
SemanticallyAligned Universal TreeStructured Solver for Math Word Problems
A practical automatic textual math word problems (MWPs) solver should be...
read it

SemanticallyAligned Equation Generation for Solving and Reasoning Math Word Problems
Solving math word problems is a challenging task that requires accurate ...
read it

InterGPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoning
Geometry problem solving has attracted much attention in the NLP communi...
read it

Natural to formallanguage generation using Tensor Product Representations
Generating formallanguage represented by relational tuples, such as Lis...
read it

Globally Optimal Symbolic Regression
In this study we introduce a new technique for symbolic regression that ...
read it

A Flawed Dataset for Symbolic Equation Verification
Arabshahi, Singh, and Anandkumar (2018) propose a method for creating a ...
read it

Highperformance symbolicnumerics via multiple dispatch
As mathematical computing becomes more democratized in highlevel langua...
read it
NeuralSymbolic Solver for Math Word Problems with Auxiliary Tasks
Previous math word problem solvers following the encoderdecoder paradigm fail to explicitly incorporate essential math symbolic constraints, leading to unexplainable and unreasonable predictions. Herein, we propose NeuralSymbolic Solver (NSSolver) to explicitly and seamlessly incorporate different levels of symbolic constraints by auxiliary tasks. Our NSSolver consists of a problem reader to encode problems, a programmer to generate symbolic equations, and a symbolic executor to obtain answers. Along with target expression supervision, our solver is also optimized via 4 new auxiliary objectives to enforce different symbolic reasoning: a) selfsupervised number prediction task predicting both number quantity and number locations; b) commonsense constant prediction task predicting what prior knowledge (e.g. how many legs a chicken has) is required; c) program consistency checker computing the semantic loss between predicted equation and target equation to ensure reasonable equation mapping; d) duality exploiting task exploiting the quasi duality between symbolic equation generation and problem's partofspeech generation to enhance the understanding ability of a solver. Besides, to provide a more realistic and challenging benchmark for developing a universal and scalable solver, we also construct a new largescale MWP benchmark CM17K consisting of 4 kinds of MWPs (arithmetic, oneunknown linear, oneunknown nonlinear, equation set) with more than 17K samples. Extensive experiments on Math23K and our CM17k demonstrate the superiority of our NSSolver compared to stateoftheart methods.
READ FULL TEXT
Comments
There are no comments yet.