paper-with-me

홈 › Papers

Introducing MathQA -- A Math-Aware Question Answering System

2019-06-28 · Moritz Schubotz, Philipp Scharpf, Kaushal Dudhat, Yash Nagar, Felix Hamborg, Bela Gipp

We present an open source math-aware Question Answering System based on Ask Platypus. Our system returns as a single mathematical formula for a natural language question in English or Hindi. This formulae originate from the knowledge-base Wikidata. We translate these formulae to computable data by integrating the calculation engine sympy into our system. This way, users can enter numeric values for the variables occurring in the formula. Moreover, the system loads numeric values for constants occurring in the formula from Wikidata. In a user study, our system outperformed a commercial computational mathematical knowledge engine by 13%. However, the performance of our system heavily depends on the size and quality of the formula data available in Wikidata. Since only a few items in Wikidata contained formulae when we started the project, we facilitated the import process by suggesting formula edits to Wikidata editors. With the simple heuristic that the first formula is significant for the article, 80% of the suggestions were correct.

📄 PDF Abstract BibTeX arXiv:1907.01642

Code (1)

ag-gipp/MathQa 공식 구현

Tasks

MathQuestion Answering

Similar Papers 제목 키워드 기반

Mining Mathematical Documents for Question Answering via Unsupervised Formula Labeling

2022-11-12 · Philipp Scharpf, Moritz Schubotz, Bela Gipp

The increasing number of questions on Question Answering (QA) platforms like Math Stack Exchange (MSE) signifies a growing information need to answer math-related questions. However, there is currently very little resear…

Entity LinkingKnowledge GraphsMathMathematical Question Answering+1

Weakly Supervised Formula Learner for Solving Mathematical Problems

2022-10-01 · COLING 2022 10 · Yuxuan Wu, Hideki Nakayama

Mathematical reasoning task is a subset of the natural language question answering task. Existing work suggested solving this task with a two-phase approach, where the model first predicts formulas from questions and the…

Mathematical ReasoningQuestion AnsweringWeakly-supervised Learning

MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models

2023-09-21 · Longhui Yu, Weisen Jiang, Han Shi, Jincheng Yu 외

Large language models (LLMs) have pushed the limits of natural language understanding and exhibited excellent problem-solving ability. Despite the great success, most existing open-source LLMs (e.g., LLaMA-2) are still f…

Arithmetic ReasoningGSM8KLanguage ModelingLanguage Modelling+4

SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step Reasoning

2023-08-01 · Ning Miao, Yee Whye Teh, Tom Rainforth

The recent progress in large language models (LLMs), especially the invention of chain-of-thought prompting, has made it possible to automatically answer questions by stepwise reasoning. However, when faced with more com…

GSM8KMathQuestion Answering

PersonaMath: Enhancing Math Reasoning through Persona-Driven Data Augmentation

2024-10-02 · Jing Luo, Run Luo, Longze Chen, Liang Zhu 외

While closed-source Large Language Models (LLMs) demonstrate strong mathematical problem-solving abilities, open-source models continue to struggle with such tasks. To bridge this gap, we propose a data augmentation appr…

Data AugmentationDiversityGSM8KMath+1