A Tag-Based Statistical English Math Word Problem Solver with Understanding, Reasoning and Explanation

By Chao-Chun Liang, Kuang-Yi Hsu, Chien-Tsung Huang, Chung-Min Li, Shen-Yu Miao, Keh-Yih Su. 2016

25 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Giving BERT a Calculator: Finding Operations and Arguments with Reading Comprehension (2019, methodology): “Transferring from the DROP dataset further improved performance beyond that of Liang et al. (2016), a model specific to math word problems that uses rules over dependency trees.”
MathDQN: Solving Arithmetic Word Problems via Deep Reinforcement Learning (2018, methodology): “To improve the generality, tag-based approach (Liang et al. 2016) was proposed with map rules to convert identified variables and values into logic forms, which are further transformed into logic statements for inference.”
Template-Based Math Word Problem Solvers with Recursive Neural Networks (2019, methodology): “To improve the generality, tag-based approach (Liang et al. 2016) was proposed with map rules to convert identiﬁed variables and values into logic forms, which were further transformed into logic statements for inference.”
The Gap of Semantic Parsing: A Survey on Automatic Math Word Problem Solvers (2018, methodology): “all quantities and the main-goal are first identified by rules in LogicForm [28], [29] and explicitly associated with their roletags.”