{"type":"ScholarlyArticle","title":"A Goal-Driven Tree-Structured Neural Model for Math Word Problems","authors":[{"name":"Zhipeng Xie","slug":"zhipeng-xie","given":"Zhipeng","family":"Xie","affiliation":"Shanghai Key Laboratory of Data Science , Fudan University School of Computer Science , Fudan University"},{"name":"Shichao Sun","slug":"shichao-sun","given":"Shichao","family":"Sun","affiliation":"Shanghai Key Laboratory of Data Science , Fudan University School of Computer Science , Fudan University"}],"abstract":"Most existing neural models for math word problems exploit Seq2Seq model to generate solution expressions sequentially from left to right, whose results are far from satisfactory due to the lack of goal-driven mechanism commonly seen in human problem solving. This paper proposes a tree-structured neural model to generate expression tree in a goal-driven manner. Given a math word problem, the model first identifies and encodes its goal to achieve, and then the goal gets decomposed into sub-goals combined by an operator in a top-down recursive way. The whole process is repeated until the goal is simple enough to be realized by a known quantity as leaf node. During the process, two-layer gated-feedforward networks are designed to implement each step of goal decomposition, and a recursive neural network is used to encode fulfilled subtrees into subtree embeddings, which provides a better representation of subtrees than the simple goals of subtrees. Experimental results on the dataset Math23K have shown that our tree-structured model outperforms significantly several state-of-the-art models.","doi":"10.24963/ijcai.2019/736","url":"https://ijcai.org/proceedings/2019/736","pdf":"https://ijcai.org/proceedings/2019/0736.pdf","markdown":"https://ijcai.org/proceedings/2019/736.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/736","volume":{"slug":"2019","title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2019","url":"https://ijcai.org/proceedings/2019/","year":2019,"location":"Macao","dates":"10-16 August 2019","editors":"Sarit Kraus","isbn":"978-0-9992411-4-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2019"},"section":"Natural Language Processing","track":"Main track","number":736,"pages":{"first":5299,"last":5305},"keywords":["Machine Learning Applications: Applications of Supervised Learning","Natural Language Processing: Natural Language Processing","Machine Learning: Deep Learning"],"videos":[],"references":[{"position":1,"raw":"[Bakman, 2007] Yefim Bakman. Robust understanding of word problems with extraneous information. arXiv preprint math/0701393, 2007.","title":"Robust understanding of word problems with extraneous information","authors":"Yefim Bakman, Bakman","year":"2007","venue":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Cho et al., 2014] Kyunghyun Cho, Bart van Merrienboer, Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. Learning phrase representations using RNN encoder-decoder for statistical machine translation. pages 1724-1734, October 2014.","title":"Learning phrase representations using RNN encoder-decoder for statistical machine translation","authors":"Cho","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Fletcher, 1985] Charles R Fletcher. Understanding and solving arithmetic word problems: A computer simula- tion. Behavior Research Methods, Instruments, & Com- puters, 17(5):565-571, 1985.","title":"Understanding and solving arithmetic word problems: A computer simulation","authors":"Charles R Fletcher","year":"1985","venue":"Behavior Research Methods, Instruments, & Computers","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Hinton et al., 2012] Geoffrey E Hinton, Nitish Srivas- tava, Alex Krizhevsky, Ilya Sutskever, and Ruslan R Salakhutdinov. Improving neural networks by prevent- ing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580, 2012.","title":"Improving neural networks by preventing co-adaptation of feature detectors","authors":"Geoffrey E Hinton, Nitish Srivastava, Alex Krizhevsky, Ilya Sutskever, Ruslan R Salakhutdinov","year":"2012","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Huang et al., 2017] Danqing Huang, Shuming Shi, Chin- Yew Lin, and Jian Yin. Learning fine-grained expressions to solve math word problems. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 805-814, 2017.","title":"Learning fine-grained expressions to solve math word problems","authors":"Huang","year":"2017","venue":"Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Huang et al., 2018] Danqing Huang, Jing Liu, Chin-Yew Lin, and Jian Yin. Neural math word problem solver with reinforcement learning. In Proceedings of the 27th Inter- national Conference on Computational Linguistics, pages 213-223, 2018.","title":"Neural math word problem solver with reinforcement learning","authors":"Huang","year":"2018","venue":"Proceedings of the 27th International Conference on Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Kingma and Ba, 2014] Diederik P Kingma and Jimmy Ba. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.","title":"Adam: A method for stochastic optimization","authors":"P Diederik, Jimmy Kingma, Ba","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Koncel-Kedziorski et al., 2015] Rik Koncel-Kedziorski, Hannaneh Hajishirzi, Ashish Sabharwal, Oren Etzioni, and Siena Dumas Ang. Parsing algebraic word problems into equations. Transactions of the Association for Computational Linguistics, 3:585-597, 2015.","title":"Parsing algebraic word problems into equations","authors":"Rik Koncel-Kedziorski, Hannaneh Hajishirzi, Ashish Sabharwal, Oren Etzioni, Siena Dumas, Ang","year":"2015","venue":"Transactions of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Kushman et al., 2014] Nate Kushman, Yoav Artzi, Luke Zettlemoyer, and Regina Barzilay. Learning to automat- ically solve algebra word problems. In Proceedings of the 52nd Annual Meeting of the Association for Compu- tational Linguistics (Volume 1: Long Papers), volume 1, pages 271-281, 2014.","title":"Learning to automatically solve algebra word problems","authors":"Kushman","year":"2014","venue":"Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Ling et al., 2017] Wang Ling, Dani Yogatama, Chris Dyer, and Phil Blunsom. Program induction by rationale gener- ation: Learning to solve and explain algebraic word prob- lems. arXiv preprint arXiv:1705.04146, 2017.","title":"Program induction by rationale generation: Learning to solve and explain algebraic word problems","authors":"Wang Ling, Dani Yogatama, Chris Dyer, Phil Blunsom","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Mitra and Baral, 2016] Arindam Mitra and Chitta Baral. Learning to use formulas to solve simple arithmetic prob- lems. In Proceedings of the 54th Annual Meeting of the As- sociation for Computational Linguistics (Volume 1: Long Papers), volume 1, pages 2144-2153, 2016.","title":"Learning to use formulas to solve simple arithmetic problems","authors":"Mitra, Baral ;, Arindam Mitra, Chitta Baral","year":"2016","venue":"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Robaidek et al., 2018] Benjamin Robaidek, Rik Koncel- Kedziorski, and Hannaneh Hajishirzi. Data-driven meth- ods for solving algebra word problems. arXiv preprint arXiv:1804.10718, 2018.","title":"Data-driven methods for solving algebra word problems","authors":"Benjamin Robaidek, Rik Koncel-Kedziorski, Hannaneh Hajishirzi","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Roy and Roth, 2017] Subhro Roy and Dan Roth. Unit de- pendency graph and its application to arithmetic word problem solving. In Thirty-First AAAI Conference on Ar- tificial Intelligence, 2017.","title":"Unit dependency graph and its application to arithmetic word problem solving","authors":"Roy, Roth ;, Subhro Roy, Dan Roth","year":"2017","venue":"Thirty-First AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Roy and Roth, 2018] Subhro Roy and Dan Roth. Mapping to declarative knowledge for word problem solving. Trans- actions of the Association of Computational Linguistics, 6:159-172, 2018.","title":"Mapping to declarative knowledge for word problem solving","authors":"Roy, Roth ;, Subhro Roy, Dan Roth","year":"2018","venue":"Transactions of the Association of Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Shi et al., 2015] Shuming Shi, Yuehui Wang, Chin-Yew Lin, Xiaojiang Liu, and Yong Rui. Automatically solv- ing number word problems by semantic parsing and rea- soning. In Proceedings of the 2015 Conference on Em- pirical Methods in Natural Language Processing, pages 1132-1142, 2015.","title":"Automatically solving number word problems by semantic parsing and reasoning","authors":"Shuming Shi, Yuehui Wang, Chin-Yew Lin, Xiaojiang Liu, Yong Rui","year":"2015","venue":"Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Sutskever et al., 2014] Ilya Sutskever, Oriol Vinyals, and Quoc V Le. Sequence to sequence learning with neural networks. In Advances in neural information processing systems, pages 3104-3112, 2014.","title":"Quoc V Le. Sequence to sequence learning with neural networks","authors":"Sutskever","year":"2014","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Wang et al., 2017] Yan Wang, Xiaojiang Liu, and Shuming Shi. Deep neural solver for math word problems. In Pro- ceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 845-854, 2017.","title":"Deep neural solver for math word problems","authors":"Yan Wang, Xiaojiang Liu, Shuming Shi","year":"2017","venue":"Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Wang et al., 2018a] Lei Wang, Yan Wang, Deng Cai, Dongxiang Zhang, and Xiaojiang Liu. Translating math word problem to expression tree. In Proceedings of the 2018 Conference on Empirical Methods in Natural Lan- guage Processing, pages 1064-1069, 2018.","title":"Translating math word problem to expression tree","authors":"Wang","year":"2018","venue":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Wang et al., 2018b] Lei Wang, Dongxiang Zhang, Lianli Gao, Jingkuan Song, Long Guo, and Heng Tao Shen. Mathdqn: Solving arithmetic word problems via deep re- inforcement learning. 2018.","title":"Mathdqn: Solving arithmetic word problems via deep reinforcement learning","authors":"Wang","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Yuhui et al., 2010] Ma Yuhui, Zhou Ying, Cui Guangzuo, Ren Yun, and Huang Ronghuai. Frame-based calculus of solving arithmetic multi-step addition and subtraction word problems. In Education Technology and Computer Science (ETCS), 2010 Second International Workshop on, volume 2, pages 476-479. IEEE, 2010.","title":"Frame-based calculus of solving arithmetic multi-step addition and subtraction word problems","authors":"Ma Yuhui, Zhou Ying, Cui Guangzuo, Ren Yun, Huang Ronghuai","year":"2010","venue":"Education Technology and Computer Science (ETCS)","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Zhang et al., 2018] Dongxiang Zhang, Lei Wang, Nuo Xu, Bing Tian Dai, and Heng Tao Shen. The gap of seman- tic parsing: A survey on automatic math word problem solvers. arXiv preprint arXiv:1808.07290, 2018.","title":"The gap of semantic parsing: A survey on automatic math word problem solvers","authors":"Dongxiang Zhang, Lei Wang, Nuo Xu, Bing Tian Dai, Heng Tao Shen","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Zhou et al., 2015] Lipu Zhou, Shuaixiang Dai, and Liwei Chen. Learn to solve algebra word problems using quadratic programming. In Proceedings of the 2015 Con- ference on Empirical Methods in Natural Language Pro- cessing, pages 817-822, 2015.","title":"Learn to solve algebra word problems using quadratic programming","authors":"Lipu Zhou, Shuaixiang Dai, Liwei Chen","year":"2015","venue":"Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}