Parsing Algebraic Word Problems into Equations
نویسندگان
چکیده
منابع مشابه
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 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 choo...
متن کاملAlgebraic properties of word equations
In [2], Aleksi Saarela has introduced a new approach to word equations that is based on linear-algebraic properties of polynomials encoding the equations and their solutions. In this paper we develop further this approach and take into account other algebraic properties of polynomials, namely their factorization. This, in particular, allows to improve the bound for the number of independent equ...
متن کاملBoundary Algebraic Equations for Lattice Problems
Boundary algebraic equations corresponding to Dirichlet boundary-value problems on lattices are introduced. These equations are based on the lattice Green’s function, from which discrete singleand double-layer potentials are derived. Structurally, the boundary algebraic equations are similar to the boundary integral equations of classical potential theory. Numerical experiments indicate that bo...
متن کاملA Method for Solving Convex Quadratic Programming Problems Based on Differential-algebraic equations
In this paper, a new model based on differential-algebraic equations(DAEs) for solving convex quadratic programming(CQP) problems is proposed. It is proved that the new approach is guaranteed to generate optimal solutions for this class of optimization problems. This paper also shows that the conventional interior point methods for solving (CQP) problems can be viewed as a special case of the n...
متن کاملAutomatically Solving Number Word Problems by Semantic Parsing and Reasoning
This paper presents a semantic parsing and reasoning approach to automatically solving math word problems. A new meaning representation language is designed to bridge natural language text and math expressions. A CFG parser is implemented based on 9,600 semi-automatically created grammar rules. We conduct experiments on a test set of over 1,500 number word problems (i.e., verbally expressed num...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Transactions of the Association for Computational Linguistics
سال: 2015
ISSN: 2307-387X
DOI: 10.1162/tacl_a_00160