ABSTRACT
Automatically generating controllable and diverse mathematical word problems (MWPs) which conform to equations and topics is a crucial task in information retrieval and natural language generation. Recent deep learning models mainly focus on improving the problem readability but overlook the mathematical logic coherence, which tends to generate unsolvable problems. In this paper, we draw inspiration from the human problem-designing process and propose a Mathematical structure Planning and Knowledge enhanced Generation model (MaPKG), following the "plan-then-generate" steps. Specifically, we propose a novel dynamic planning module to make sentence-level equation plans and a dual-attention mechanism for word-level generation, incorporating equation structure representation and external commonsense knowledge. Extensive experiments on two MWP datasets show our model can guarantee more solvable, high-quality, and diverse problems. Our code is available at https://github.com/KenelmQLH/MaPKG.git
- Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2014. Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014).Google Scholar
- Tianyang Cao, Shuang Zeng, Xiaodan Xu, Mairgup Mansur, and Baobao Chang. 2022. DISK: Domain-constrained Instance Sketch for Math Word Problem Generation. arXiv preprint arXiv:2204.04686 (2022).Google Scholar
- Tianyang Cao, Shuang Zeng, Songge Zhao, Mairgup Mansur, and Baobao Chang. 2021. Generating math word problems from equations with topic consistency maintaining and commonsense enforcement. In Artificial Neural Networks and Machine Learning-ICANN 2021: 30th International Conference on Artificial Neural Networks, Bratislava, Slovakia, September 14-17, 2021, Proceedings, Part III 30. Springer, 66--79.Google ScholarDigital Library
- Jian Guan, Xiaoxi Mao, Changjie Fan, Zitao Liu, Wenbiao Ding, and Minlie Huang. 2021. Long Text Generation by Modeling Sentence-Level and Discourse-Level Coherence. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). Association for Computational Linguistics, Online, 6379--6393. https://doi.org/10.18653/v1/2021.acl-long.499Google ScholarCross Ref
- Zhe Hu, Hou Pong Chan, Jiachen Liu, Xinyan Xiao, Hua Wu, and Lifu Huang. 2022. PLANET: Dynamic Content Planning in Autoregressive Transformers for Long-form Text Generation. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, Dublin, Ireland, 2288--2305. https://doi.org/10.18653/v1/2022.acl-long.163Google ScholarCross Ref
- Zhenya Huang, Xin Lin, Hao Wang, Qi Liu, Enhong Chen, Jianhui Ma, Yu Su, and Wei Tong. 2021. Disenqnet: Disentangled representation learning for educational questions. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. 696--704.Google ScholarDigital Library
- Zhenya Huang, Qi Liu, Weibo Gao, Jinze Wu, Yu Yin, Hao Wang, and Enhong Chen. 2020. Neural mathematical solver with enhanced formula structure. In Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. 1729--1732.Google ScholarDigital Library
- Nabila Ahmed Khodeir, Hanan Elazhary, and Nayer Wanas. 2018. Generating story problems via controlled parameters in a web-based intelligent tutoring system. The International Journal of Information and Learning Technology, Vol. 35, 3 (2018), 199--216.Google ScholarCross Ref
- Ghader Kurdi, Jared Leo, Bijan Parsia, Uli Sattler, and Salam Al-Emari. 2020. A systematic review of automatic question generation for educational purposes. International Journal of Artificial Intelligence in Education, Vol. 30 (2020), 121--204.Google ScholarCross Ref
- Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Ves Stoyanov, and Luke Zettlemoyer. 2019. Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv preprint arXiv:1910.13461 (2019).Google Scholar
- Junyi Li, Wayne Xin Zhao, Zhicheng Wei, Nicholas Jing Yuan, and Ji-Rong Wen. 2021b. Knowledge-based review generation by coherence enhanced text planning. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. 183--192.Google ScholarDigital Library
- Yujia Li, Daniel Tarlow, Marc Brockschmidt, and Richard Zemel. 2015. Gated graph sequence neural networks. arXiv preprint arXiv:1511.05493 (2015).Google Scholar
- Zekang Li, Jinchao Zhang, Zhengcong Fei, Yang Feng, and Jie Zhou. 2021a. Conversations Are Not Flat: Modeling the Dynamic Information Flow across Dialogue Utterances. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). Association for Computational Linguistics, Online, 128--138. https://doi.org/10.18653/v1/2021.acl-long.11Google ScholarCross Ref
- Xin Lin, Zhenya Huang, Hongke Zhao, Enhong Chen, Qi Liu, Hao Wang, and Shijin Wang. 2021. Hms: A hierarchical solver with dependency-enhanced understanding for math word problem. In Proceedings of the AAAI conference on artificial intelligence, Vol. 35. 4232--4240.Google ScholarCross Ref
- Jiayu Liu, Zhenya Huang, Xin Lin, Qi Liu, Jianhui Ma, and Enhong Chen. 2022. A Cognitive Solver with Autonomously Knowledge Learning for Reasoning Mathematical Answers. In 2022 IEEE International Conference on Data Mining (ICDM). IEEE, 269--278.Google ScholarCross Ref
- Jiayu Liu, Zhenya Huang, Chengxiang Zhai, and Qi Liu. 2023. Learning by Applying: A General Framework for Mathematical Reasoning via Enhancing Explicit Knowledge Learning. arXiv preprint arXiv:2302.05717 (2023).Google Scholar
- Tianqiao Liu, Qiang Fang, Wenbiao Ding, Hang Li, Zhongqin Wu, and Zitao Liu. 2021. Mathematical Word Problem Generation from Commonsense Knowledge Graph and Equations (Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing). Association for Computational Linguistics, 4225--4240. https://doi.org/10.18653/v1/2021.emnlp-main.348Google ScholarCross Ref
- Oleksandr Polozov, Eleanor O'Rourke, Adam M Smith, Luke Zettlemoyer, Sumit Gulwani, and Zoran Popović. 2015. Personalized mathematical word problem generation. In Twenty-Fourth International Joint Conference on Artificial Intelligence.Google Scholar
- Ratish Puduppully, Li Dong, and Mirella Lapata. 2019. Data-to-text generation with content selection and planning. In Proceedings of the AAAI conference on artificial intelligence, Vol. 33. 6908--6915.Google ScholarDigital Library
- Jinghui Qin, Lihui Lin, Xiaodan Liang, Rumin Zhang, and Liang Lin. 2020. Semantically-Aligned Universal Tree-Structured Solver for Math Word Problems. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). Association for Computational Linguistics, Online, 3780--3789. https://doi.org/10.18653/v1/2020.emnlp-main.309Google ScholarCross Ref
- Yibin Shen, Qianying Liu, Zhuoyuan Mao, Zhen Wan, Fei Cheng, and Sadao Kurohashi. 2022. Seeking Diverse Reasoning Logic: Controlled Equation Expression Generation for Solving Math Word Problems. In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers). Association for Computational Linguistics, Online only, 254--260. https://aclanthology.org/2022.aacl-short.32Google Scholar
- Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, Vol. 30 (2017).Google Scholar
- Ke Wang and Zhendong Su. 2016. Dimensionally Guided Synthesis of Mathematical Word Problems.. In IJCAI. 2661--2668.Google Scholar
- Zichao Wang, Andrew Lan, and Richard Baraniuk. 2021. Math Word Problem Generation with Mathematical Consistency and Problem Context Constraints (Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing). Association for Computational Linguistics, 5986--5999. https://doi.org/10.18653/v1/2021.emnlp-main.484Google ScholarCross Ref
- Kai Zhang, Qi Liu, Hao Qian, Biao Xiang, Qing Cui, Jun Zhou, and Enhong Chen. 2023. EATN: An Efficient Adaptive Transfer Network for Aspect-Level Sentiment Analysis. IEEE Transactions on Knowledge and Data Engineering, Vol. 35, 1 (Jan 2023), 377--389. https://doi.org/10.1109/TKDE.2021.3075238Google ScholarCross Ref
- Kun Zhang, Guangyi Lv, Le Wu, Enhong Chen, Qi Liu, and Meng Wang. 2021. Ladra-net: Locally aware dynamic reread attention net for sentence semantic matching. IEEE Transactions on Neural Networks and Learning Systems (2021).Google Scholar
- Tiancheng Zhao, Ran Zhao, and Maxine Eskenazi. 2017. Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, Vancouver, Canada, 654--664. https://doi.org/10.18653/v1/P17-1061Google ScholarCross Ref
- Qingyu Zhou and Danqing Huang. 2019. Towards generating math word problems from equations and topics. In Proceedings of the 12th International Conference on Natural Language Generation. 494--503.Google ScholarCross Ref
- Yaoming Zhu, Sidi Lu, Lei Zheng, Jiaxian Guo, Weinan Zhang, Jun Wang, and Yong Yu. 2018. Texygen: A benchmarking platform for text generation models. In The 41st international ACM SIGIR conference on research & development in information retrieval. 1097--1100.Google ScholarDigital Library
Index Terms
- A Mathematical Word Problem Generator with Structure Planning and Knowledge Enhancement
Recommendations
Open-world story generation with structured knowledge enhancement: A comprehensive survey
AbstractStorytelling and narrative are fundamental to human experience, intertwined with our social and cultural engagement. As such, researchers have long attempted to create systems that can generate stories automatically. In recent years, powered by ...
Comments