2021

Towards Tractable Mathematical Reasoning: Challenges, Strategies, and Opportunities for Solving Math Word Problems

Faldu, Keyur, Sheth, Amit, Kikani, Prashant et al.

Understand

Mathematical reasoning would be one of the next frontiers for artificial intelligence to make significant progress.

The ongoing surge to solve math word problems (MWPs) and hence achieve better mathematical reasoning ability would continue to be a key line of research in the coming time.
We inspect non-neural and neural methods to solve math word problems narrated in a natural language.
We also highlight the ability of these methods to be generalizable, mathematically reasonable, interpretable, and explainable.

Built on

On the capabilities and limitations of reasoning for natural language understanding
Original
Daniel Khashabi, Erfan Sadeqi Azer, Tushar Khot, Ashish Sabharwal, and Dan Roth. 2019 · 1901
Earlier work this paper cites.
Analysing mathematical reasoning abilities of neural models
Original
David Saxton, Edward Grefenstette, Felix Hill, and Pushmeet Kohli. 2019 · 1904
Earlier work this paper cites.
Commonsense reasoning for natural language understanding: A survey of benchmarks, resources, and approaches
Original
Shane Storks, Qiaozi Gao, and Joyce Y Chai. 2019 · 1904
Earlier work this paper cites.
Mathqa: Towards interpretable math word problem solving with operation-based formalisms
Original
Aida Amini, Saadia Gabriel, Peter Lin, Rik Koncel-Kedziorski, Yejin Choi, and Hannaneh Hajishirzi. 2019 · 1905
Earlier work this paper cites.
Superglue: A stickier benchmark for general-purpose language understanding systems
Original
Alex Wang, Yada Pruksachatkun, Nikita Nangia, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy, and Samuel R Bowman. 2019 · 1905
Earlier work this paper cites.
Numnet: Machine reading comprehension with numerical reasoning
Original
Qiu Ran, Yankai Lin, Peng Li, Jie Zhou, and Zhiyuan Liu. 2019 · 1910
Earlier work this paper cites.
Deep learning for symbolic mathematics
Original
Guillaume Lample and François Charton. 2019 · 1912
Earlier work this paper cites.
Computers and thought
Edward A Feigenbaum, Julian Feldman, et al. 1963 · 1963
Earlier work this paper cites.
Natural language input for a computer problem solving system
Daniel G Bobrow. 1964 · 1964
Earlier work this paper cites.
Calculus word problems
Eugene Charniak. 1968 · 1968
Earlier work this paper cites.
An integrated model of skill in solving elementary word problems
Diane J Briars and Jill H Larkin. 1984 · 1984
Earlier work this paper cites.
Understanding and solving arithmetic word problems: A computer simulation
Charles R Fletcher. 1985 · 1985
Earlier work this paper cites.
A computer simulation of children’s arithmetic word-problem solving
Denise Dellarosa. 1986 · 1986
Earlier work this paper cites.
Mathematical reasoning in task solving
Johan Lithner. 2000 · 2000
Earlier work this paper cites.
Approximation with artificial neural networks
Balázs Csanád Csáji et al. 2001 · 2001
Earlier work this paper cites.
K-adapter: Infusing knowledge into pre-trained models with adapters
Original
Ruize Wang, Duyu Tang, Nan Duan, Zhongyu Wei, Xuanjing Huang, Guihong Cao, Daxin Jiang, Ming Zhou, et al. 2020 · 2002
Earlier work this paper cites.
Wt5?! training text-to-text models to explain their predictions
Original
Sharan Narang, Colin Raffel, Katherine Lee, Adam Roberts, Noah Fiedel, and Karishma Malkan. 2020 · 2004
Earlier work this paper cites.
Extended-hownet: A representational framework for concepts
Keh-Jiann Chen, Shu-Ling Huang, Yueh-Yin Shih, and Yi-Jun Chen. 2005 · 2005
Earlier work this paper cites.
Robust understanding of word problems with extraneous information
Yefim Bakman. 2007 · 2007
Earlier work this paper cites.
Observational learning
Albert Bandura. 2008 · 2008
Earlier work this paper cites.
Ape210k: A large-scale and template-rich dataset of math word problems
Original
Wei Zhao, Mingyue Shang, Yang Liu, Liang Wang, and Jingming Liu. 2020 · 2009
Earlier work this paper cites.
A framework for predicting, interpreting, and improving learning outcomes
Original
Chintan Donda, Sayan Dasgupta, Soma S Dhavala, Keyur Faldu, and Aditi Avasthi. 2020 · 2010
Earlier work this paper cites.

Similar

Reverse operation based data augmentation for solving math word problems
Original
Qianying Liu, Wenyu Guan, Sujian Li, Fei Cheng, Daisuke Kawahara, and Sadao Kurohashi. 2020 · 2010
Cited alongside, same era.
Semantically-aligned universal tree-structured solver for math word problems
Original
Jinghui Qin, Lihui Lin, Xiaodan Liang, Rumin Zhang, and Liang Lin. 2020 · 2010
Cited alongside, same era.
Frame-based calculus of solving arithmetic multi-step addition and subtraction word problems
Ma Yuhui, Zhou Ying, Cui Guangzuo, Ren Yun, and Huang Ronghuai. 2010 · 2010
Cited alongside, same era.
Thinking, fast and slow
Daniel Kahneman. 2011 · 2011
Cited alongside, same era.
Modeling math word problems with augmented semantic networks
Christian Liguda and Thies Pfeiffer. 2012 · 2012
Cited alongside, same era.
Mathematical reasoning: Analogies, metaphors, and images
Lyn D English. 2013 · 2013
Cited alongside, same era.
Machine-guided solution to mathematical word problems
Bussaba Amnueypornsakul and Suma Bhat. 2014 · 2014
Cited alongside, same era.
Learning to solve arithmetic word problems with verb categorization
Mohammad Javad Hosseini, Hannaneh Hajishirzi, Oren Etzioni, and Nate Kushman. 2014 · 2014
Cited alongside, same era.
Learning to automatically solve algebra word problems
Nate Kushman, Yoav Artzi, Luke Zettlemoyer, and Regina Barzilay. 2014 · 2014
Cited alongside, same era.
Parsing algebraic word problems into equations
Rik Koncel-Kedziorski, Hannaneh Hajishirzi, Ashish Sabharwal, Oren Etzioni, and Siena Dumas Ang. 2015 · 2015
Cited alongside, same era.
Designing a tag-based statistical math word problem solver with reasoning and explanation
Yi-Chung Lin, Chao-Chun Liang, Kuang-Yi Hsu, Chien-Tsung Huang, Shen-Yun Miao, Wei-Yun Ma, Lun-Wei Ku, Churn-Jung Liau, and Keh-Yih Su. 2015 · 2015
Cited alongside, same era.
Reasoning about quantities in natural language
Subhro Roy, Tim Vieira, and Dan Roth. 2015 · 2015
Cited alongside, same era.

Then

A meaning-based statistical english math word problem solver
Original
Chao-Chun Liang, Yu-Shiang Wong, Yi-Chung Lin, and Keh-Yih Su. 2018 · 2018
Later among the works it cites.
Data-driven methods for solving algebra word problems
Original
Benjamin Robaidek, Rik Koncel-Kedziorski, and Hannaneh Hajishirzi. 2018 · 2018
Later among the works it cites.
Mapping to declarative knowledge for word problem solving
Subhro Roy and Dan Roth. 2018 · 2018
Later among the works it cites.
Modeling intra-relation in math word problems with different functional multi-head attentions
Jierui Li, Lei Wang, Jipeng Zhang, Yan Wang, Bing Tian Dai, and Dongxiang Zhang. 2019 · 2019
Later among the works it cites.
Tree-structured decoding for solving math word problems
Qianying Liu, Wenyv Guan, Sujian Li, and Daisuke Kawahara. 2019 · 2019
Later among the works it cites.
A goal-driven tree-structured neural model for math word problems
Zhipeng Xie and Shichao Sun. 2019 · 2019
Later among the works it cites.
Auto generation of diagnostic assessments and their quality evaluation
Soma Dhavala, Chirag Bhatia, Joy Bose, Keyur Faldu, and Aditi Avasthi. 2020 · 2020
Later among the works it cites.
Commonsense reasoning for natural language processing
Maarten Sap, Vered Shwartz, Antoine Bosselut, Yejin Choi, and Dan Roth. 2020 · 2020
Later among the works it cites.
Graph-to-tree learning for solving math word problems
Jipeng Zhang, Lei Wang, Roy Ka-Wei Lee, Yi Bin, Yan Wang, Jie Shao, and Ee-Peng Lim. 2020 · 2020
Later among the works it cites.
A deep reinforcement learning approach to first-order logic theorem proving
Maxwell Crouse, Ibrahim Abdelaziz, Bassem Makni, Spencer Whitehead, Cristina Cornelio, Pavan Kapanipathi, Kavitha Srinivas, Veronika Thost, Michael Witbrock, and Achille Fokoue. 2021 · 2021
Closest in time.
Ki-bert: Infusing knowledge context for better language and domain understanding
Original
Keyur Faldu, Amit Sheth, Prashant Kikani, and Hemang Akabari. 2021 · 2021
Closest in time.
Semantics of the black-box: Can knowledge graphs help make deep learning systems more interpretable and explainable?
Manas Gaur, Keyur Faldu, and Amit Sheth. 2021 · 2021
Closest in time.
Solving arithmetic word problems with transformers and preprocessing of problem text
Original
Kaden Griffith and Jugal Kalita. 2021 · 2021
Closest in time.
Measuring mathematical problem solving with the math dataset
Original
Dan Hendrycks, Collin Burns, Saurav Kadavath, Akul Arora, Steven Basart, Eric Tang, Dawn Song, and Jacob Steinhardt. 2021 · 2021
Closest in time.
Mwp-bert: A strong baseline for math word problems
Original
Zhenwen Liang, Jipeng Zhang, Jie Shao, and Xiangliang Zhang. 2021 · 2021
Closest in time.
A diverse corpus for evaluating and developing english math word problem solvers
Original
Shen-Yun Miao, Chao-Chun Liang, and Keh-Yih Su. 2021 · 2021
Closest in time.
A reinforcement learning environment for mathematical reasoning via program synthesis
Original
Joseph Palermo, Johnny Ye, and Alok Singh. 2021 · 2021
Closest in time.
Are nlp models really able to solve simple math word problems?
Original
Arkil Patel, Satwik Bhattamishra, and Navin Goyal. 2021 · 2021
Closest in time.
Neural-symbolic solver for math word problems with auxiliary tasks
Original
Jinghui Qin, Xiaodan Liang, Yining Hong, Jianheng Tang, and Liang Lin. 2021 · 2021
Closest in time.
Knowledge-intensive language understanding for explainable ai
Amit Sheth, Manas Gaur, Kaushik Roy, and Keyur Faldu. 2021 · 2021
Closest in time.
Math word problem solving with explicit numerical values
Qinzhuo Wu, Qi Zhang, Zhongyu Wei, and Xuan-Jing Huang. 2021 · 2021
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…