A Knowledge-Aware Sequence-to-Tree Network for Math Word Problem Solving
With the advancements in natural language processing tasks, math word problem solving has received increasing attention. Previous methods have achieved promising results but ignore background common-sense knowledge not directly provided by the problem. In addition, during generation, they focus on local features while neglecting global information. To incorporate external knowledge and global expression information, we propose a novel knowledge-aware sequence-to-tree (KA-S2T) network in which the entities in the problem sequences and their categories are modeled as an entity graph. Based on this entity graph, a graph attention network is used to capture knowledge-aware problem representations. Further, we use a tree-structured decoder with a state aggregation mechanism to capture the long-distance dependency and global expression information. Experimental results on the Math23K dataset revealed that the KA-S2T model can achieve better performance than previously reported best results.
Code (0)
등록된 구현이 없습니다.
Tasks
Common Sense ReasoningDecoderGraph AttentionMathMath Word Problem SolvingSimilar Papers 제목 키워드 기반
Sequence to General Tree: Knowledge-Guided Geometry Word Problem Solving
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 contain basic arithmetic o…
MathTAMER: Tree-Aware Transformer for Handwritten Mathematical Expression Recognition
Handwritten Mathematical Expression Recognition (HMER) has extensive applications in automated grading and office automation. However, existing sequence-based decoding methods, which directly predict $\LaTeX$ sequences, …
Handwritten Mathmatical Expression RecognitionPredictionTesting Transformer Learnability on the Arithmetic Sequence of Rooted Trees
We study whether a Large Language Model can learn the deterministic sequence of trees generated by the iterated prime factorization of the natural numbers. Each integer is mapped into a rooted planar tree and the resulti…
Graph-to-Tree Neural Networks for Learning Structured Input-Output Translation with Applications to Semantic Parsing and Math Word Problem
The celebrated Seq2Seq technique and its numerous variants achieve excellent performance on many tasks such as neural machine translation, semantic parsing, and math word problem solving. However, these models either onl…
DecoderMachine TranslationMathMath Word Problem Solving+2Translating a Math Word Problem to a Expression Tree
Sequence-to-sequence (SEQ2SEQ) models have been successfully applied to automatic math word problem solving. Despite its simplicity, a drawback still remains: a math word problem can be correctly solved by more than one …
Machine TranslationMathMath Word Problem SolvingSemantic Parsing