Generalizing Math Word Problem Solvers via Solution Diversification

• URL: http://arxiv.org/abs/2212.00833v1
• Date: Thu, 1 Dec 2022 19:34:58 GMT
• Title: Generalizing Math Word Problem Solvers via Solution Diversification
• Authors: Zhenwen Liang, Jipeng Zhang, Lei Wang, Yan Wang, Jie Shao, Xiangliang Zhang
• Abstract summary: We design a new training framework for an MWP solver by introducing a solution buffer and a solution discriminator. Our framework is flexibly applicable to a wide setting of fully, semi-weakly and weakly supervised training for all Seq2Seq MWP solvers.
• Score: 56.2690023011738
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Current math word problem (MWP) solvers are usually Seq2Seq models trained by the (one-problem; one-solution) pairs, each of which is made of a problem description and a solution showing reasoning flow to get the correct answer. However, one MWP problem naturally has multiple solution equations. The training of an MWP solver with (one-problem; one-solution) pairs excludes other correct solutions, and thus limits the generalizability of the MWP solver. One feasible solution to this limitation is to augment multiple solutions to a given problem. However, it is difficult to collect diverse and accurate augment solutions through human efforts. In this paper, we design a new training framework for an MWP solver by introducing a solution buffer and a solution discriminator. The buffer includes solutions generated by an MWP solver to encourage the training data diversity. The discriminator controls the quality of buffered solutions to participate in training. Our framework is flexibly applicable to a wide setting of fully, semi-weakly and weakly supervised training for all Seq2Seq MWP solvers. We conduct extensive experiments on a benchmark dataset Math23k and a new dataset named Weak12k, and show that our framework improves the performance of various MWP solvers under different settings by generating correct and diverse solutions.

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)
• Learning by Analogy: Diverse Questions Generation in Math Word Problem [21.211970350827183]
  Solving math word problem (MWP) with AI techniques has recently made great progress with the success of deep neural networks (DNN) We argue that the ability of learning by analogy is essential for an MWP solver to better understand same problems which may typically be formulated in diverse ways. In this paper, we make a first attempt to solve MWPs by generating diverse yet consistent questions/equations.
  arXiv  Detail & Related papers  (2023-06-15T11:47:07Z)
• 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)
• A Mutual Information Maximization Approach for the Spurious Solution Problem in Weakly Supervised Question Answering [60.768146126094955]
  Weakly supervised question answering usually has only the final answers as supervision signals. There may exist many spurious solutions that coincidentally derive the correct answer, but training on such solutions can hurt model performance. We propose to explicitly exploit such semantic correlations by maximizing the mutual information between question-answer pairs and predicted solutions.
  arXiv  Detail & Related papers  (2021-06-14T05:47:41Z)
• WARM: A Weakly (+Semi) Supervised Model for Solving Math word Problems [21.501567886241087]
  Solving math word problems (MWPs) is an important and challenging problem in natural language processing. We propose a weakly supervised model for solving MWPs by requiring only the final answer as supervision. We demonstrate that our approach achieves accuracy gains of 4.5% and 32% over the state-of-the-art weakly supervised approach.
  arXiv  Detail & Related papers  (2021-04-14T09:25:38Z)
• Discovering Diverse Solutions in Deep Reinforcement Learning [84.45686627019408]
  Reinforcement learning algorithms are typically limited to learning a single solution of a specified task. We propose an RL method that can learn infinitely many solutions by training a policy conditioned on a continuous or discrete low-dimensional latent variable.
  arXiv  Detail & Related papers  (2021-03-12T04:54:31Z)
• 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)
• Neural Learning of One-of-Many Solutions for Combinatorial Problems in Structured Output Spaces [20.101005623256626]
  We argue that being oblivious to the presence of multiple solutions can severely hamper their training ability. We present a generic learning framework that adapts an existing prediction network for an RL problem to handle solution multiplicity.
  arXiv  Detail & Related papers  (2020-08-27T08:37:01Z)
• Pareto Multi-Task Learning [53.90732663046125]
  Multi-task learning is a powerful method for solving multiple correlated tasks simultaneously. It is often impossible to find one single solution to optimize all the tasks, since different tasks might conflict with each other. Recently, a novel method is proposed to find one single Pareto optimal solution with good trade-off among different tasks by casting multi-task learning as multiobjective optimization.
  arXiv  Detail & Related papers  (2019-12-30T08:58:40Z)

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.