DISK: Domain-constrained Instance Sketch for Math Word Problem Generation

04/10/2022
by   Tianyang Cao, et al.
0

A math word problem (MWP) is a coherent narrative which reflects the underlying logic of math equations. Successful MWP generation can automate the writing of mathematics questions. Previous methods mainly generate MWP text based on inflexible pre-defined templates. In this paper, we propose a neural model for generating MWP text from math equations. Firstly, we incorporate a matching model conditioned on the domain knowledge to retrieve a MWP instance which is most consistent with the ground-truth, where the domain is a latent variable extracted with a domain summarizer. Secondly, by constructing a Quantity Cell Graph (QCG) from the retrieved MWP instance and reasoning over it, we improve the model's comprehension of real-world scenarios and derive a domain-constrained instance sketch to guide the generation. Besides, the QCG also interacts with the equation encoder to enhance the alignment between math tokens (e.g., quantities and variables) and MWP text. Experiments and empirical analysis on educational MWP set show that our model achieves impressive performance in both automatic evaluation metrics and human evaluation metrics.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/13/2020

Mathematical Word Problem Generation from Commonsense Knowledge Graph and Equations

There is an increasing interest in the use of automatic mathematical wor...
research
12/14/2020

Generating Math Word Problems from Equations with Topic Controlling and Commonsense Enforcement

Recent years have seen significant advancement in text generation tasks ...
research
05/19/2016

A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues

Sequential data often possesses a hierarchical structure with complex de...
research
08/17/2020

Evaluating for Diversity in Question Generation over Text

Generating diverse and relevant questions over text is a task with wides...
research
08/31/2019

Quantity Tagger: A Latent-Variable Sequence Labeling Approach to Solving Addition-Subtraction Word Problems

An arithmetic word problem typically includes a textual description cont...
research
07/23/2019

Learning to Select, Track, and Generate for Data-to-Text

We propose a data-to-text generation model with two modules, one for tra...

Please sign up or login with your details

Forgot password? Click here to reset