問題生成是數年來研究人數不斷增加的領域，教育者想透過機器學習與人工智慧，找到更簡單產生試卷的方法。在這篇論文中，我們探究了轉換器模型是如何利用樣本段落進行推論，並自動產生端對端的提問。這個模型使用端對端的方法訓練，會針對文本段落處理，在理解各句子後，再產生提問。而這些問題的答案並不直接出現在文本之中。言談分析與重述技巧是用來找出隱藏句子的一種推論方法，將資料輸入調校好的模型，即可從新句子或隱藏句子中產生提問。史丹佛的語法剖析器也被運用來特別針對句中的動詞、代名詞，及其他關鍵單元，以取得更清楚的文章全貌。我們在SQuAD 1.1資料集上進行文本段落的研究，先輸入原始段落，再經由推論規則轉換。所有句子轉換後，我們將這些縮減的段落輸進轉換器模型，以產生具更深理解程度的提問。分析及結果顯示，比起之前研究中較簡單、能從輸入段落裡找到答案的問題來說，這個模型能夠產生更深層的提問。重述及語法剖析的運用，及其創造和產生對於段落的推論，有望助於模型理解文章更深的涵義。

Question Generation is a field of research that has been growing in popularity through the years, as educators seek to find ways to make test generation a lot easier with the use of Machine Learning and Artificial Intelligence. In this paper we research how automated end-to-end question generation that utilizes transformers will generate an understandable question by making an inference on sample paragraphs. The model is trained in an end-to-end approach where the model focuses on the context paragraph to understand the sentences and generate a question where the answer is not directly in the context paragraph. An inference approach is proposed to find hidden sentences by using discourse analysis and paraphrasing techniques based on fine tuning transformers to be fed into a model that can generate a question from the hidden or new sentences. The Stanford parser was also utilized to get a clearer view of the parts of speech focusing particularly on the verbs, pronouns, and other key entities in the sentence. Experiments on the context paragraphs was conducted on the SQuAD 1.1 dataset where we attempted to transform the original input paragraphs using the inference rule. After transforming all sentences, we then fed these new shortened paragraphs to the transformer model to generate a deeper level understanding question. The analysis results show that the model was able to generate questions of a deeper level than a simple one from previous research where the answer can be found in the input paragraph. Paraphrasing and utilizing parsers to create and conduct an inference on the sentences seemed to help the model to generate on a deeper level.

1] N. A. Smith and M. Heilman, “Automatic factual question generation from text,” 2011.

[2] X. Du, J. Shao, and C. Cardie, “Learning to ask: Neural question generation for reading compre-hension,” 2017.

[3] P. Rajpurkar, R. Jia, and P. Liang, “Know what you don’t know: Unanswerable questions for squad,”2018.

[4] L. E. Lopez, D. K. Cruz, J. C. B. Cruz, and C. Cheng, “Transformer-based end-to-end questiongeneration,”ArXiv, vol. abs/2005.01107, 2020.

[5] P. Rajpurkar, J. Zhang, K. Lopyrev, and P. Liang, “Squad: 100,000+ questions for machine com-prehension of text,” 2016.

[6] K. Kriangchaivech and A. Wangperawong, “Question generation by transformers,” 2019.

[7] T. Klein and M. Nabi, “Learning to answer by learning to ask: Getting the best of gpt-2 and bertworlds,” 2019.

[8] J. Qiu and D. Xiong, “Generating highly relevant questions,” 2019.

[9] A. Radford, J. Wu, R. Child, D. Luan, D. Amodei, and I. Sutskever, “Language models are unsu-pervised multitask learners,” 2019.

[10] J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “Bert: Pre-training of deep bidirectional trans-formers for language understanding,” 2019.43

[11] C. Raffel, N. Shazeer, A. Roberts, K. Lee, S. Narang, M. Matena, Y. Zhou, W. Li, and P. J. Liu,“Exploring the limits of transfer learning with a unified text-to-text transformer,” 2020.

[12] A. LW, K. DR, A. PW, C. KA, R. Mayer, P. PR, J. Raths, and W. MC,A Taxonomy for Learning,Teaching, and Assessing: A Revision of Bloom’s Taxonomy of Educational Objectives. 01 2001.

[13] V. Rus, B. Wyse, P. Piwek, M. Lintean, S. Stoyanchev, and C. Moldovan, “The first question gen-eration shared task evaluation challenge,” inProceedings of the 6th International Natural LanguageGeneration Conference, 2010.

[14] A. Andrenucci and E. Sneiders, “Automated question answering: Review of the main approaches.,”pp. 514–519, 01 2005.

[15] W. Wang, T. Hao, and W. Liu, “Automatic question generation for learning evaluation in medicine,”vol. 4823, pp. 242–251, 08 2007.

[16] W. Chen and G. Aist, “Generating questions automatically from informational text,” 2009.

[17] J. Brown, G. Frishkoff, and M. Eskenazi, “Automatic question generation for vocabulary assessment,”inProceedings of Human Language Technology Conference and Conference on Empirical Methods inNatural Language Processing, (Vancouver, British Columbia, Canada), pp. 819–826, Association forComputational Linguistics, Oct. 2005.

[18] X. Du and C. Cardie, “Harvesting paragraph-level question-answer pairs from Wikipedia,” inPro-ceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1:Long Papers), (Melbourne, Australia), pp. 1907–1917, Association for Computational Linguistics,July 2018.

[19] L. Dong, N. Yang, W. Wang, F. Wei, X. Liu, Y. Wang, J. Gao, M. Zhou, and H.-W. Hon, “Unifiedlanguage model pre-training for natural language understanding and generation,” 2019.

[20] Y. Zhao, X. Ni, Y. Ding, and Q. Ke, “Paragraph-level neural question generation with maxout pointerand gated self-attention networks,” inProceedings of the 2018 Conference on Empirical Methods inNatural Language Processing, (Brussels, Belgium), pp. 3901–3910, Association for ComputationalLinguistics, Oct.-Nov. 2018.44

[21] A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin,“Attention is all you need,” 2017.

[22] Y. Chen, L. Wu, and M. J. Zaki, “Reinforcement learning based graph-to-sequence model for naturalquestion generation,” 2020.

[23] P. Rajpukar, J. Shang, K. Lopyrev, and P. Liang, “The stanford question answer dataset explorer,”2016.

[24] C. Manning, “Generating typed dependency parses from phrase structure parses.” 2006.

[25] J. Zhang, Y. Zhao, M. Saleh, and P. J. Liu, “Pegasus: Pre-training with extracted gap-sentences forabstractive summarization,” 2020.

[26] J. Vig, “A multiscale visualization of attention in the transformer model,” inProceedings of the57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations,(Florence, Italy), pp. 37–42, Association for Computational Linguistics, July 2019.

[27] M. Gardner, J. Grus, M. Neumann, O. Tafjord, P. Dasigi, N. F. Liu, M. Peters, M. Schmitz, andL. S. Zettlemoyer, “Allennlp: A deep semantic natural language processing platform,” 2017.

[28] T. Hosking and S. Riedel, “Evaluating rewards for question generation models,” inProceedings ofthe 2019 Conference of the North American Chapter of the Association for Computational Linguis-tics: Human Language Technologies, Volume 1 (Long and Short Papers), (Minneapolis, Minnesota),pp. 2278–2283, Association for Computational Linguistics, June 2019.

[29] K. Stasaski, M. Rathod, T. Tu, Y. Xiao, and M. A. Hearst, “Automatically generating cause-and-effect questions from passages,” inProceedings of the 16th Workshop on Innovative Use of NLP forBuilding Educational Applications, (Online), pp. 158–170, Association for Computational Linguistics,Apr. 2021.

[30] Y.-H. Chan and Y.-C. Fan, “A recurrent BERT-based model for question generation,” inProceedingsof the 2nd Workshop on Machine Reading for Question Answering, (Hong Kong, China), pp. 154–162, Association for Computational Linguistics, Nov. 2019.45

[31] P. Nema and M. M. Khapra, “Towards a better metric for evaluating question generation systems,” inProceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, (Brussels,Belgium), pp. 3950–3959, Association for Computational Linguistics, Oct.-Nov. 2018.

[32] D. Klein and C. D. Manning, “Accurate unlexicalized parsing,” inProceedings of the 41st AnnualMeeting of the Association for Computational Linguistics, (Sapporo, Japan), pp. 423–430, Associa-tion for Computational Linguistics, July 2003.

[33] M. Heilman and N. A. Smith, “Good question! statistical ranking for question generation,” inHuman Language Technologies: The 2010 Annual Conference of the North American Chapter of theAssociation for Computational Linguistics, (Los Angeles, California), pp. 609–617, Association forComputational Linguistics, June 2010.

[34] L. Pan, W. Lei, T.-S. Chua, and M.-Y. Kan, “Recent advances in neural question generation,” 2019.

[35] M. Agarwal, R. Shah, and P. Mannem, “Automatic question generation using discourse cues,” inProceedings of the Sixth Workshop on Innovative Use of NLP for Building Educational Applications,(Portland, Oregon), pp. 1–9, Association for Computational Linguistics, June 2011.

[36] V. Kumar, R. Chaki, S. T. Talluri, G. Ramakrishnan, Y.-F. Li, and G. Haffari, “Question generationfrom paragraphs: A tale of two hierarchical models,” 2019.