Clause-level Relationship-aware Math Word Problems Solver  

作　　者：Chang-Yang Wu Xin Lin Zhen-Ya Huang Yu Yin Jia-Yu Liu Qi Liu Gang Zhou 

机构地区：[1]Anhui Province Key Laboratory of Big Data Analysis and Application,School of Data Science,University of Science and Technology of China,Hefei 230026,China [2]Institute of Artificial Intelligence,Hefei Comprehensive National Science Center,Hefei 230088,China [3]Laboratory of Mathematical Engineering and Advanced Computing,Information Engineering University,Zhengzhou 450001,China

出　　处：《Machine Intelligence Research》2022年第5期425-438,共14页机器智能研究（英文版）

基　　金：supported by National Key Research and Development Program of China(No.2021YFF0901003);National Natural Science Foundation of China(Nos.61922073,U20A20229,and 62106244)。

摘　　要：Automatically solving math word problems,which involves comprehension,cognition,and reasoning,is a crucial issue in artificial intelligence research.Existing math word problem solvers mainly work on word-level relationship extraction and the generation of expression solutions while lacking consideration of the clause-level relationship.To this end,inspired by the theory of two levels of process in comprehension,we propose a novel clause-level relationship-aware math solver(CLRSolver)to mimic the process of human comprehension from lower level to higher level.Specifically,in the lower-level processes,we split problems into clauses according to their natural division and learn their semantics.In the higher-level processes,following human′s multi-view understanding of clause-level relationships,we first apply a CNN-based module to learn the dependency relationships between clauses from word relevance in a local view.Then,we propose two novel relationship-aware mechanisms to learn dependency relationships from the clause semantics in a global view.Next,we enhance the representation of clauses based on the learned clause-level dependency relationships.In expression generation,we develop a tree-based decoder to generate the mathematical expression.We conduct extensive experiments on two datasets,where the results demonstrate the superiority of our framework.

关 键 词：Artificial intelligence(AI) artificial neural network(ANN) computational mathematics machine intelligence machine learning 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] TP391.1[自动化与计算机技术—控制科学与工程]