Jian","family":"Yin","sequence":"additional","affiliation":[{"name":"Guangdong Key Laboratory of Big Data Analysis and Processing, Sun Yat-sen University, Guangzhou 510006, China; and Pazhou Lab, Guangzhou, 510330, China"}]}],"member":"286","published-online":{"date-parts":[[2021,7,19]]},"reference":[{"key":"2021103114301658400_ref1","first-page":"2614","article-title":"Learning to learn by gradient descent by gradient descent","volume-title":"Proceedings of the 29th NeurIPS","author":"Andrychowicz","year":"2016"},{"key":"2021103114301658400_ref2","first-page":"597","article-title":"Massively multilingual sentence embeddings for zero-shot cross-lingual transfer and beyond","volume-title":"Transactions of the Association for Computational Linguistics","author":"Artetxe","year":"2019"},{"key":"2021103114301658400_ref3","first-page":"124","article-title":"Neural machine translation by jointly learning to align and translate","volume-title":"Proceedings of the 3rd ICLR","author":"Bahdanau","year":"2015"},{"key":"2021103114301658400_ref4","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization","author":"Banerjee","year":"2005"},{"key":"2021103114301658400_ref5","first-page":"5070","article-title":"Meta multi-task learning for sequence modeling","volume-title":"Proceedings of the 32nd AAAI","author":"Chen","year":"2018"},{"key":"2021103114301658400_ref6","first-page":"5972","article-title":"Controllable paraphrase generation with a syntactic exemplar","volume-title":"Proceedings of the 57th ACL","author":"Chen","year":". 2019"},{"key":"2021103114301658400_ref7","first-page":"7682","article-title":"Cross-lingual natural language generation via pre-training","volume-title":"Proceedings of the 34th AAAI","author":"Chi","year":"2020"},{"key":"2021103114301658400_ref8","first-page":"1724","article-title":"Learning phrase representations using rnn encoder-decoder for statistical machine translation","volume-title":"Proceedings of the EMNLP","author":"Cho","year":"2014"},{"key":"2021103114301658400_ref9","first-page":"7057","article-title":"Cross-lingual language model pretraining","volume-title":"Proceedings of the 32th NeurIPS","author":"Conneau","year":"2019"},{"key":"2021103114301658400_ref10","first-page":"5883","article-title":"A span-extraction dataset for Chinese machine reading comprehension","volume-title":"Proceedings of the EMNLP","author":"Cui","year":"2019"},{"key":"2021103114301658400_ref11","first-page":"856","article-title":"Hyperspherical variational auto-encoders","volume-title":"Proceedings of the 34th AAAI","author":"Davidson","year":"2018"},{"key":"2021103114301658400_ref12","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of the NAACL","author":"Devlin","year":"2019"},{"key":"2021103114301658400_ref13","first-page":"2067","article-title":"Identifying where to focus in reading comprehension for neural question generation","volume-title":"Proceedings of the EMNLP","author":"Du","year":"2017"},{"key":"2021103114301658400_ref14","first-page":"866","article-title":"Question generation for question answering","volume-title":"Proceedings of the EMNLP","author":"Duan","year":"2017"},{"key":"2021103114301658400_ref15","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"Finn","year":"2017"},{"key":"2021103114301658400_ref16","first-page":"3168","article-title":"Reinforcement learning based text style transfer without parallel training corpus","volume-title":"Proceedings of the NAACL","author":"Gong","year":"2019"},{"key":"2021103114301658400_ref17","first-page":"723","article-title":"A kernel two-sample test","volume-title":"Journal of Machine Learning Research","author":"Gretton","year":"2012"},{"key":"2021103114301658400_ref18","first-page":"1631","article-title":"Incorporating copying mechanism in sequence-to-sequence learning","volume-title":"Proceedings of the 54th ACL","author":"Gu","year":". 2016"},{"key":"2021103114301658400_ref19","first-page":"855","article-title":"Coupling retrieval and meta-learning for context-dependent semantic parsing","volume-title":"Proceedings of the 57th ACL","author":"Guo","year":"2019"},{"key":"2021103114301658400_ref20","article-title":"A retrieve-and-edit framework for predicting structured outputs","volume-title":"Proceedings of the 31st NeurIPS","author":"Hashimoto","year":"2018"},{"key":"2021103114301658400_ref21","first-page":"732","article-title":"Natural language to structured query generation via meta-learning","volume-title":"Proceedings of the NAACL","author":"Huang","year":"2018"},{"key":"2021103114301658400_ref22","article-title":"Automatic english question generation system based on template driven scheme","volume-title":"Journal of Computer Science","author":"Hussein","year":"2014"},{"key":"2021103114301658400_ref23","first-page":"6602","article-title":"Improving neural question generation using answer separation","volume-title":"Proceedings of the 33th AAAI","author":"Kim","year":"2019"},{"key":"2021103114301658400_ref24","first-page":"1746","article-title":"Convolutional neural networks for sentence classification","volume-title":"Proceedings of the EMNLP, Doha, Qatar","author":"Kim","year":". 2014"},{"key":"2021103114301658400_ref25","first-page":"324","article-title":"Adam: A method for stochastic optimization","volume-title":"Proceedings of the 3rd ICLR","author":"Kingma","year":"2015"},{"key":"2021103114301658400_ref26","first-page":"2014","article-title":"Auto-encoding variational bayes","volume-title":"Proceedings of the 2nd ICLR","author":"Kingma"},{"key":"2021103114301658400_ref27","first-page":"4863","article-title":"Cross-lingual training for automatic question generation","volume-title":"Proceedings of the 57th ACL","author":"Kumar","year":". 2019"},{"key":"2021103114301658400_ref28","first-page":"812","article-title":"Putting the horse before the cart: A generator-evaluator framework for question generation from text","volume-title":"Proceedings of the 23rd CoNLL","author":"Kumar","year":". 2019"},{"key":"2021103114301658400_ref29","article-title":"Korquad1.0: Korean qa dataset for machine reading comprehension","volume-title":"arXiv:1909.07005","author":"Lim","year":"2019"},{"key":"2021103114301658400_ref30","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Text Summarization Branches Out","author":"Lin","year":"2004"},{"key":"2021103114301658400_ref31","first-page":"105","article-title":"Generating natural language questions to support learning on-line","volume-title":"Proceedings of the 14th European Workshop on Natural Language Generation","author":"Lindberg","year":"2013"},{"key":"2021103114301658400_ref32","first-page":"55","article-title":"The Stanford CoreNLP natural language processing toolkit","volume-title":"Proceedings of 52nd ACL: System Demonstrations","author":"Manning","year":". 2014"},{"key":"2021103114301658400_ref33","first-page":"3151","article-title":"Meta-learning for low-resource natural language generation in task-oriented dialogue systems","volume-title":"Proceedings of the 28th AAAI","author":"Mi","year":"2019"},{"key":"2021103114301658400_ref34","first-page":"462","article-title":"Image-grounded conversations: Multimodal context for natural question and response generation","volume-title":"Proceedings of the 8th IJCNLP","author":"Mostafazadeh","year":"2017"},{"key":"2021103114301658400_ref35","first-page":"429","article-title":"Integral probability metrics and their generating classes of functions","volume-title":"Journal of Advances in Applied Probability","author":"Muller","year":". 1997"},{"key":"2021103114301658400_ref36","first-page":"3950","article-title":"Towards a better metric for evaluating question generation systems","volume-title":"Proceedings of the EMNLP","author":"Nema","year":"2018"},{"key":"2021103114301658400_ref37","first-page":"311","article-title":"Bleu: a method for automatic evaluation of machine translation","volume-title":"Proceedings of the 40th ACL","author":"Papineni","year":"2002"},{"key":"2021103114301658400_ref38","first-page":"8026","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume-title":"Journal of Advances in Neural Information Processing Systems","author":"Paszke","year":"2019"},{"key":"2021103114301658400_ref39","article-title":"A deep reinforced model for abstractive summarization","volume-title":"arXiv:1705.04304","author":"Paulus","year":"2017"},{"key":"2021103114301658400_ref40","first-page":"2383","article-title":"SQuAD: 100,000+ questions for machine comprehension of text","author":"Rajpurkar","year":"2016","journal-title":"Proceedings of the EMNLP, Austin, Texas, Nov."},{"key":"2021103114301658400_ref41","article-title":"Free-marginal multirater kappa (multirater kfree): An alternative to fleiss\u2019 fixed- marginal multirater kappa","volume-title":"Joensuu Learning and Instruction Symposium","author":"Randolph","year":"2005"},{"key":"2021103114301658400_ref42","first-page":"7008","article-title":"Self-critical sequence training for image captioning","volume-title":"Proceedings of the 30th IEEE CVPR","author":"Rennie","year":"2017"},{"key":"2021103114301658400_ref43","first-page":"2019","article-title":"Meta-learning with latent embedding optimization","volume-title":"Proceedings of the 7th ICLR","author":"Rusu"},{"key":"2021103114301658400_ref44","first-page":"732","article-title":"Trust region policy optimization","volume-title":"Proceedings of the 32nd ICML","author":"Schulman","year":"2015"},{"key":"2021103114301658400_ref45","first-page":"3795","article-title":"Cross-lingual transfer learning for multilingual task oriented dialog","volume-title":"Proceedings of the NAACL","author":"Schuster","year":"2019"},{"key":"2021103114301658400_ref46","article-title":"DRCD: a chinese machine reading comprehension dataset","author":"Shao","year":"2018"},{"key":"2021103114301658400_ref47","article-title":"Relevance of unsupervised metrics in task-oriented dialogue for evaluating natural language generation","author":"Sharma","year":"2017"},{"key":"2021103114301658400_ref48","first-page":"2079","article-title":"Towards generating long and coherent text with multi-level latent variable models","volume-title":"Proceedings of the 57th ACL","author":"Shen","year":". 2019"},{"key":"2021103114301658400_ref49","first-page":"569","article-title":"Leveraging context information for natural question generation","volume-title":"Proceedings of the NAACL","author":"Song","year":"2018"},{"key":"2021103114301658400_ref50","first-page":"1550","article-title":"On the empirical estimation of integral probability metrics","volume-title":"E-Journal of Statistics","author":"Sriperumbudur","year":". 2012"},{"key":"2021103114301658400_ref51","first-page":"78","article-title":"Neural models for key phrase extraction and question generation","volume-title":"Proceedings of the 56th ACL","author":"Subramanian","year":"2018"},{"key":"2021103114301658400_ref52","first-page":"1199","article-title":"Learning to compare: Relation network for few-shot learning","volume-title":"Proceedings of the 31th IEEE CVPR","author":"Sung","year":"2018"},{"key":"2021103114301658400_ref53","first-page":"477","article-title":"Cross-lingual word clusters for direct transfer of linguistic structure","volume-title":"Proceedings of the NAACL","author":"T\u00e4ckstr\u00f6m","year":". 2012"},{"key":"2021103114301658400_ref54","first-page":"1556","article-title":"Improved semantic representations from tree-structured long short-term memory networks","volume-title":"Proceedings of the 53rd ACL","author":"Tai","year":". 2015"},{"key":"2021103114301658400_ref55","first-page":"219","article-title":"Cross-lingual named entity recognition via wikification","volume-title":"Proceedings of The 20th SIGNLL","author":"Tsai","year":". 2016"},{"key":"2021103114301658400_ref56","first-page":"607","article-title":"Robust cross-lingual hypernymy detection using dependency context","volume-title":"Proceedings of the NAACL","author":"Upadhyay","year":"2018"},{"key":"2021103114301658400_ref57","first-page":"360","article-title":"Understanding interobserver agreement: the kappa statistic","volume-title":"Journal of Fam Med","author":"Viera","year":"2005"},{"key":"2021103114301658400_ref58","first-page":"2692","article-title":"Pointer networks","volume-title":"Proceedings of the 28th NeurIPS","author":"Vinyals","year":"2015"},{"key":"2021103114301658400_ref59","first-page":"1705","article-title":"Gated self-matching networks for reading comprehension and question answering","volume-title":"Proceedings of the 55th ACL","author":"Wang","year":"2017"},{"key":"2021103114301658400_ref60","first-page":"229","article-title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning","volume-title":"Journal of Machine Learning","author":"Williams","year":"1992"},{"key":"2021103114301658400_ref61","first-page":"5015","article-title":"Enhanced meta-learning for cross-lingual named entity recognition with minimal resources","volume-title":"Proceedings of the 34th AAAI Conference on Artificial","author":"Wu","year":"2020"},{"key":"2021103114301658400_ref62","first-page":"833","article-title":"Beto, bentz, becas: The surprising cross-lingual effectiveness of BERT","volume-title":"Proceedings of the EMNLP-IJCNLP","author":"Wu","year":"2019"},{"key":"2021103114301658400_ref63","article-title":"Google\u2019s neural machine translation system: Bridging the gap between human and machine translation","author":"Wu","year":"2016"},{"key":"2021103114301658400_ref64","first-page":"4503","article-title":"Spherical latent spaces for stable variational autoencoders","volume-title":"Proceedings of the EMNLP","author":"Xu","year":"2018"},{"key":"2021103114301658400_ref65","first-page":"6729","article-title":"Low-resource generation of multi-hop reasoning questions","volume-title":"Proceedings of the 58th ACL","author":"Yu","year":"2020"},{"key":"2021103114301658400_ref66","doi-asserted-by":"crossref","first-page":"550","DOI":"10.1145\/3366423.3380114","article-title":"Generating multi-hop reasoning questions to improve machine reading comprehension","volume-title":"Proceedings of the WWW","author":"Yu","year":"2020"},{"key":"2021103114301658400_ref67","first-page":"2241","article-title":"Inferential machine comprehension: Answering questions by recursively deducing the evidence chain from text","volume-title":"Proceedings of the 57th ACL","author":"Yu","year":"2019"},{"key":"2021103114301658400_ref68","first-page":"584","article-title":"Sentence simplification with deep reinforcement learning","volume-title":"Proceedings of the EMNLP","author":"Zhang","year":"2017"},{"key":"2021103114301658400_ref69","first-page":"487","article-title":"A novel framework for automatic chinese question generation based on multi-feature neural network model","volume-title":"Journal of Computer Science and Information Systems","author":"Zheng","year":"2018"},{"key":"2021103114301658400_ref70","first-page":"390","article-title":"Cross-lingual transfer of named entity recognizers without parallel corpora","volume-title":"Proceedings of the 53rd ACL-IJCNLP","author":"Zirikly","year":". 2015"}],"container-title":["The Computer Journal"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/comjnl\/article-pdf\/64\/7\/1056\/40979374\/bxab106.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/academic.oup.com\/comjnl\/article-pdf\/64\/7\/1056\/40979374\/bxab106.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,31]],"date-time":"2021-10-31T14:31:08Z","timestamp":1635690668000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/comjnl\/article\/64\/7\/1056\/6323599"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7]]},"references-count":70,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2021,7,19]]},"published-print":{"date-parts":[[2021,8,24]]}},"URL":"https:\/\/doi.org\/10.1093\/comjnl\/bxab106","relation":{},"ISSN":["0010-4620","1460-2067"],"issn-type":[{"value":"0010-4620","type":"print"},{"value":"1460-2067","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2021,7]]},"published":{"date-parts":[[2021,7]]}}}