EqFix:通过实例修复LaTeX方程错误
EqFix: Fixing LaTeX Equation Errors by Examples
摘要:
LaTeX是一个广泛使用的文档准备系统。其强大的数学方程编辑能力或许是其在学术界受欢迎的主要原因。然而,有时,即使是专家用户也可能花费大量时间来修正错误的等式。在本文中,我们提出了EqFix,一个基于合成的修复系统的LaTeX方程。它采用了一套固定的规则,并可以建议可能的修复常见的错误,在LaTeX方程。提出了一种特定领域的语言来形式化地表达固定规则。固定规则可以从一组输入-输出示例中自动合成。还引入了一个扩展的松弛器,以提高EqFix的实用性。我们评估EqFix在现实世界的例子,发现它可以合成具有高泛化能力的规则。与最先进的字符串转换合成器相比,EqFix解决了37%以上的情况,并且花费了不到一半的合成时间。
英文摘要:
LaTeX is a widely-used document preparation system. Its powerful ability in mathematical equation editing is perhaps the main reason for its popularity in academia. Sometimes, however, even an expert user may spend much time fixing an erroneous equation. In this paper, we present EqFix, a synthesis-based repairing system for LaTeX equations. It employs a set of fixing rules and can suggest possible repairs for common errors in LaTeX equations. A domain-specific language is proposed for formally expressing the fixing rules. The fixing rules can be automatically synthesized from a set of input-output examples. An extension of relaxers is also introduced to enhance the practicality of EqFix. We evaluate EqFix on real-world examples and find that it can synthesize rules with high generalization ability. Compared with a state-of-the-art string transformation synthesizer, EqFix solved 37% more cases and spent less than half of their synthesis time.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。