# Parsing Algebraic Word Problems into Equations

@article{KoncelKedziorski2015ParsingAW, title={Parsing Algebraic Word Problems into Equations}, author={Rik Koncel-Kedziorski and Hannaneh Hajishirzi and Ashish Sabharwal and Oren Etzioni and S. Ang}, journal={Transactions of the Association for Computational Linguistics}, year={2015}, volume={3}, pages={585-597} }

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 score their likelihood by learning local and global discriminative models. These models are trained on a small set of word problems and their answers, without any manual annotation, in order to choose the equation that best matches the problem text. We refer to the overall system as Alges. We… Expand

#### Topics from this paper

#### 91 Citations

Solving arithmetic word problems by scoring equations with recursive neural networks

- Computer Science
- Expert Syst. Appl.
- 2021

This work explores novel approaches to score candidate solution equations using tree-structured recursive neural network (Tree-RNN) configurations using more established sequential representations, and improves overall performance and outperforms sequential LSTMs on such more complex problems. 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

Tree-structured Decoding for Solving Math Word Problems

- Computer Science
- EMNLP/IJCNLP
- 2019

A tree-structured decoding method that generates the abstract syntax tree of the equation in a top-down manner and can automatically stop during decoding without a redundant stop token is proposed. Expand

Solving Math Word Problems by Scoring Equations with Recursive Neural Networks

- Computer Science
- ArXiv
- 2020

This work explores novel approaches to score candidate solution equations using tree-structured recursive neural network (Tree-RNN) configurations using more established sequential representations, and improves overall performance and outperforms sequential LSTMs on such more complex problems. Expand

Learning To Use Formulas To Solve Simple Arithmetic Problems

- Computer Science
- ACL
- 2016

A novel method to learn to use formulas to solve simple arithmetic word problems and beats the state-of-the-art by 86.07% of the problems in a corpus of standard primary school test questions. Expand

A Simple Arithmetic Calculator to Solve Single Sentence Mathematical Word Problems

- Computer Science
- ICITAM
- 2019

The work involves identification of problem types, simplification of the given word problem to extract the operators and the operands, mapping the operators to appropriate operands to create the mathematical expression and solve the query to generate the final result. Expand

Solving Arithmetic Word Problems Automatically Using Transformer and Unambiguous Representations

- Computer Science, Mathematics
- 2019 International Conference on Computational Science and Computational Intelligence (CSCI)
- 2019

The use of Transformer networks trained to translate math word problems to equivalent arithmetic expressions in infix, prefix, and postfix notations are outlined and most configurations outperform previously reported approaches on three of four datasets with significant increases in accuracy. Expand

Point to the Expression: Solving Algebraic Word Problems Using the Expression-Pointer Transformer Model

- Computer Science
- EMNLP
- 2020

A pure neural model, EPT, is proposed, which can address the expression fragmentation and the operand-context separation, and yields comparable performance to existing models using hand-crafted features, and achieves better performance than existing pure neural models by at most 40%. 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

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

#### References

SHOWING 1-10 OF 36 REFERENCES

Learn to Solve Algebra Word Problems Using Quadratic Programming

- Computer Science
- EMNLP
- 2015

This paper presents a new algorithm to automatically solve algebra word problems via analyzing a hypothesis space containing all possible equation systems generated by assigning the numbers in the word problem into a set of equation system templates extracted from the training data. 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

Learning to Automatically Solve Algebra Word Problems

- Computer Science
- ACL
- 2014

An approach for automatically learning to solve algebra word problems by reasons across sentence boundaries to construct and solve a system of linear equations, while simultaneously recovering an alignment of the variables and numbers to the problem text. 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

Inducing Probabilistic CCG Grammars from Logical Form with Higher-Order Unification

- Computer Science
- EMNLP
- 2010

This paper uses higher-order unification to define a hypothesis space containing all grammars consistent with the training data, and develops an online learning algorithm that efficiently searches this space while simultaneously estimating the parameters of a log-linear parsing model. Expand

Discriminative Reranking for Natural Language Parsing

- Computer Science
- Computational Linguistics
- 2005

The boosting approach to ranking problems described in Freund et al. (1998) is applied to parsing the Wall Street Journal treebank, and it is argued that the method is an appealing alternative-in terms of both simplicity and efficiency-to work on feature selection methods within log-linear (maximum-entropy) models. Expand

Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars

- Computer Science
- UAI
- 2005

A learning algorithm is described that takes as input a training set of sentences labeled with expressions in the lambda calculus and induces a grammar for the problem, along with a log-linear model that represents a distribution over syntactic and semantic analyses conditioned on the input sentence. Expand

A Linear Programming Formulation for Global Inference in Natural Language Tasks

- Computer Science
- CoNLL
- 2004

This work develops a linear programing formulation for this problem and evaluates it in the context of simultaneously learning named entities and relations to efficiently incorporate domain and task specific constraints at decision time, resulting in significant improvements in the accuracy and the "human-like" quality of the inferences. Expand

Automatically Solving Number Word Problems by Semantic Parsing and Reasoning

- Computer Science
- EMNLP
- 2015

A new meaning representation language is designed to bridge natural language text and math expressions and a CFG parser is implemented based on 9,600 semi-automatically created grammar rules. Expand

Learning to Parse Database Queries Using Inductive Logic Programming

- Computer Science
- AAAI/IAAI, Vol. 2
- 1996

Experimental results with a complete database-query application for U.S. geography show that CHILL is able to learn parsers that outperform a preexisting, hand-crafted counterpart, and provide direct evidence of the utility of an empirical approach at the level of a complete natural language application. Expand