Abstract: Natural Language Generation (NLG) technologies use artificial intelligence and linguistic methods to automatically generate understandable natural language texts. The difficulty of communication between human and computer is reduced by NLG, which is widely used in machine news writing, chatbot and other fields, and has become one of the research hotspots of artificial intelligence. Firstly, the current mainstream methods and models of NLG were listed, and the advantages and disadvantages of these methods and models were compared in detail. Then, aiming at three NLG technologies:text-to-text, data-to-text and image-to-text, the application fields, existing problems and current research progresses were summarized and analyzed respectively. Furthermore, the common evaluation methods and their application scopes of the above generation technologies were described. Finally, the development trends and research difficulties of NLG technologies were given.

Key words: Natural Language Generation (NLG), linguistics, natural language processing, evaluation method, text-to-text generation, data-to-text generation, image-to-text generation [1] REITER E,DALE R. Building natural language generation systems[J]. Computational Lingus,2001,27(2):298-300.
[2] DAY C. Robot science writers[J]. Computing in Science and Engineering,2018,20(3):101-101.
[3] JING B,XIE P,XING E. On the automatic generation of medical imaging reports[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA:Association for Computational Linguistics,2018:2577-2586.
[4] GOLDBERG E,DRIEDGER N,KITTREDGE R I. Using naturallanguage processing to produce weather forecasts[J]. IEEE Expert, 1994,9(2):45-53.
[5] ZHANG B,XIONG D,SU J. Neural machine translation with deep attention[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2020,42(1):154-163.
[6] LI X,CHEN Y N,LI L,et al. End-to-end task-completion neural dialogue systems[C/OL]//Proceedings of the 8th International Joint Conference on Natural Language Processing.[2020-05-03]. https://www.aclweb.org/anthology/I17-1074.pdf.
[7] VAN DEEMTER K,THEUNE M,KRAHMER E. Real versus template-based natural language generation:a false opposition[J]. Computational Linguistics,2005,31(1):15-24.
[8] CULLEN C,O' NEILL I,HANNA P. Flexible natural language generation in multiple contexts[C]//Proceedings of the 3rd Language and Technology Conference, LNCS 5603. Berlin:Springer,2009:142-153.
[9] ZHANG Y,YAO Q,DAI W,et al. AutoSF:searching scoring functions for knowledge graph embedding[C]//Proceedings of the IEEE 36th International Conference on Data Engineering. Piscataway:IEEE,2020:433-444.
[10] SUTSKEVER I,VINYALS O,LE Q V. Sequence to sequence learning with neural networks[C]//Proceedings of the 27th International Conference on Neural Information Processing Systems. Cambridge:MIT Press,2014:3104-3112.
[11] REITER E. A structured review of the validity of BLEU[J]. Computational Linguistics,2018,44(3):393-401.
[12] 李强, 黄辉, 周沁, 等. 模板驱动的神经机器翻译[J]. 计算机学报,2019,42(3):566-581.(LI Q,WONG F,CHAO S,et al. Template-driven neural machine translation[J]. Chinese Journal of Computers,2019,42(3):566-581.)
[13] BROWN P F,PIETRA S A D,PIETRA V J D,et al. The mathematics of statistical machine translation:parameter estimation[J]. Computational Linguistics, 1993, 19(2):263-311.
[14] BANNARD C, CALLISON-BURCH C. Paraphrasing with bilingual parallel corpora[C]//Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA:Association for Computational Linguistics, 2005:597-604.
[15] KALCHBRENNER N, BLUNSOM P. Recurrent continuous translation models[C]//Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing. Stroudsburg, PA:Association for Computational Linguistics,2013:1700-1709.
[16] BAHDANAU D,CHO K,BENGIO Y. Neural machine translation by jointly learning to align and translate[EB/OL].[2020-06-03]. https://arxiv.org/pdf/1409.0473.pdf.
[17] NARAYAN S,COHEN S B,LAPATA M. Ranking sentences for extractive summarization with reinforcement learning[C]//Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies. Stroudsburg,PA:Association for Computational Linguistics,2018:1747-1759.
[18] JADHAV A,RAJAN V. Extractive summarization with SWAPNET:sentences and words from alternating pointer networks[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA:Association for Computational Linguistics,2018:142-151.
[19] LAHA A,JAIN P,MISHRA A,et al. Scalable micro-planned generation of discourse from structured data[J]. Computational Linguistics,2019,45(4):737-763.
[20] SIDDHARTHAN A. A survey of research on text simplification[J]. International Journal of Applied Linguistics,2014,165(2):259-298.
[21] COSTER W,KAUCHAK D. Simple English Wikipedia:a new text simplification task[C]//Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics:Human Language Technologies. Stroudsburg, PA:Association for Computational Linguistics,2011:665-669.
[22] 徐戈, 王厚峰. 自然语言处理中主题模型的发展[J]. 计算机学报,2011,34(8):1423-1436. (XU G,WANG H F. The development of topic models in natural language processing[J]. Chinese Journal of Computers,2011,34(8):1423-1436.)
[23] ORABY S,HARRISON V,EBRAHIMI A,et al. Curate and generate:a corpus and method for joint control of semantics and style in neural NLG[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA:Association for Computational Linguistics,2019:5938-5951.
[24] DUBOUE P A,MCKEOWN K R. Statistical acquisition of content selection rules for natural language generation[C]//Proceedings of the 2003 Conference on Empirical Methods in Natural Language Processing. Stroudsburg, PA:Association for Computational Linguistics,2003:121-128.
[25] GONG J,REN W,ZHANG P. An automatic generation method of sports news based on knowledge rules[C]//Proceedings of the IEEE/ACIS 16th International Conference on Computer and Information Science. Piscataway:IEEE,2017:499-502.
[26] DUŠEK O,NOVIKOVA J,RIESER V. Evaluating the state-ofthe-art of end-to-end natural language generation:the E2E NLG challenge[J]. Computer Speech and Language, 2020, 59:123-156.
[27] MEI H,BANSAL M,WALTER M R. What to talk about and how? Selective generation using LSTMs with coarse-to-fine alignment[C]//Proceedings of the 2016 North American Chapter of the Association for Computational Linguistics:Human Language Technologies. Stroudsburg,PA:Association for Computational Linguistics,2016:720-730.
[28] PUDUPPULLY R,DONG L,LAPATA M. Data-to-text generation with content selection and planning[C]//Proceedings of the 33rd National Conference on Artificial Intelligence. Palo Alto,CA:AAAI Press,2019:6908-6915.
[29] BENGIO Y,DUCHARME R,VINCENT P,et al. A neural probabilistic language model[J]. Journal of Machine Learning Research,2003,3:1137-1155.
[30] YANG P, LI L, LUO F, et al. Enhancing topic-to-essay generation with external commonsense knowledge[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA:Association for Computational Linguistics,2019:2002-2012.
[31] REITER E,SRIPADA S,HUNTER J,et al. Choosing words in computer-generated weather forecasts[J]. Artificial Intelligence, 2005,167(1/2):137-169.
[32] LIANG P, JORDAN M I, KLEIN D. Learning semantic correspondences with less supervision[C]//Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL/the 4th International Joint Conference on Natural Language Processing of the AFNLP. Stroudsburg, PA:Association for Computational Linguistics,2009:91-99.
[33] CHEN D L,MOONEY R J. Learning to sportscast:a test of grounded language acquisition[C]//Proceedings of the 25th International Conference on Machine Learning. New York:ACM, 2008:128-135.
[34] BARZILAY R, LAPATA M. Collective content selection for concept-to-text generation[C]//Proceedings of the 2005 Human Language Technology Conference/Conference on Empirical Methods in Natural Language Processing. Stroudsburg, PA:Association for Computational Linguistics,2005:331-338.
[35] WISEMAN S,SHIEBER S M,RUSH A M. Challenges in data-todocument generation[C]//Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. Stroudsburg, PA:Association for Computational Linguistics,2017:2253-2263.
[36] DAHL D A,BATES M,BROWN M,et al. Expanding the scope of the ATIS task:the ATIS-3 corpus[C]//Proceedings of the 1994 Workshop on Human Language Technology. Stroudsburg,PA:Association for Computational Linguistics,1994:43-48.
[37] LEBRET R,GRANGIER D,AULI M. Neural text generation from structured data with application to the biography domain[C]//Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. Stroudsburg,PA:Association for Computational Linguistics,2016:1741-1752.
[38] YAO B Z,YANG X,LIN L,et al. I2T:image parsing to text description[J]. Proceedings of the IEEE,2010,98(8):1485-1508.
[39] 莫凌波. 基于图像的文本自动生成关键技术研究[D]. 北京:北京邮电大学,2019:6-8. (MO L B. Research on key technologies of automatic text generation based on images[D]. Beijing:Beijing University of Posts and Telecommunications, 2019:6-8.)
[40] FARHADI A,ENDRES I,HOIEM D,et al. Describing objects by their attributes[C]//Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2009:1778-1785.
[41] 孔锐, 谢玮, 雷泰. 基于神经网络的图像描述方法研究[J]. 系统仿真学报,2020,32(4):601-611.(KONG R,XIE W,LEI T. Research on image description method based on neural network[J]. Journal of System Simulation,2020,32(4):601-611.)
[42] LI C Y,LIANG X,HU Z,et al. Hybrid retrieval-generation reinforced agent for medical image report generation[C]//Proceedings of the 32nd International Conference on Neural Information Processing Systems. Red Hook, NY:Curran Associates Inc.,2018:1537-1547.
[43] REN Z,WANG X Y,ZHANG N,et al. Deep reinforcement learning-based imagecaptioning with embedding reward[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2017:1151-1159.
[44] RENNIE S J,MARCHERET E,MROUEH Y,et al. Self-critical sequence training for image captioning[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2017:7008-7024.
[45] LOPEZ-GAZPIO I,MARITXALAR M,LAPATA M,et al. Word n-gram attention models for sentence similarity and inference[J]. Expert Systems with Applications,2019,132:1-11.
[46] DENKOWSKI M,LAVIE A. Meteor universal:language specific translation evaluation for any target language[C]//Proceedings of the 9th Workshop on Statistical Machine Translation. Stroudsburg, PA:Association for Computational Linguistics, 2014:376-380.
[47] LIN C Y,HOVY E. Automatic evaluation of summaries using Ngram co-occurrence statistics[C/OL]//Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology.[2020-05-03]. https://www.aclweb.org/anthology/N03-1020.pdf.
[48] NOVIKOVA J,DUSEK O,CURRY A C,et al. Why we need new evaluation metrics for NLG[C]//Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. Stroudsburg, PA:Association for Computational Linguistics, 2017:2241-2252.