A Meaning-Based Statistical English Math Word Problem Solver

  title={A Meaning-Based Statistical English Math Word Problem Solver},
  author={Chao-Chun Liang and Yu-Shiang Wong and Yi-Chung Lin and Keh-Yih Su},
We introduce MeSys, a meaning-based approach, for solving English math word problems (MWPs) via understanding and reasoning in this paper. It first analyzes the text, transforms both body and question parts into their corresponding logic forms, and then performs inference on them. The associated context of each quantity is represented with proposed role-tags (e.g., nsubj, verb, etc.), which provides the flexibility for annotating an extracted math quantity with its associated context… Expand
MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms
A large-scale dataset of math word problems and an interpretable neural math problem solver by learning to map problems to their operation programs and a new representation language to model operation programs corresponding to each math problem that aim to improve both the performance and the interpretability of the learned models. Expand
A Diverse Corpus for Evaluating and Developing English Math Word Problem Solvers
A metric to measure the lexicon usage diversity of a given MWP corpus is proposed, and it is demonstrated that ASDiv (Academia Sinica Diverse MWP Dataset) is more diverse than existing corpora. Expand
EquGener: A Reasoning Network for Word Problem Solving by Generating Arithmetic Equations
This work introduces a novel method where the participants first learn a dense representation of the problem description conditioned on the question in hand, and leverage this representation to generate the operands and operators in the appropriate order. Expand
Text2Math: End-to-end Parsing Text into Math Expressions
This work proposes Text2Math, a model for semantically parsing text into math expressions that aims to predict the complete math expression at once as a tree structure, where minimal manual efforts are involved in the process. Expand
Neural-Symbolic Solver for Math Word Problems with Auxiliary Tasks
  • Jinghui Qin, Xiaodan Liang, Yining Hong, Jianheng Tang, Liang Lin
  • Computer Science
  • 2021
This work proposes Neural-Symbolic Solver (NS-Solver) to explicitly and seamlessly incorporate different levels of symbolic constraints by auxiliary tasks, and constructs a new largescale MWP benchmark CM17K consisting of 4 kinds of MWPs with more than 17K samples. Expand
Sequence to General Tree: Knowledge-Guided Geometry Word Problem Solving
With the recent advancements in deep learning, neural solvers have gained promising results in solving math word problems. However, these SOTA solvers only generate binary expression trees thatExpand


A Tag-based English Math Word Problem Solver with Understanding, Reasoning and Explanation
This paper presents a meaning-based statistical math word problem (MWP) solver with understanding, reasoning and explanation. It comprises a web user interface and pipelined modules for analysing theExpand
Designing a Tag-Based Statistical Math Word Problem Solver with Reasoning and Explanation
A tag-based logic representation such that the system is less sensitive to the irrelevant information and could provide answer more precisely and a unified statistical framework for performing reasoning from the given text is proposed. Expand
Learning Fine-Grained Expressions to Solve Math Word Problems
A novel template-based method that learns the mappings between math concept phrases in math word problems and their math expressions from training data and does a fine-grained inference to obtain the final answer. Expand
Explanation Generation for a Math Word Problem Solver
This paper proposes a math operation (e.g., Summation, Addition, Subtraction, Multiplication, Division, etc.) oriented approach to explain how the answers are obtained for math word problems using a specific template to generate the text for each kind of math operator. Expand
Unit Dependency Graph and Its Application to Arithmetic Word Problem Solving
A decomposed model for inducing UDGs with minimal additional annotations is introduced, and it is shown that introduction of UDGs reduces the error of the solver by over 10 %, surpassing all existing systems for solving arithmetic word problems. Expand
Modeling Math Word Problems with Augmented Semantic Networks
This work proposes a model based on augmented semantic networks to represent the mathematical structure behind word problems that is able to understand and solve mathematical text problems from German primary school books and could be extended to other languages by exchanging the language model in the natural language processing module. Expand
Learning to Solve Arithmetic Word Problems with Verb Categorization
The paper analyzes the arithmetic-word problems “genre”, identifying seven categories of verbs used in such problems, and reports the first learning results on this task without reliance on predefined templates and makes the data publicly available. Expand
Solving General Arithmetic Word Problems
This is the first algorithmic approach that can handle arithmetic problems with multiple steps and operations, without depending on additional annotations or predefined templates, and it outperforms existing systems, achieving state of the art performance on benchmark datasets of arithmetic word problems. Expand
Parsing Algebraic Word Problems into Equations
This paper formalizes the problem of solving multi-sentence algebraic word problems as that of generating and scoring equation trees. We use integer linear programming to generate equation trees andExpand
Reasoning about Quantities in Natural Language
A computational approach is developed which is shown to successfully recognize and normalize textual expressions of quantities and is used to further develop algorithms to assist reasoning in the context of the aforementioned tasks. Expand