# A Meaning-Based Statistical English Math Word Problem Solver

@inproceedings{Liang2018AMS, 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}, booktitle={NAACL}, year={2018} }

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

#### Figures, Tables, and Topics from this paper

#### 6 Citations

MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms

- Computer Science
- NAACL
- 2019

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

- Computer Science
- ACL
- 2020

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

- Computer Science
- PACLIC
- 2018

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

- Computer Science
- EMNLP/IJCNLP
- 2019

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

- Computer Science
- ACL/IJCNLP
- 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

- Computer Science
- ACL/IJCNLP
- 2021

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 that… Expand

#### References

SHOWING 1-10 OF 29 REFERENCES

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

- Computer Science
- NAACL
- 2016

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 the… Expand

Designing a Tag-Based Statistical Math Word Problem Solver with Reasoning and Explanation

- Computer Science
- ROCLING/IJCLCLP
- 2015

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

- Computer Science
- EMNLP
- 2017

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

- Computer Science, Mathematics
- ROCLING/IJCLCLP
- 2015

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

- Computer Science
- AAAI
- 2017

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

- Computer Science
- NLDB
- 2012

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

- Computer Science
- EMNLP
- 2014

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

- Computer Science
- EMNLP
- 2015

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

- Computer Science
- Transactions of the Association for Computational Linguistics
- 2015

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 and… Expand

Reasoning about Quantities in Natural Language

- Computer Science
- Transactions of the Association for Computational Linguistics
- 2015

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