Non-Autoregressive Math Word Problem Solver with Unified Tree Structure
- URL: http://arxiv.org/abs/2305.04556v2
- Date: Sat, 28 Oct 2023 07:09:38 GMT
- Title: Non-Autoregressive Math Word Problem Solver with Unified Tree Structure
- Authors: Yi Bin, Mengqun Han, Wenhao Shi, Lei Wang, Yang Yang, See-Kiong Ng,
Heng Tao Shen
- Abstract summary: We propose a novel non-autoregressive solver, named textitMWP-NAS, to parse the problem and deduce the solution expression based on the unified tree.
The results from extensive experiments conducted on Math23K and MAWPS demonstrate the effectiveness of our proposed MWP-NAS.
- Score: 62.869481432887106
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Existing MWP solvers employ sequence or binary tree to present the solution
expression and decode it from given problem description. However, such
structures fail to handle the variants that can be derived via mathematical
manipulation, e.g., $(a_1+a_2) * a_3$ and $a_1 * a_3+a_2 * a_3$ can both be
possible valid solutions for a same problem but formulated as different
expression sequences or trees. The multiple solution variants depicting
different possible solving procedures for the same input problem would raise
two issues: 1) making it hard for the model to learn the mapping function
between the input and output spaces effectively, and 2) wrongly indicating
\textit{wrong} when evaluating a valid expression variant. To address these
issues, we introduce a unified tree structure to present a solution expression,
where the elements are permutable and identical for all the expression
variants. We propose a novel non-autoregressive solver, named \textit{MWP-NAS},
to parse the problem and deduce the solution expression based on the unified
tree. For evaluating the possible expression variants, we design a path-based
metric to evaluate the partial accuracy of expressions of a unified tree. The
results from extensive experiments conducted on Math23K and MAWPS demonstrate
the effectiveness of our proposed MWP-NAS. The codes and checkpoints are
available at: \url{https://github.com/mengqunhan/MWP-NAS}.
Related papers
- Solving Math Word Problem with Problem Type Classification [12.700472956406005]
Math word problems (MWPs) require analyzing text descriptions and generating mathematical equations to derive solutions.
Existing works focus on solving MWPs with two types of solvers: tree-based solver and large language model (LLM) solver.
This paper utilizes multiple ensemble approaches to improve MWP-solving ability.
arXiv Detail & Related papers (2023-08-26T10:35:16Z) - Structure-Unified M-Tree Coding Solver for MathWord Problem [57.825176412485504]
In previous work, models designed by taking into account the properties of the binary tree structure of mathematical expressions at the output side have achieved better performance.
In this paper, we propose the Structure-Unified M-Tree Coding Coding (S-UMCr), which applies a tree with any M branches (M-tree) to unify the output structures.
Experimental results on the widely used MAWPS and Math23K datasets have demonstrated that SUMC-r not only outperforms several state-of-the-art models but also performs much better under low-resource conditions.
arXiv Detail & Related papers (2022-10-22T12:20:36Z) - Tackling Math Word Problems with Fine-to-Coarse Abstracting and
Reasoning [22.127301797950572]
We propose to model a math word problem in a fine-to-coarse manner to capture both the local fine-grained information and the global logical structure of it.
Our model is naturally sensitive to local variations and can better generalize to unseen problem types.
arXiv Detail & Related papers (2022-05-17T12:14:44Z) - LogicSolver: Towards Interpretable Math Word Problem Solving with
Logical Prompt-enhanced Learning [135.8654475934613]
We first construct a high-quality MWP dataset named InterMWP which consists of 11,495 MWPs.
We propose a novel approach with logical prompt and interpretation, called Logicr.
With these improved semantic representations, our Logicr generates corresponding solution expressions and interpretable knowledge in accord with the generated solution expressions.
arXiv Detail & Related papers (2022-05-17T11:01:52Z) - Learning by Fixing: Solving Math Word Problems with Weak Supervision [70.62896781438694]
Previous neural solvers of math word problems (MWPs) are learned with full supervision and fail to generate diverse solutions.
We introduce a textitweakly-supervised paradigm for learning MWPs.
Our method only requires the annotations of the final answers and can generate various solutions for a single problem.
arXiv Detail & Related papers (2020-12-19T03:10:21Z) - Semantically-Aligned Universal Tree-Structured Solver for Math Word
Problems [129.90766822085132]
A practical automatic textual math word problems (MWPs) solver should be able to solve various textual MWPs.
We propose a simple but efficient method called Universal Expression Tree (UET) to make the first attempt to represent the equations of various MWPs uniformly.
Then a semantically-aligned universal tree-structured solver (SAU-r) based on an encoder-decoder framework is proposed to resolve multiple types of MWPs in a unified model.
arXiv Detail & Related papers (2020-10-14T06:27:07Z) - Solving Arithmetic Word Problems by Scoring Equations with Recursive
Neural Networks [25.08023032443234]
Recent works use automatic extraction and ranking of candidate solution equations providing the answer to arithmetic word problems.
In this work, we explore novel approaches to score such candidate solution equations using Tree-RNN configurations.
Our proposed method consists of transforming the mathematical expression of the equation into an expression tree.
arXiv Detail & Related papers (2020-09-11T19:48:42Z) - AMR Parsing via Graph-Sequence Iterative Inference [62.85003739964878]
We propose a new end-to-end model that treats AMR parsing as a series of dual decisions on the input sequence and the incrementally constructed graph.
We show that the answers to these two questions are mutually causalities.
We design a model based on iterative inference that helps achieve better answers in both perspectives, leading to greatly improved parsing accuracy.
arXiv Detail & Related papers (2020-04-12T09:15:21Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.