Modeling Intra-Relation in Math Word Problems with Different Functional Multi-Head Attentions

Abstract

Several deep learning models have been proposed for solving math word problems (MWPs) automatically. Although these models have the ability to capture features without manual efforts, their approaches to capturing features are not specifically designed for MWPs. To utilize the merits of deep learning models with simultaneous consideration of MWPs' specific features, we propose a group attention mechanism to extract global features, quantity-related features, quantitypair features and question-related features in MWPs respectively. The experimental results show that the proposed approach performs significantly better than previous state-of-the-art methods, and boost performance from 66.9% to 69.5% on Math23K with training-test split, from 65.8% to 66.9% on Math23K with 5-fold cross-validation and from 69.2% to 76.1% on MAWPS.

Graph-to-Tree Neural Networks for Learning Structured Input-Output Translation with Applications to Semantic Parsing and Math Word Problem

“…Inspired by the great success of Seq2Seq models in Neural Machine Translation, deep-learning based methods are intensively explored by researchers in the equation generation (Wang et al, 2017;Ling et al, 2017;Li et al, 2018Li et al, , 2019Zou and Lu, 2019;Xie and Sun, 2019). However, different forms of equations can be formed to solve the same math problem, which often makes models fail.…”

“…We report the solution accuracy for each baseline in test set. On MAWPS, our baselines are: i) Retrieval, Classification, and Seq2Seq (Robaidek et al, 2018); ii) Seq2Tree (Dong and Lapata, 2016); iii) Graph2Seq (Xu et al, 2018a); iv) MathDQN ; v) T-RNN ; vi) Group-Att (Li et al, 2019). On MATHQA, our baselines are: i) Sequence-to-program (Amini et al, 2019); ii) TP-N2F (Chen et al, 2019a); iii) Seq2Seq, Seq2Tree and Graph2Seq.…”

“…It is worth noting that our hierarchical tree decoder directly generates original mathematical expressions, which faithfully reflect reasoning steps when building math equations. However, state-ofthe-art math word problem solvers like Group-Att (Li et al, 2019) or T-RNN have achieved high performance by utilizing Equation Normalization (EN) proposed by to keep structures of output equations unified. This method can improve solution accuracy because it reduces the difficulty of equation generation.…”

Math Word Problem Generation with Mathematical Consistency and Problem Context Constraints

“…To date, there exist limited literature on MWP generation. Most prior works focus on automatically answering MWPs, e.g., (Li et al, 2019(Li et al, , 2020Qin et al, 2020;Shi et al, 2015;Roy and Roth, 2015;Wu et al, 2020a) instead of generating them (Nandhini and Balasundaram, 2011;Williams, 2011;Polozov et al, 2015;Deane and Sheehan, 2003). Existing MWP generation methods also often generate MWPs that either are of unsatisfactory language quality or fail to preserve information on math equations and contexts that need to be embedded in them.…”

Solving arithmetic word problems by scoring equations with recursive neural networks

“…The research community has focused in solving mainly two types of mathematical word problems: arithmetic word problems (Hosseini et al, 2014;Mitra & Baral, 2016;Wang et al, 2017;Li et al, 2019;Chiang & Chen, 2019) and algebraic word problems (Kushman et al, 2014;Shi et al, 2015;Ling et al, 2017;Amini et al, 2019). Arithmetic word problems can be solved using basic mathematical operations (+, −, ×, ÷) and involve a single unknown variable.…”