MATHion: Solving Math Word Problems with Logically Consistent Problems
Solving the math word problems (MWPs) is a challenging task. Some existing MWP solvers retrieve textually similar problems and draw on their solutions to solve the given problem. However, textually similar questions are not guaranteed to have similar solutions. And questions could share the same solution but with different descriptions. Therefore in this work, we investigate the logical consistency among different problems and propose a novel framework named MATHion which solves math word problems with logically consistent problems. Experimental results show that our method outperforms many strong baselines, including some pre-trained language model-based methods. Further analysis shows that our retrieval method can learn the logical similarity between questions and plays a key role in our model's performance.
Code (0)
등록된 구현이 없습니다.
Tasks
Language ModelingLanguage ModellingMathRetrievalSimilar Papers 제목 키워드 기반
Reverse Operation based Data Augmentation for Solving Math Word Problems
Automatically solving math word problems is a critical task in the field of natural language processing. Recent models have reached their performance bottleneck and require more high-quality data for training. We propose…
Data AugmentationMathMathematical ReasoningMath Word Problem SolvingSolving Math Word Problems by Combining Language Models With Symbolic Solvers
Automatically generating high-quality step-by-step solutions to math word problems has many applications in education. Recently, combining large language models (LLMs) with external tools to perform complex reasoning and…
GSM8KLanguage ModelingLanguage ModellingMathVerityMath: Advancing Mathematical Reasoning by Self-Verification Through Unit Consistency
Large Language Models (LLMs), combined with program-based solving techniques, are increasingly demonstrating proficiency in mathematical reasoning. For example, closed-source models such as OpenAI GPT-4 and Claude show e…
MathMathematical ReasoningMath Word Problem SolvingCLEVR-Math: A Dataset for Compositional Language, Visual and Mathematical Reasoning
We introduce CLEVR-Math, a multi-modal math word problems dataset consisting of simple math word problems involving addition/subtraction, represented partly by a textual description and partly by an image illustrating th…
MathMathematical ReasoningQuestion AnsweringVisual Question Answering+1Semantically-Aligned Equation Generation for Solving and Reasoning Math Word Problems
Solving math word problems is a challenging task that requires accurate natural language understanding to bridge natural language texts and math expressions. Motivated by the intuition about how human generates the equat…
DecoderMathMath Word Problem SolvingNatural Language Understanding+1